Add SOMA and G1 model support
This commit is contained in:
Richard Palethorpe
parent
dedbe1066a
commit
92341f3194
87
README.md
87
README.md
@ -4,14 +4,24 @@ GGML/C++ implementation of NVIDIA's Kimodo text-to-motion model.
|
|||||||
|
|
||||||
## Status
|
## Status
|
||||||
|
|
||||||
`Kimodo-SMPLX-RP-v1` accepts either a UTF-8 prompt or a precomputed LLM2Vec
|
The five released Kimodo motion checkpoints accept either a UTF-8 prompt or a
|
||||||
embedding and generates unconstrained SMPL-X22 local rotations and root
|
precomputed LLM2Vec embedding and generate local rotations plus root
|
||||||
translations on CPU or Vulkan. The text encoder uses eight-layer Vulkan chunks
|
translations on CPU or Vulkan:
|
||||||
by default; set `KIMODO_TEXT_LAYER_CHUNK=1..32` to tune VRAM use.
|
|
||||||
|
- SMPL-X RP v1: 22 joints
|
||||||
|
- SOMA RP/SEED v1.1: the predicted compact 30-joint control skeleton
|
||||||
|
- G1 RP/SEED v1: 34 Unitree G1 joints
|
||||||
|
|
||||||
|
NVIDIA's Python API expands SOMA's predicted 30 joints to a relaxed-hand
|
||||||
|
77-joint presentation skeleton. The native API currently returns the 30 joints
|
||||||
|
the model actually predicts. The text encoder uses eight-layer Vulkan chunks by
|
||||||
|
default; set `KIMODO_TEXT_LAYER_CHUNK=1..32` to tune VRAM use.
|
||||||
|
|
||||||
Included: checked GGUF loading, safetensors conversion, DDIM sampling, C/C++
|
Included: checked GGUF loading, safetensors conversion, DDIM sampling, C/C++
|
||||||
APIs, CPU/Vulkan parity tests, and a local text-to-motion demo. Constraints,
|
APIs, conditioned multi-prompt transitions, CPU/Vulkan parity tests,
|
||||||
SOMA, G1, GLB export, and quantised models are not implemented yet.
|
skeleton-only GLB export, and a local text-to-motion demo. General constraint
|
||||||
|
input, 77-joint SOMA expansion, skinned-mesh GLB export, and quantised models
|
||||||
|
are not implemented yet.
|
||||||
|
|
||||||
## Build and test on Linux
|
## Build and test on Linux
|
||||||
|
|
||||||
@ -21,7 +31,7 @@ support. GGML is a pinned Git submodule:
|
|||||||
|
|
||||||
```sh
|
```sh
|
||||||
git submodule update --init --recursive
|
git submodule update --init --recursive
|
||||||
scripts/download_gguf_weights.sh --output "$PWD"
|
scripts/download_gguf_weights.sh --output "$PWD" --model soma-rp-v1.1
|
||||||
cmake --preset debug
|
cmake --preset debug
|
||||||
cmake --build --preset debug
|
cmake --build --preset debug
|
||||||
ctest --preset debug
|
ctest --preset debug
|
||||||
@ -56,8 +66,9 @@ to the process. The GGUF parser fuzzer requires Clang.
|
|||||||
|
|
||||||
`include/kimodo/kimodo_capi.h` is the C API. Model loading checks the motion
|
`include/kimodo/kimodo_capi.h` is the C API. Model loading checks the motion
|
||||||
GGUF and text bundle before inference. Use `kimodo_generate_embedding` for
|
GGUF and text bundle before inference. Use `kimodo_generate_embedding` for
|
||||||
4096 F32 values or `kimodo_generate` for text. Both return SMPL-X22 root
|
4096 F32 values or `kimodo_generate` for text. Both return the selected model's
|
||||||
translations and local XYZW rotations.
|
root translations and local XYZW rotations; query the joint count from the
|
||||||
|
result rather than assuming a fixed skeleton.
|
||||||
|
|
||||||
## Demo
|
## Demo
|
||||||
|
|
||||||
@ -69,27 +80,43 @@ go run ./demo -addr 0.0.0.0:8094
|
|||||||
|
|
||||||
Open `http://localhost:8094`. The left sidebar contains the prompt and a
|
Open `http://localhost:8094`. The left sidebar contains the prompt and a
|
||||||
persistent history; choosing a previous animation restores its prompt for a
|
persistent history; choosing a previous animation restores its prompt for a
|
||||||
new generation.
|
new generation. Every successful animation also writes a standalone
|
||||||
|
`animation.glb` beside its raw streams, for example
|
||||||
|
`demo-output/<animation-id>/animation.glb`. It contains the selected animated
|
||||||
|
node hierarchy (no mesh), ready to copy into a Three.js project. It is also
|
||||||
|
available from `/api/animations/<animation-id>/animation.glb` while the demo
|
||||||
|
is running.
|
||||||
|
|
||||||
## Weights
|
## Weights
|
||||||
|
|
||||||
Ready-to-run native GGML weights are published under the Hugging Face
|
Ready-to-run native GGML weights are published under the Hugging Face
|
||||||
`LocalAI-io` organisation (not GitHub's `localai-org`). The reusable
|
`LocalAI-io` organisation (not GitHub's `localai-org`). The reusable
|
||||||
[Llama-3-Kimodo-GGML](https://huggingface.co/LocalAI-io/Llama-3-Kimodo-GGML)
|
[Llama-3-Kimodo-GGML](https://huggingface.co/LocalAI-io/Llama-3-Kimodo-GGML)
|
||||||
text encoder and the upstream-linked
|
text encoder is separate from the four redistributable motion repositories,
|
||||||
[Kimodo-SMPLX-RP-v1-GGML](https://huggingface.co/LocalAI-io/Kimodo-SMPLX-RP-v1-GGML)
|
each of which preserves a one-to-one relationship to its NVIDIA upstream:
|
||||||
diffusion model are separate, so users download rather than recreate them:
|
|
||||||
|
- [Kimodo-SOMA-RP-v1.1-GGML](https://huggingface.co/LocalAI-io/Kimodo-SOMA-RP-v1.1-GGML)
|
||||||
|
- [Kimodo-SOMA-SEED-v1.1-GGML](https://huggingface.co/LocalAI-io/Kimodo-SOMA-SEED-v1.1-GGML)
|
||||||
|
- [Kimodo-G1-RP-v1-GGML](https://huggingface.co/LocalAI-io/Kimodo-G1-RP-v1-GGML)
|
||||||
|
- [Kimodo-G1-SEED-v1-GGML](https://huggingface.co/LocalAI-io/Kimodo-G1-SEED-v1-GGML)
|
||||||
|
|
||||||
|
Download one or repeat `--model` to install several:
|
||||||
|
|
||||||
```sh
|
```sh
|
||||||
scripts/download_gguf_weights.sh --output "$PWD"
|
scripts/download_gguf_weights.sh --output "$PWD" \
|
||||||
|
--model soma-rp-v1.1 --model g1-rp-v1
|
||||||
```
|
```
|
||||||
|
|
||||||
The installer verifies each published manifest and SHA-256 hashes. Use
|
The installer verifies each published manifest and SHA-256 hashes. Use
|
||||||
`--motion-only` when supplying a precomputed 4096-float LLM2Vec embedding.
|
`--motion-only` when supplying a precomputed 4096-float LLM2Vec embedding.
|
||||||
|
SMPL-X RP is deliberately absent from the published-weight installer: its
|
||||||
|
internal-R&D licence prohibits distributing derivative models, so it must be
|
||||||
|
converted locally after the user obtains the upstream checkpoint under its
|
||||||
|
gated terms.
|
||||||
|
|
||||||
The GGUF bundle includes converted Meta Llama 3 material and Kimodo is
|
The text bundle includes converted Meta Llama 3 material and retains its
|
||||||
non-commercial research-only. Review the published model card and upstream
|
separate terms. Review every selected model card before downloading or
|
||||||
licences before downloading or redistributing.
|
redistributing.
|
||||||
|
|
||||||
## License
|
## License
|
||||||
|
|
||||||
@ -97,6 +124,22 @@ The C++ port and its original tooling are licensed under Apache-2.0; see
|
|||||||
[LICENSE](LICENSE). GGML and the model weights retain their respective
|
[LICENSE](LICENSE). GGML and the model weights retain their respective
|
||||||
licences.
|
licences.
|
||||||
|
|
||||||
|
| Motion checkpoint | Upstream terms | Commercial use |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| Kimodo-SMPLX-RP-v1 | [NVIDIA Internal Scientific Research and Development Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/) | No; internal, non-production R&D only; derivative model redistribution is prohibited |
|
||||||
|
| SOMA RP/SEED v1.1 | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/) | Permitted by the model licence |
|
||||||
|
| G1 RP/SEED v1 | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/) | Permitted by the model licence |
|
||||||
|
|
||||||
|
The SMPL-X warning is about NVIDIA's trained Kimodo checkpoint, not the mere
|
||||||
|
fact that its output uses an SMPL-X-shaped 22-joint hierarchy. Converting that
|
||||||
|
checkpoint to GGUF is a new runtime representation of the same weights and does
|
||||||
|
not replace its licence. Skeleton names, parent links, and the Apache-2.0 port
|
||||||
|
source do not by themselves make the SOMA or G1 checkpoints non-commercial.
|
||||||
|
The SMPL-X Hugging Face metadata, model card, and access terms identify the
|
||||||
|
internal-R&D licence; treat those restrictive terms as controlling even though
|
||||||
|
an apparently inconsistent `LICENSE` file has also appeared in that upstream
|
||||||
|
repository.
|
||||||
|
|
||||||
### Regenerating the bundle
|
### Regenerating the bundle
|
||||||
|
|
||||||
This is only needed to reproduce a conversion. The SMPL-X checkpoint and Llama
|
This is only needed to reproduce a conversion. The SMPL-X checkpoint and Llama
|
||||||
@ -105,8 +148,9 @@ authenticating, download the exact revisions and hash manifests with:
|
|||||||
|
|
||||||
```sh
|
```sh
|
||||||
nix develop path:. --command hf auth login
|
nix develop path:. --command hf auth login
|
||||||
nix develop path:. --command scripts/download_weights.sh \
|
scripts/download_weights.sh --output "$PWD/models" --with-text \
|
||||||
--output "$PWD/models" --with-text
|
--model smplx-rp-v1 --model soma-rp-v1.1 --model soma-seed-v1.1 \
|
||||||
|
--model g1-rp-v1 --model g1-seed-v1
|
||||||
```
|
```
|
||||||
|
|
||||||
Convert the local LLM2Vec model to the native component bundle with:
|
Convert the local LLM2Vec model to the native component bundle with:
|
||||||
@ -120,9 +164,10 @@ Validate a prospective release without network access, then explicitly upload
|
|||||||
it from an account allowed to publish to `LocalAI-io`:
|
it from an account allowed to publish to `LocalAI-io`:
|
||||||
|
|
||||||
```sh
|
```sh
|
||||||
nix develop path:. --command python scripts/publish_gguf.py --component motion
|
|
||||||
nix develop path:. --command python scripts/publish_gguf.py --component motion \
|
nix develop path:. --command python scripts/publish_gguf.py --component motion \
|
||||||
--upload --confirm-upstream-licences
|
--motion-model soma-rp-v1.1
|
||||||
|
nix develop path:. --command python scripts/publish_gguf.py --component motion \
|
||||||
|
--motion-model soma-rp-v1.1 --upload --confirm-upstream-licences
|
||||||
nix develop path:. --command python scripts/publish_gguf.py --component text \
|
nix develop path:. --command python scripts/publish_gguf.py --component text \
|
||||||
--upload --confirm-upstream-licences
|
--upload --confirm-upstream-licences
|
||||||
```
|
```
|
||||||
|
|||||||
@ -1,20 +1,21 @@
|
|||||||
<!doctype html><html lang="en"><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1"><title>Kimodo text to motion</title>
|
<!doctype html><html lang="en"><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1"><title>Kimodo text to motion</title>
|
||||||
<style>
|
<style>
|
||||||
:root{color-scheme:dark;font-family:Inter,system-ui,sans-serif;background:#10131b;color:#f2f5fb}body{margin:0;overflow:hidden;background:#10131b}main{width:100vw;height:100vh;display:grid;grid-template-columns:360px minmax(0,1fr)}.sidebar{padding:24px 18px;display:flex;flex-direction:column;gap:18px;overflow-y:auto;overflow-x:hidden;background:radial-gradient(circle at 0 0,#293b62,transparent 32rem),#141a27;border-right:1px solid #2b354b}h1{font-size:2rem;letter-spacing:-.05em;margin:0}.eyebrow{font-size:.7rem;text-transform:uppercase;letter-spacing:.14em;color:#9bb8ff;margin-bottom:8px}.card{background:#171c28dd;border:1px solid #2b354b;border-radius:14px;overflow:hidden}.stage{min-width:0;min-height:0;display:flex;flex-direction:column;background:#0c1019}canvas{display:block;width:100%;height:100%;flex:1;min-height:0;background:linear-gradient(#111b31,#0c1019);cursor:grab;touch-action:none}canvas.dragging{cursor:grabbing}.controls{padding:14px 18px;display:flex;align-items:center;gap:10px;flex-wrap:wrap;border-top:1px solid #2b354b}.promptbox{padding:16px;display:grid;gap:10px}.promptbox textarea{min-height:110px;resize:none;overflow:hidden}textarea,input{box-sizing:border-box;width:100%;border:1px solid #35415b;border-radius:10px;background:#0d121d;color:#f2f5fb;padding:10px;font:inherit}button{border:0;border-radius:999px;padding:10px 16px;background:#9bb8ff;color:#10131b;font:inherit;font-weight:700;cursor:pointer}button:disabled{opacity:.5;cursor:wait}.readout,.hint{color:#a9b3c8;font-size:.88rem}.gallery{padding:4px;display:grid;gap:8px;align-content:start}.history{flex:none;min-height:0;overflow:visible}.gallery h2{font-size:1rem;margin:8px}.item{width:100%;background:#101622;border:1px solid #2c3750;border-radius:12px;padding:11px;text-align:left;color:#e8eefc}.item:hover,.item.active{border-color:#9bb8ff;background:#19233a}.item p{margin:0 0 6px;font-size:.88rem;line-height:1.35}.status{font-size:.75rem;color:#a9b3c8}.error{color:#ffacac;display:-webkit-box;-webkit-line-clamp:3;-webkit-box-orient:vertical;overflow:hidden}.camera{flex:1 1 100%;color:#a9b3c8;font-size:.82rem}.progress{display:inline-flex;align-items:center;gap:7px;color:#d9e5ff;font-weight:600}.progress::before{content:'';width:8px;height:8px;border-radius:50%;background:#9bb8ff;box-shadow:0 0 0 0 #9bb8ff;animation:pulse 1.25s infinite}@keyframes pulse{70%{box-shadow:0 0 0 8px #9bb8ff00}}.item.running{border-color:#739cf7}@media(max-width:850px){body{overflow:auto}main{height:auto;min-height:100vh;grid-template-columns:1fr}.sidebar{overflow:visible}.stage{height:min(70vh,700px)}}
|
:root{color-scheme:dark;font-family:Inter,system-ui,sans-serif;background:#10131b;color:#f2f5fb}body{margin:0;overflow:hidden;background:#10131b}main{width:100vw;height:100vh;display:grid;grid-template-columns:360px minmax(0,1fr)}.sidebar{padding:24px 18px;display:flex;flex-direction:column;gap:18px;overflow-y:auto;overflow-x:hidden;background:radial-gradient(circle at 0 0,#293b62,transparent 32rem),#141a27;border-right:1px solid #2b354b}h1{font-size:2rem;letter-spacing:-.05em;margin:0}.eyebrow{font-size:.7rem;text-transform:uppercase;letter-spacing:.14em;color:#9bb8ff;margin-bottom:8px}.card{background:#171c28dd;border:1px solid #2b354b;border-radius:14px;overflow:hidden}.stage{min-width:0;min-height:0;display:flex;flex-direction:column;background:#0c1019}canvas{display:block;width:100%;height:100%;flex:1;min-height:0;background:linear-gradient(#111b31,#0c1019);cursor:grab;touch-action:none}canvas.dragging{cursor:grabbing}.controls{padding:14px 18px;display:flex;align-items:center;gap:10px;flex-wrap:wrap;border-top:1px solid #2b354b}.promptbox{padding:16px;display:grid;gap:10px}.promptbox textarea{min-height:110px;resize:none;overflow:hidden}textarea,input{box-sizing:border-box;width:100%;border:1px solid #35415b;border-radius:10px;background:#0d121d;color:#f2f5fb;padding:10px;font:inherit}button,.download{border:0;border-radius:999px;padding:10px 16px;background:#9bb8ff;color:#10131b;font:inherit;font-weight:700;cursor:pointer;text-decoration:none}button:disabled{opacity:.5;cursor:wait}.download{background:#24313a;color:#dce9e8}.readout,.hint{color:#a9b3c8;font-size:.88rem}.gallery{padding:4px;display:grid;gap:8px;align-content:start}.history{flex:none;min-height:0;overflow:visible}.gallery h2{font-size:1rem;margin:8px}.item{width:100%;background:#101622;border:1px solid #2c3750;border-radius:12px;padding:11px;text-align:left;color:#e8eefc}.item:hover,.item.active{border-color:#9bb8ff;background:#19233a}.item p{margin:0 0 6px;font-size:.88rem;line-height:1.35}.status{font-size:.75rem;color:#a9b3c8}.error{color:#ffacac;display:-webkit-box;-webkit-line-clamp:3;-webkit-box-orient:vertical;overflow:hidden}.camera{flex:1 1 100%;color:#a9b3c8;font-size:.82rem}.progress{display:inline-flex;align-items:center;gap:7px;color:#d9e5ff;font-weight:600}.progress::before{content:'';width:8px;height:8px;border-radius:50%;background:#9bb8ff;box-shadow:0 0 0 0 #9bb8ff;animation:pulse 1.25s infinite}@keyframes pulse{70%{box-shadow:0 0 0 8px #9bb8ff00}}.item.running{border-color:#739cf7}@media(max-width:850px){body{overflow:auto}main{height:auto;min-height:100vh;grid-template-columns:1fr}.sidebar{overflow:visible}.stage{height:min(70vh,700px)}}
|
||||||
/* LocalAI house style: dark graphite surfaces with a cyan/violet edge. */
|
/* LocalAI house style: dark graphite surfaces with a cyan/violet edge. */
|
||||||
:root{--la-bg:#080b0f;--la-panel:#10151b;--la-panel-2:#151c23;--la-line:#25313b;--la-text:#f3f6f4;--la-muted:#8b9aa5;--la-cyan:#3bd3d0;--la-cyan-2:#5ee6be;--la-violet:#9f7aea}body{background:var(--la-bg);color:var(--la-text)}.sidebar{background:radial-gradient(circle at 18% 0,rgba(59,211,208,.12),transparent 26rem),var(--la-panel);border-color:var(--la-line);box-sizing:border-box;min-height:0;min-width:0}.card{background:var(--la-panel-2);border-color:var(--la-line)}.stage{background:#090d12}canvas{background:radial-gradient(circle at 50% 25%,#102632 0,#090d12 56%)}.eyebrow{color:var(--la-cyan);font-family:ui-monospace,SFMono-Regular,Menlo,monospace}.product-title{display:flex;align-items:center;gap:11px}.product-mark{display:grid;place-items:center;width:36px;height:36px;border-radius:11px;background:linear-gradient(135deg,var(--la-cyan),#218eac 55%,var(--la-violet));color:#051013;font-size:20px;font-weight:900;box-shadow:0 0 28px rgba(59,211,208,.2)}.localai-logo{position:fixed;top:18px;right:18px;z-index:2;width:56px;height:56px;object-fit:contain;filter:drop-shadow(0 5px 16px #0009)}.promptbox label,.gallery h2{color:var(--la-text)}textarea,input{border-color:var(--la-line);background:#0b1015}button{background:linear-gradient(135deg,var(--la-cyan),var(--la-cyan-2));color:#051013;border-radius:8px;box-shadow:0 8px 22px rgba(59,211,208,.12)}.history,.gallery,#items{min-width:0}.item{background:#0b1015;border-color:var(--la-line);box-sizing:border-box;min-width:0;white-space:normal;overflow-wrap:anywhere}.item:hover,.item.active{border-color:var(--la-cyan);background:#111d24}.status,.readout,.hint,.camera{color:var(--la-muted)}.progress{color:var(--la-cyan-2)}.progress::before{background:var(--la-cyan);box-shadow:0 0 0 0 var(--la-cyan)}.item.running{border-color:var(--la-cyan)}
|
:root{--la-bg:#080b0f;--la-panel:#10151b;--la-panel-2:#151c23;--la-line:#25313b;--la-text:#f3f6f4;--la-muted:#8b9aa5;--la-cyan:#3bd3d0;--la-cyan-2:#5ee6be;--la-violet:#9f7aea}body{background:var(--la-bg);color:var(--la-text)}.sidebar{background:radial-gradient(circle at 18% 0,rgba(59,211,208,.12),transparent 26rem),var(--la-panel);border-color:var(--la-line);box-sizing:border-box;min-height:0;min-width:0}.card{background:var(--la-panel-2);border-color:var(--la-line)}.stage{background:#090d12}canvas{background:radial-gradient(circle at 50% 25%,#102632 0,#090d12 56%)}.eyebrow{color:var(--la-cyan);font-family:ui-monospace,SFMono-Regular,Menlo,monospace}.product-title{display:flex;align-items:center;gap:11px}.product-mark{display:grid;place-items:center;width:36px;height:36px;border-radius:11px;background:linear-gradient(135deg,var(--la-cyan),#218eac 55%,var(--la-violet));color:#051013;font-size:20px;font-weight:900;box-shadow:0 0 28px rgba(59,211,208,.2)}.localai-logo{position:fixed;top:18px;right:18px;z-index:2;width:56px;height:56px;object-fit:contain;filter:drop-shadow(0 5px 16px #0009)}.promptbox label,.gallery h2{color:var(--la-text)}textarea,input{border-color:var(--la-line);background:#0b1015}button{background:linear-gradient(135deg,var(--la-cyan),var(--la-cyan-2));color:#051013;border-radius:8px;box-shadow:0 8px 22px rgba(59,211,208,.12)}.history,.gallery,#items{min-width:0}.item{background:#0b1015;border-color:var(--la-line);box-sizing:border-box;min-width:0;white-space:normal;overflow-wrap:anywhere}.item:hover,.item.active{border-color:var(--la-cyan);background:#111d24}.status,.readout,.hint,.camera{color:var(--la-muted)}.progress{color:var(--la-cyan-2)}.progress::before{background:var(--la-cyan);box-shadow:0 0 0 0 var(--la-cyan)}.item.running{border-color:var(--la-cyan)}
|
||||||
</style><main><aside class="sidebar"><header><div class="eyebrow">Kimodo-SMPLX-RP-v1 · Vulkan</div><div class="product-title"><span class="product-mark">K</span><h1>Text to motion</h1></div></header><section class="card promptbox"><label for="prompt">Describe a motion</label><textarea id="prompt">A person runs forward and then leaps over an obstacle in front of them.</textarea><button id="generate">Generate motion</button><span id="status" class="readout">Ready</span><div class="hint">One generation runs at a time. Select an animation below to restore and edit its prompt.</div></section><section class="card history"><div class="gallery"><h2>Past animations</h2><div id="items" class="readout">Loading…</div></div></section></aside><section class="stage"><canvas id="view" width="1280" height="720" aria-label="Animated SMPL-X skeleton"></canvas><div class="controls"><button id="play">Pause</button><button id="reset">Reset view</button><input id="frame" type="range" min="0" value="0" step="1"><span id="frameText" class="readout"></span><span class="camera">Camera tracks motion · Drag: rotate · wheel: zoom · Shift/right-drag: pan · double-click: reset</span></div></section></main><img class="localai-logo" src="/localai.png" alt="LocalAI">
|
</style><main><aside class="sidebar"><header><div class="eyebrow">Kimodo-SMPLX-RP-v1 · Vulkan</div><div class="product-title"><span class="product-mark">K</span><h1>Text to motion</h1></div></header><section class="card promptbox"><label for="prompt">Describe a motion</label><textarea id="prompt">A person runs forward and then leaps over an obstacle in front of them.</textarea><button id="generate">Generate motion</button><span id="status" class="readout">Ready</span><div class="hint">One generation runs at a time. Select an animation below to restore and edit its prompt.</div></section><section class="card history"><div class="gallery"><h2>Past animations</h2><div id="items" class="readout">Loading…</div></div></section></aside><section class="stage"><canvas id="view" width="1280" height="720" aria-label="Animated SMPL-X skeleton"></canvas><div class="controls"><button id="play">Pause</button><button id="reset">Reset view</button><a id="download" class="download" hidden download>Download GLB</a><input id="frame" type="range" min="0" value="0" step="1"><span id="frameText" class="readout"></span><span class="camera">Camera tracks motion · Drag: rotate · wheel: zoom · Shift/right-drag: pan · double-click: reset</span></div></section></main><img class="localai-logo" src="/localai.png" alt="LocalAI">
|
||||||
<style>.promptbox,.history{flex:0 0 auto}</style>
|
<style>.promptbox,.history{flex:0 0 auto}.license-warning{color:#ffbf78!important;font-weight:650}</style>
|
||||||
<script src="/models.js"></script><script>
|
<script src="/models.js"></script><script>
|
||||||
const parents=[-1,0,0,0,1,2,3,4,5,6,7,8,9,9,9,12,13,14,16,17,18,19];
|
let parents=[-1,0,0,0,1,2,3,4,5,6,7,8,9,9,9,12,13,14,16,17,18,19];
|
||||||
// SMPL-X22 rest offsets calibrated from the captured upstream posed-joint /
|
// SMPL-X22 rest offsets calibrated from the captured upstream posed-joint /
|
||||||
// global-rotation fixture. The generator persists local rotations and root
|
// global-rotation fixture. The generator persists local rotations and root
|
||||||
// translations; these fixed parent-local bone vectors make them viewable here.
|
// translations; these fixed parent-local bone vectors make them viewable here.
|
||||||
const offsets=[[0,0,0],[.052299,-.093936,-.027607],[-.057193,-.106548,-.022218],[-.001496,.11293,-.024981],[.058867,-.416442,-.006557],[-.048074,-.39756,-.014061],[.0069,.145636,-.006859],[-.041738,-.437584,-.029512],[.014489,-.446853,-.01803],[-.010334,.056082,.021116],[.049294,-.065279,.126259],[-.040575,-.065287,.127076],[-.011026,.171365,-.028827],[.047725,.087643,-.008375],[-.046636,.086612,-.014864],[.024654,.175391,.024463],[.126285,.05768,-.013885],[-.109342,.053674,-.009118],[.272907,-.069853,-.039094],[-.292029,-.03544,-.024565],[.276174,.021254,-.002478],[-.271878,-.004835,-.016445]];
|
let offsets=[[0,0,0],[.052299,-.093936,-.027607],[-.057193,-.106548,-.022218],[-.001496,.11293,-.024981],[.058867,-.416442,-.006557],[-.048074,-.39756,-.014061],[.0069,.145636,-.006859],[-.041738,-.437584,-.029512],[.014489,-.446853,-.01803],[-.010334,.056082,.021116],[.049294,-.065279,.126259],[-.040575,-.065287,.127076],[-.011026,.171365,-.028827],[.047725,.087643,-.008375],[-.046636,.086612,-.014864],[.024654,.175391,.024463],[.126285,.05768,-.013885],[-.109342,.053674,-.009118],[.272907,-.069853,-.039094],[-.292029,-.03544,-.024565],[.276174,.021254,-.002478],[-.271878,-.004835,-.016445]];
|
||||||
const canvas=document.querySelector('#view'),ctx=canvas.getContext('2d'),slider=document.querySelector('#frame'),promptBox=document.querySelector('#prompt'),generate=document.querySelector('#generate'),status=document.querySelector('#status'),items=document.querySelector('#items');let selected,root,rotations,frame=0,playbackBlend=0,playing=true,last=0,cameraLast=0,animations=[],activeRequest,activeStarted;const defaultView={yaw:-.68,pitch:-.20,zoom:2700,panX:0,panY:0,cameraX:0,cameraZ:0,cameraZoom:2700,cameraSpeed:0},view={...defaultView};window.addEventListener('kimodo:sequence-controls-ready',()=>{if(selected)window.dispatchEvent(new CustomEvent('kimodo:restore-sequence',{detail:{segments:selected.segments,model:selected.model}}))});
|
window.addEventListener('kimodo:restore-sequence',event=>{const id=event.detail?.model||'smplx-rp-v1',model=window.kimodoModels?.find(item=>item.id===id);if(model?.parents?.length&&model.offsets?.length===model.parents.length){parents=model.parents;offsets=model.offsets}});
|
||||||
|
const canvas=document.querySelector('#view'),ctx=canvas.getContext('2d'),slider=document.querySelector('#frame'),promptBox=document.querySelector('#prompt'),generate=document.querySelector('#generate'),status=document.querySelector('#status'),items=document.querySelector('#items'),download=document.querySelector('#download');let selected,root,rotations,frame=0,playbackBlend=0,playing=true,last=0,cameraLast=0,animations=[],activeRequest,activeStarted;const defaultView={yaw:-.68,pitch:-.20,zoom:2700,panX:0,panY:0,cameraX:0,cameraZ:0,cameraZoom:2700,cameraSpeed:0},view={...defaultView};window.addEventListener('kimodo:sequence-controls-ready',()=>{if(selected)window.dispatchEvent(new CustomEvent('kimodo:restore-sequence',{detail:{segments:selected.segments,model:selected.model}}))});
|
||||||
function renderedRoot(){if(!selected||!root)return[0,0,0];const at=frame*3,next=((frame+1)%selected.frames)*3,b=playbackBlend;return[root[at]*(1-b)+root[next]*b,root[at+1]*(1-b)+root[next+1]*b,root[at+2]*(1-b)+root[next+2]*b]}function snapCamera(){const[x,,z]=renderedRoot();view.cameraX=x;view.cameraZ=z;view.cameraZoom=view.zoom;view.cameraSpeed=0;cameraLast=performance.now()}function reset(){Object.assign(view,defaultView);snapCamera();draw()}function updateCamera(now){if(!selected||!root)return;const dt=Math.min(.1,Math.max(0,(now-cameraLast)/1000));cameraLast=now;const at=frame*3,next=((frame+1)%selected.frames)*3,[rootX,,rootZ]=renderedRoot(),speed=playing?Math.hypot(root[next]-root[at],root[next+2]-root[at+2])*30:0,dx=rootX-view.cameraX,dz=rootZ-view.cameraZ,distance=Math.hypot(dx,dz),deadZone=.18;const targetX=distance>deadZone?rootX-dx/distance*deadZone:view.cameraX,targetZ=distance>deadZone?rootZ-dz/distance*deadZone:view.cameraZ,follow=1-Math.exp(-3*dt),speedFollow=1-Math.exp(-2.4*dt),zoomFollow=1-Math.exp(-2.6*dt);view.cameraSpeed+=(speed-view.cameraSpeed)*speedFollow;const targetZoom=view.zoom*(1-Math.min(.22,view.cameraSpeed*.035));view.cameraX+=(targetX-view.cameraX)*follow;view.cameraZ+=(targetZ-view.cameraZ)*follow;view.cameraZoom+=(targetZoom-view.cameraZoom)*zoomFollow}function rotate(q,v){const[x,y,z,w]=q,[vx,vy,vz]=v,tx=2*(y*vz-z*vy),ty=2*(z*vx-x*vz),tz=2*(x*vy-y*vx);return[vx+w*tx+y*tz-z*ty,vy+w*ty+z*tx-x*tz,vz+w*tz+x*ty-y*tx]};function add(a,b){return[a[0]+b[0],a[1]+b[1],a[2]+b[2]]}function multiply(a,b){const[x,y,z,w]=a,[X,Y,Z,W]=b;return[x*W+w*X+y*Z-z*Y,y*W+w*Y+z*X-x*Z,z*W+w*Z+x*Y-y*X,w*W-x*X-y*Y-z*Z]}
|
function renderedRoot(){if(!selected||!root)return[0,0,0];const at=frame*3,next=((frame+1)%selected.frames)*3,b=playbackBlend;return[root[at]*(1-b)+root[next]*b,root[at+1]*(1-b)+root[next+1]*b,root[at+2]*(1-b)+root[next+2]*b]}function snapCamera(){const[x,,z]=renderedRoot();view.cameraX=x;view.cameraZ=z;view.cameraZoom=view.zoom;view.cameraSpeed=0;cameraLast=performance.now()}function reset(){Object.assign(view,defaultView);snapCamera();draw()}function updateCamera(now){if(!selected||!root)return;const dt=Math.min(.1,Math.max(0,(now-cameraLast)/1000));cameraLast=now;const at=frame*3,next=((frame+1)%selected.frames)*3,[rootX,,rootZ]=renderedRoot(),speed=playing?Math.hypot(root[next]-root[at],root[next+2]-root[at+2])*30:0,dx=rootX-view.cameraX,dz=rootZ-view.cameraZ,distance=Math.hypot(dx,dz),deadZone=.18;const targetX=distance>deadZone?rootX-dx/distance*deadZone:view.cameraX,targetZ=distance>deadZone?rootZ-dz/distance*deadZone:view.cameraZ,follow=1-Math.exp(-3*dt),speedFollow=1-Math.exp(-2.4*dt),zoomFollow=1-Math.exp(-2.6*dt);view.cameraSpeed+=(speed-view.cameraSpeed)*speedFollow;const targetZoom=view.zoom*(1-Math.min(.22,view.cameraSpeed*.035));view.cameraX+=(targetX-view.cameraX)*follow;view.cameraZ+=(targetZ-view.cameraZ)*follow;view.cameraZoom+=(targetZoom-view.cameraZoom)*zoomFollow}function rotate(q,v){const[x,y,z,w]=q,[vx,vy,vz]=v,tx=2*(y*vz-z*vy),ty=2*(z*vx-x*vz),tz=2*(x*vy-y*vx);return[vx+w*tx+y*tz-z*ty,vy+w*ty+z*tx-x*tz,vz+w*tz+x*ty-y*tx]};function add(a,b){return[a[0]+b[0],a[1]+b[1],a[2]+b[2]]}function multiply(a,b){const[x,y,z,w]=a,[X,Y,Z,W]=b;return[x*W+w*X+y*Z-z*Y,y*W+w*Y+z*X-x*Z,z*W+w*Z+x*Y-y*X,w*W-x*X-y*Y-z*Z]}
|
||||||
function pose(){if(!selected||!root||!rotations)return[];const positions=[],global=[],rootPosition=renderedRoot();for(let j=0;j<22;j++){const q=Array.from(rotations.subarray((frame*22+j)*4,(frame*22+j+1)*4)),p=parents[j];if(p<0){global[j]=q;positions[j]=rootPosition}else{global[j]=multiply(global[p],q);positions[j]=add(positions[p],rotate(global[p],offsets[j]))}}return positions}function project([x,y,z]){x-=view.cameraX;z-=view.cameraZ;const rx=x*Math.cos(view.yaw)-z*Math.sin(view.yaw),rz=x*Math.sin(view.yaw)+z*Math.cos(view.yaw),ry=y*Math.cos(view.pitch)-rz*Math.sin(view.pitch),dz=y*Math.sin(view.pitch)+rz*Math.cos(view.pitch)+8;return[canvas.width/2+view.panX+view.cameraZoom*rx/dz,canvas.height*.78+view.panY-view.cameraZoom*ry/dz]}
|
function pose(){if(!selected||!root||!rotations)return[];const positions=[],global=[],rootPosition=renderedRoot(),joints=parents.length;for(let j=0;j<joints;j++){const q=Array.from(rotations.subarray((frame*joints+j)*4,(frame*joints+j+1)*4)),p=parents[j];if(p<0){global[j]=q;positions[j]=rootPosition}else{global[j]=multiply(global[p],q);positions[j]=add(positions[p],rotate(global[p],offsets[j]))}}return positions}function project([x,y,z]){x-=view.cameraX;z-=view.cameraZ;const rx=x*Math.cos(view.yaw)-z*Math.sin(view.yaw),rz=x*Math.sin(view.yaw)+z*Math.cos(view.yaw),ry=y*Math.cos(view.pitch)-rz*Math.sin(view.pitch),dz=y*Math.sin(view.pitch)+rz*Math.cos(view.pitch)+8;return[canvas.width/2+view.panX+view.cameraZoom*rx/dz,canvas.height*.78+view.panY-view.cameraZoom*ry/dz]}
|
||||||
function ground(){const cx=0,cz=0,step=.5,initialExtent=6,drawGrid=(extent,alpha,colour,width)=>{ctx.globalAlpha=alpha;ctx.strokeStyle=colour;ctx.lineWidth=width;for(let i=-extent/step;i<=extent/step;i++){let a=project([cx-extent,0,cz+i*step]),b=project([cx+extent,0,cz+i*step]);ctx.beginPath();ctx.moveTo(a[0],a[1]);ctx.lineTo(b[0],b[1]);ctx.stroke();a=project([cx+i*step,0,cz-extent]),b=project([cx+i*step,0,cz+extent]);ctx.beginPath();ctx.moveTo(a[0],a[1]);ctx.lineTo(b[0],b[1]);ctx.stroke()}};const[x,,z]=renderedRoot(),rootDistance=Math.max(Math.abs(x),Math.abs(z)),outerAlpha=.72*Math.max(0,Math.min(1,(rootDistance-3.5)/2.5));if(outerAlpha)drawGrid(18,outerAlpha,'#173943',1);drawGrid(initialExtent,1,'#173943',2);ctx.globalAlpha=1;ctx.strokeStyle='#23606b';ctx.lineWidth=3;const xAxis=project([cx-initialExtent,0,cz]),zAxis=project([cx,0,cz-initialExtent]),xEnd=project([cx+initialExtent,0,cz]),zEnd=project([cx,0,cz+initialExtent]);ctx.beginPath();ctx.moveTo(xAxis[0],xAxis[1]);ctx.lineTo(xEnd[0],xEnd[1]);ctx.moveTo(zAxis[0],zAxis[1]);ctx.lineTo(zEnd[0],zEnd[1]);ctx.stroke()}function draw(){ctx.clearRect(0,0,canvas.width,canvas.height);const p=pose();ground();if(p.length){ctx.lineCap='round';for(let pass=0;pass<2;pass++){ctx.strokeStyle=pass?'#65eee1':'#071014';ctx.lineWidth=pass?7:13;for(let i=1;i<22;i++){const a=project(p[i]),b=project(p[parents[i]]);ctx.beginPath();ctx.moveTo(a[0],a[1]);ctx.lineTo(b[0],b[1]);ctx.stroke()}}for(const x of p){const a=project(x);ctx.fillStyle='#071014';ctx.beginPath();ctx.arc(a[0],a[1],7,0,Math.PI*2);ctx.fill();ctx.fillStyle='#ecfffd';ctx.beginPath();ctx.arc(a[0],a[1],4,0,Math.PI*2);ctx.fill()}}slider.value=frame;document.querySelector('#frameText').textContent=selected?`frame ${frame+1} / ${selected.frames}`:'No animation selected'}function tick(t){if(selected){const interval=1000/30;if(!last)last=t;if(playing){while(t-last>=interval){frame=(frame+1)%selected.frames;last+=interval}playbackBlend=Math.min(1,(t-last)/interval)}else playbackBlend=0;updateCamera(t);draw()}requestAnimationFrame(tick)}
|
function ground(){const cx=0,cz=0,step=.5,initialExtent=6,drawGrid=(extent,alpha,colour,width)=>{ctx.globalAlpha=alpha;ctx.strokeStyle=colour;ctx.lineWidth=width;for(let i=-extent/step;i<=extent/step;i++){let a=project([cx-extent,0,cz+i*step]),b=project([cx+extent,0,cz+i*step]);ctx.beginPath();ctx.moveTo(a[0],a[1]);ctx.lineTo(b[0],b[1]);ctx.stroke();a=project([cx+i*step,0,cz-extent]),b=project([cx+i*step,0,cz+extent]);ctx.beginPath();ctx.moveTo(a[0],a[1]);ctx.lineTo(b[0],b[1]);ctx.stroke()}};const[x,,z]=renderedRoot(),rootDistance=Math.max(Math.abs(x),Math.abs(z)),outerAlpha=.72*Math.max(0,Math.min(1,(rootDistance-3.5)/2.5));if(outerAlpha)drawGrid(18,outerAlpha,'#173943',1);drawGrid(initialExtent,1,'#173943',2);ctx.globalAlpha=1;ctx.strokeStyle='#23606b';ctx.lineWidth=3;const xAxis=project([cx-initialExtent,0,cz]),zAxis=project([cx,0,cz-initialExtent]),xEnd=project([cx+initialExtent,0,cz]),zEnd=project([cx,0,cz+initialExtent]);ctx.beginPath();ctx.moveTo(xAxis[0],xAxis[1]);ctx.lineTo(xEnd[0],xEnd[1]);ctx.moveTo(zAxis[0],zAxis[1]);ctx.lineTo(zEnd[0],zEnd[1]);ctx.stroke()}function draw(){ctx.clearRect(0,0,canvas.width,canvas.height);const p=pose();ground();if(p.length){ctx.lineCap='round';for(let pass=0;pass<2;pass++){ctx.strokeStyle=pass?'#65eee1':'#071014';ctx.lineWidth=pass?7:13;for(let i=1;i<parents.length;i++){const a=project(p[i]),b=project(p[parents[i]]);ctx.beginPath();ctx.moveTo(a[0],a[1]);ctx.lineTo(b[0],b[1]);ctx.stroke()}}for(const x of p){const a=project(x);ctx.fillStyle='#071014';ctx.beginPath();ctx.arc(a[0],a[1],7,0,Math.PI*2);ctx.fill();ctx.fillStyle='#ecfffd';ctx.beginPath();ctx.arc(a[0],a[1],4,0,Math.PI*2);ctx.fill()}}slider.value=frame;document.querySelector('#frameText').textContent=selected?`frame ${frame+1} / ${selected.frames}`:'No animation selected'}function tick(t){if(selected){const interval=1000/30;if(!last)last=t;if(playing){while(t-last>=interval){frame=(frame+1)%selected.frames;last+=interval}playbackBlend=Math.min(1,(t-last)/interval)}else playbackBlend=0;updateCamera(t);draw()}requestAnimationFrame(tick)}
|
||||||
async function select(a){if(a.status!=='ready')return;selected=a;promptBox.value=a.prompt;window.dispatchEvent(new CustomEvent('kimodo:restore-sequence',{detail:{segments:a.segments,model:a.model}}));status.className='readout';status.textContent=`Selected ${a.id.slice(0,8)} · sequence restored`;[root,rotations]=await Promise.all([fetch(`/api/animations/${a.id}/root.f32`).then(r=>r.arrayBuffer()).then(b=>new Float32Array(b)),fetch(`/api/animations/${a.id}/rotations.f32`).then(r=>r.arrayBuffer()).then(b=>new Float32Array(b))]);frame=0;playbackBlend=0;last=performance.now();snapCamera();slider.max=a.frames-1;renderGallery();draw()}function renderGallery(){if(!animations.length){items.textContent='No animations yet.';return}items.replaceChildren(...animations.map(a=>{const b=document.createElement('button');b.className='item '+a.status+(selected?.id===a.id?' active':'');b.disabled=a.status!=='ready';b.innerHTML=`<p>${a.prompt}</p><span class="status">${a.status} · ${a.frames} frames · ${a.diffusion_steps} steps</span>${a.error?`<div class="error">${a.error}</div>`:''}`;b.onclick=()=>select(a);return b}))}function showProgress(){const a=animations.find(a=>a.id===activeRequest);if(!a)return;if(a.status==='ready'){status.className='readout';status.textContent='Generation complete — select it from the gallery to play it.';activeRequest=undefined;generate.disabled=false;return}if(a.status==='failed'){status.className='error';status.textContent=`Generation failed: ${a.error}`;activeRequest=undefined;generate.disabled=false;return}const seconds=Math.max(0,Math.floor((Date.now()-activeStarted)/1000));status.className='readout progress';status.textContent=a.status==='running'?`Generating motion… ${seconds}s elapsed`:`Queued for generation… ${seconds}s elapsed`;generate.disabled=true}async function refresh(){animations=await fetch('/api/animations').then(r=>r.json());renderGallery();showProgress()}generate.onclick=async()=>{const prompt=promptBox.value.trim();if(!prompt)return;generate.disabled=true;status.className='readout progress';status.textContent='Submitting generation…';try{const r=await fetch('/api/generate',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify({prompt,frames:150,steps:100,seed:0})});if(!r.ok)throw new Error(await r.text());const a=await r.json();activeRequest=a.id;activeStarted=Date.now();await refresh()}catch(e){status.className='error';status.textContent=e.message;generate.disabled=false}};
|
async function select(a){if(a.status!=='ready')return;selected=a;download.href=`/api/animations/${a.id}/animation.glb`;download.download=`kimodo-${a.id}.glb`;download.hidden=false;promptBox.value=a.prompt;window.dispatchEvent(new CustomEvent('kimodo:restore-sequence',{detail:{segments:a.segments,model:a.model}}));status.className='readout';status.textContent=`Selected ${a.id.slice(0,8)} · sequence restored`;[root,rotations]=await Promise.all([fetch(`/api/animations/${a.id}/root.f32`).then(r=>r.arrayBuffer()).then(b=>new Float32Array(b)),fetch(`/api/animations/${a.id}/rotations.f32`).then(r=>r.arrayBuffer()).then(b=>new Float32Array(b))]);frame=0;playbackBlend=0;last=performance.now();snapCamera();slider.max=a.frames-1;renderGallery();draw()}function renderGallery(){if(!animations.length){items.textContent='No animations yet.';return}items.replaceChildren(...animations.map(a=>{const b=document.createElement('button');b.className='item '+a.status+(selected?.id===a.id?' active':'');b.disabled=a.status!=='ready';b.innerHTML=`<p>${a.prompt}</p><span class="status">${a.status} · ${a.frames} frames · ${a.diffusion_steps} steps</span>${a.error?`<div class="error">${a.error}</div>`:''}`;b.onclick=()=>select(a);return b}))}function showProgress(){const a=animations.find(a=>a.id===activeRequest);if(!a)return;if(a.status==='ready'){status.className='readout';status.textContent='Generation complete — select it from the gallery to play it.';activeRequest=undefined;generate.disabled=false;return}if(a.status==='failed'){status.className='error';status.textContent=`Generation failed: ${a.error}`;activeRequest=undefined;generate.disabled=false;return}const seconds=Math.max(0,Math.floor((Date.now()-activeStarted)/1000));status.className='readout progress';status.textContent=a.status==='running'?`Generating motion… ${seconds}s elapsed`:`Queued for generation… ${seconds}s elapsed`;generate.disabled=true}async function refresh(){animations=await fetch('/api/animations').then(r=>r.json());renderGallery();showProgress()}generate.onclick=async()=>{const prompt=promptBox.value.trim();if(!prompt)return;generate.disabled=true;status.className='readout progress';status.textContent='Submitting generation…';try{const r=await fetch('/api/generate',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify({prompt,frames:150,steps:100,seed:0})});if(!r.ok)throw new Error(await r.text());const a=await r.json();activeRequest=a.id;activeStarted=Date.now();await refresh()}catch(e){status.className='error';status.textContent=e.message;generate.disabled=false}};
|
||||||
document.querySelector('#play').onclick=e=>{playing=!playing;last=performance.now();playbackBlend=0;e.target.textContent=playing?'Pause':'Play'};slider.oninput=()=>{frame=Number(slider.value);playbackBlend=0;last=performance.now();draw()};document.querySelector('#reset').onclick=reset;canvas.addEventListener('dblclick',reset);canvas.addEventListener('contextmenu',e=>e.preventDefault());let drag;canvas.addEventListener('pointerdown',e=>{canvas.setPointerCapture(e.pointerId);drag={x:e.clientX,y:e.clientY,pan:e.button===2||e.shiftKey};canvas.classList.add('dragging')});canvas.addEventListener('pointermove',e=>{if(!drag)return;const dx=e.clientX-drag.x,dy=e.clientY-drag.y;drag.x=e.clientX;e.clientY;drag.y=e.clientY;if(drag.pan){view.panX+=dx;view.panY+=dy}else{view.yaw+=dx*.008;view.pitch=Math.max(-1.25,Math.min(1.25,view.pitch+dy*.008))}draw()});function end(){drag=undefined;canvas.classList.remove('dragging')}canvas.addEventListener('pointerup',end);canvas.addEventListener('pointercancel',end);canvas.addEventListener('wheel',e=>{e.preventDefault();view.zoom=Math.max(350,Math.min(3600,view.zoom*Math.exp(-e.deltaY*.001)));draw()},{passive:false});refresh().then(()=>{const a=animations.find(a=>a.status==='ready');if(a)return select(a);draw()});setInterval(refresh,2500);requestAnimationFrame(tick);
|
document.querySelector('#play').onclick=e=>{playing=!playing;last=performance.now();playbackBlend=0;e.target.textContent=playing?'Pause':'Play'};slider.oninput=()=>{frame=Number(slider.value);playbackBlend=0;last=performance.now();draw()};document.querySelector('#reset').onclick=reset;canvas.addEventListener('dblclick',reset);canvas.addEventListener('contextmenu',e=>e.preventDefault());let drag;canvas.addEventListener('pointerdown',e=>{canvas.setPointerCapture(e.pointerId);drag={x:e.clientX,y:e.clientY,pan:e.button===2||e.shiftKey};canvas.classList.add('dragging')});canvas.addEventListener('pointermove',e=>{if(!drag)return;const dx=e.clientX-drag.x,dy=e.clientY-drag.y;drag.x=e.clientX;e.clientY;drag.y=e.clientY;if(drag.pan){view.panX+=dx;view.panY+=dy}else{view.yaw+=dx*.008;view.pitch=Math.max(-1.25,Math.min(1.25,view.pitch+dy*.008))}draw()});function end(){drag=undefined;canvas.classList.remove('dragging')}canvas.addEventListener('pointerup',end);canvas.addEventListener('pointercancel',end);canvas.addEventListener('wheel',e=>{e.preventDefault();view.zoom=Math.max(350,Math.min(3600,view.zoom*Math.exp(-e.deltaY*.001)));draw()},{passive:false});refresh().then(()=>{const a=animations.find(a=>a.status==='ready');if(a)return select(a);draw()});setInterval(refresh,2500);requestAnimationFrame(tick);
|
||||||
</script></html>
|
</script></html>
|
||||||
|
|||||||
274
demo/main.go
274
demo/main.go
@ -54,9 +54,15 @@ type motionModel struct {
|
|||||||
ID string `json:"id"`
|
ID string `json:"id"`
|
||||||
Label string `json:"label"`
|
Label string `json:"label"`
|
||||||
Skeleton string `json:"skeleton"`
|
Skeleton string `json:"skeleton"`
|
||||||
|
SkeletonKey string `json:"skeleton_key"`
|
||||||
Upstream string `json:"upstream"`
|
Upstream string `json:"upstream"`
|
||||||
|
License string `json:"license"`
|
||||||
|
LicenseURL string `json:"license_url"`
|
||||||
|
Commercial bool `json:"commercial"`
|
||||||
Available bool `json:"available"`
|
Available bool `json:"available"`
|
||||||
Reason string `json:"reason,omitempty"`
|
Reason string `json:"reason,omitempty"`
|
||||||
|
Parents []int `json:"parents"`
|
||||||
|
Offsets [][3]float32 `json:"offsets"`
|
||||||
Motion string `json:"-"`
|
Motion string `json:"-"`
|
||||||
}
|
}
|
||||||
type gallery struct {
|
type gallery struct {
|
||||||
@ -94,14 +100,6 @@ func (g *gallery) list() []*animation {
|
|||||||
return result
|
return result
|
||||||
}
|
}
|
||||||
|
|
||||||
func copyFile(dst, src string) error {
|
|
||||||
b, err := os.ReadFile(src)
|
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
return os.WriteFile(dst, b, 0600)
|
|
||||||
}
|
|
||||||
|
|
||||||
func readF32(path string) ([]float32, error) {
|
func readF32(path string) ([]float32, error) {
|
||||||
b, err := os.ReadFile(path)
|
b, err := os.ReadFile(path)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
@ -125,79 +123,159 @@ func writeF32(path string, values []float32) error {
|
|||||||
return os.WriteFile(path, b, 0600)
|
return os.WriteFile(path, b, 0600)
|
||||||
}
|
}
|
||||||
|
|
||||||
func blendQuaternion(a, b []float32, alpha float32) {
|
// Each motion is exported as a node-only GLB: it deliberately has no mesh or
|
||||||
dot := a[0]*b[0] + a[1]*b[1] + a[2]*b[2] + a[3]*b[3]
|
// skin, so consumers can attach their own Three.js geometry to the named
|
||||||
if dot < 0 {
|
// joints. Kimodo stores root translations and local XYZW rotations.
|
||||||
for i := range b {
|
var smplx22Parents = [...]int{-1, 0, 0, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 9, 9, 12, 13, 14, 16, 17, 18, 19}
|
||||||
b[i] = -b[i]
|
var smplx22Names = [...]string{"pelvis", "left_hip", "right_hip", "spine1", "left_knee", "right_knee", "spine2", "left_ankle", "right_ankle", "spine3", "left_foot", "right_foot", "neck", "left_collar", "right_collar", "head", "left_shoulder", "right_shoulder", "left_elbow", "right_elbow", "left_wrist", "right_wrist"}
|
||||||
}
|
var smplx22Offsets = [...][3]float32{{}, {.052299, -.093936, -.027607}, {-.057193, -.106548, -.022218}, {-.001496, .11293, -.024981}, {.058867, -.416442, -.006557}, {-.048074, -.39756, -.014061}, {.0069, .145636, -.006859}, {-.041738, -.437584, -.029512}, {.014489, -.446853, -.01803}, {-.010334, .056082, .021116}, {.049294, -.065279, .126259}, {-.040575, -.065287, .127076}, {-.011026, .171365, -.028827}, {.047725, .087643, -.008375}, {-.046636, .086612, -.014864}, {.024654, .175391, .024463}, {.126285, .05768, -.013885}, {-.109342, .053674, -.009118}, {.272907, -.069853, -.039094}, {-.292029, -.03544, -.024565}, {.276174, .021254, -.002478}, {-.271878, -.004835, -.016445}}
|
||||||
}
|
|
||||||
length := float32(0)
|
type skeletonDefinition struct {
|
||||||
for i := range a {
|
key string
|
||||||
a[i] = alpha*a[i] + (1-alpha)*b[i]
|
names []string
|
||||||
length += a[i] * a[i]
|
parents []int
|
||||||
}
|
offsets [][3]float32
|
||||||
if length > 0 {
|
|
||||||
length = 1 / float32(math.Sqrt(float64(length)))
|
|
||||||
for i := range a {
|
|
||||||
a[i] *= length
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// stitchSegments joins independently sampled demo segments. The overlap is
|
var skeletonDefinitions = map[string]skeletonDefinition{
|
||||||
// blended in root space and by normalized linear interpolation for quaternions.
|
"smplx22": {key: "smplx22", names: smplx22Names[:], parents: smplx22Parents[:], offsets: smplx22Offsets[:]},
|
||||||
// Native observed-motion conditioning is deliberately a later parity step.
|
}
|
||||||
func stitchSegments(output string, dirs []string, overlap int) error {
|
|
||||||
var roots, rotations []float32
|
type gltfBufferView struct {
|
||||||
for index, dir := range dirs {
|
Buffer int `json:"buffer"`
|
||||||
root, err := readF32(filepath.Join(dir, "root_positions.f32"))
|
ByteOffset int `json:"byteOffset,omitempty"`
|
||||||
|
ByteLength int `json:"byteLength"`
|
||||||
|
}
|
||||||
|
type gltfAccessor struct {
|
||||||
|
BufferView int `json:"bufferView"`
|
||||||
|
ComponentType int `json:"componentType"`
|
||||||
|
Count int `json:"count"`
|
||||||
|
Type string `json:"type"`
|
||||||
|
}
|
||||||
|
|
||||||
|
func appendF32(dst []byte, values []float32) []byte {
|
||||||
|
for _, value := range values {
|
||||||
|
var b [4]byte
|
||||||
|
binary.LittleEndian.PutUint32(b[:], math.Float32bits(value))
|
||||||
|
dst = append(dst, b[:]...)
|
||||||
|
}
|
||||||
|
return dst
|
||||||
|
}
|
||||||
|
|
||||||
|
func writeSkeletonGLB(path string, roots, rotations []float32, skeleton skeletonDefinition) error {
|
||||||
|
frames := len(roots) / 3
|
||||||
|
joints := len(skeleton.parents)
|
||||||
|
if frames < 1 || joints < 1 || len(skeleton.names) != joints || len(skeleton.offsets) != joints || len(roots) != frames*3 || len(rotations) != frames*joints*4 {
|
||||||
|
return fmt.Errorf("invalid %s motion for GLB export", skeleton.key)
|
||||||
|
}
|
||||||
|
times := make([]float32, frames)
|
||||||
|
for i := range times {
|
||||||
|
times[i] = float32(i) / 30
|
||||||
|
}
|
||||||
|
bin := make([]byte, 0, (frames+frames*3+frames*22*4)*4)
|
||||||
|
views := make([]gltfBufferView, 0, 24)
|
||||||
|
addView := func(values []float32) int {
|
||||||
|
offset := len(bin)
|
||||||
|
bin = appendF32(bin, values)
|
||||||
|
views = append(views, gltfBufferView{Buffer: 0, ByteOffset: offset, ByteLength: len(bin) - offset})
|
||||||
|
return len(views) - 1
|
||||||
|
}
|
||||||
|
timeView, rootView := addView(times), addView(roots)
|
||||||
|
rotationViews := make([]int, joints)
|
||||||
|
for joint := range rotationViews {
|
||||||
|
track := make([]float32, frames*4)
|
||||||
|
for frame := 0; frame < frames; frame++ {
|
||||||
|
copy(track[frame*4:], rotations[(frame*joints+joint)*4:(frame*joints+joint+1)*4])
|
||||||
|
}
|
||||||
|
rotationViews[joint] = addView(track)
|
||||||
|
}
|
||||||
|
accessors := []gltfAccessor{{BufferView: timeView, ComponentType: 5126, Count: frames, Type: "SCALAR"}, {BufferView: rootView, ComponentType: 5126, Count: frames, Type: "VEC3"}}
|
||||||
|
for _, view := range rotationViews {
|
||||||
|
accessors = append(accessors, gltfAccessor{BufferView: view, ComponentType: 5126, Count: frames, Type: "VEC4"})
|
||||||
|
}
|
||||||
|
nodes := make([]map[string]any, joints)
|
||||||
|
for joint := range nodes {
|
||||||
|
node := map[string]any{"name": skeleton.names[joint]}
|
||||||
|
if joint != 0 {
|
||||||
|
node["translation"] = skeleton.offsets[joint]
|
||||||
|
}
|
||||||
|
children := make([]int, 0, 3)
|
||||||
|
for child, parent := range skeleton.parents {
|
||||||
|
if parent == joint {
|
||||||
|
children = append(children, child)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if len(children) != 0 {
|
||||||
|
node["children"] = children
|
||||||
|
}
|
||||||
|
nodes[joint] = node
|
||||||
|
}
|
||||||
|
samplers := make([]map[string]any, 0, 23)
|
||||||
|
channels := make([]map[string]any, 0, 23)
|
||||||
|
addChannel := func(node, output int, path string) {
|
||||||
|
samplers = append(samplers, map[string]any{"input": 0, "output": output, "interpolation": "LINEAR"})
|
||||||
|
channels = append(channels, map[string]any{"sampler": len(samplers) - 1, "target": map[string]any{"node": node, "path": path}})
|
||||||
|
}
|
||||||
|
addChannel(0, 1, "translation")
|
||||||
|
for joint := 0; joint < joints; joint++ {
|
||||||
|
addChannel(joint, joint+2, "rotation")
|
||||||
|
}
|
||||||
|
document := map[string]any{
|
||||||
|
"asset": map[string]string{"version": "2.0", "generator": "kimodo.cpp skeleton exporter"},
|
||||||
|
"scene": 0,
|
||||||
|
"scenes": []map[string]any{{"nodes": []int{0}}},
|
||||||
|
"nodes": nodes,
|
||||||
|
"buffers": []map[string]int{{"byteLength": len(bin)}},
|
||||||
|
"bufferViews": views,
|
||||||
|
"accessors": accessors,
|
||||||
|
"animations": []map[string]any{{"name": "KimodoMotion", "samplers": samplers, "channels": channels}},
|
||||||
|
"extras": map[string]any{"skeleton": skeleton.key, "fps": 30, "rotation_order": "xyzw"},
|
||||||
|
}
|
||||||
|
jsonChunk, err := json.Marshal(document)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
rot, err := readF32(filepath.Join(dir, "local_rotations_xyzw.f32"))
|
for len(jsonChunk)%4 != 0 {
|
||||||
|
jsonChunk = append(jsonChunk, ' ')
|
||||||
|
}
|
||||||
|
for len(bin)%4 != 0 {
|
||||||
|
bin = append(bin, 0)
|
||||||
|
}
|
||||||
|
total := 12 + 8 + len(jsonChunk) + 8 + len(bin)
|
||||||
|
out := make([]byte, 0, total)
|
||||||
|
putU32 := func(value uint32) {
|
||||||
|
var b [4]byte
|
||||||
|
binary.LittleEndian.PutUint32(b[:], value)
|
||||||
|
out = append(out, b[:]...)
|
||||||
|
}
|
||||||
|
putU32(0x46546c67)
|
||||||
|
putU32(2)
|
||||||
|
putU32(uint32(total))
|
||||||
|
putU32(uint32(len(jsonChunk)))
|
||||||
|
putU32(0x4e4f534a)
|
||||||
|
out = append(out, jsonChunk...)
|
||||||
|
putU32(uint32(len(bin)))
|
||||||
|
putU32(0x004e4942)
|
||||||
|
out = append(out, bin...)
|
||||||
|
return os.WriteFile(path, out, 0600)
|
||||||
|
}
|
||||||
|
|
||||||
|
func exportSkeletonGLB(dir, skeletonKey string) error {
|
||||||
|
skeleton, ok := skeletonDefinitions[skeletonKey]
|
||||||
|
if !ok {
|
||||||
|
return fmt.Errorf("unsupported skeleton %q", skeletonKey)
|
||||||
|
}
|
||||||
|
roots, err := readF32(filepath.Join(dir, "root_positions.f32"))
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
frames := len(root) / 3
|
rotations, err := readF32(filepath.Join(dir, "local_rotations_xyzw.f32"))
|
||||||
if frames == 0 || len(rot) != frames*22*4 {
|
if err != nil {
|
||||||
return fmt.Errorf("invalid motion segment %d", index+1)
|
|
||||||
}
|
|
||||||
if index == 0 {
|
|
||||||
roots, rotations = root, rot
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
n := overlap
|
|
||||||
if n > frames {
|
|
||||||
n = frames
|
|
||||||
}
|
|
||||||
if n > len(roots)/3 {
|
|
||||||
n = len(roots) / 3
|
|
||||||
}
|
|
||||||
for frame := 0; frame < n; frame++ {
|
|
||||||
alpha := float32(0.5)
|
|
||||||
if n > 1 {
|
|
||||||
alpha = 1 - float32(frame)/float32(n-1)
|
|
||||||
}
|
|
||||||
old := (len(roots)/3 - n + frame) * 3
|
|
||||||
newest := frame * 3
|
|
||||||
for axis := 0; axis < 3; axis++ {
|
|
||||||
roots[old+axis] = alpha*roots[old+axis] + (1-alpha)*root[newest+axis]
|
|
||||||
}
|
|
||||||
for joint := 0; joint < 22; joint++ {
|
|
||||||
oldQ := (len(rotations)/4 - n*22 + frame*22 + joint) * 4
|
|
||||||
newQ := (frame*22 + joint) * 4
|
|
||||||
blendQuaternion(rotations[oldQ:oldQ+4], append([]float32(nil), rot[newQ:newQ+4]...), alpha)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
roots = append(roots, root[n*3:]...)
|
|
||||||
rotations = append(rotations, rot[n*22*4:]...)
|
|
||||||
}
|
|
||||||
if err := writeF32(filepath.Join(output, "root_positions.f32"), roots); err != nil {
|
|
||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
return writeF32(filepath.Join(output, "local_rotations_xyzw.f32"), rotations)
|
return writeSkeletonGLB(filepath.Join(dir, "animation.glb"), roots, rotations, skeleton)
|
||||||
}
|
}
|
||||||
|
|
||||||
func (g *gallery) worker() {
|
func (g *gallery) worker() {
|
||||||
for id := range g.queue {
|
for id := range g.queue {
|
||||||
g.mu.Lock()
|
g.mu.Lock()
|
||||||
@ -239,6 +317,9 @@ func (g *gallery) worker() {
|
|||||||
err = fmt.Errorf("sequence: %w: %s", runErr, strings.TrimSpace(string(output)))
|
err = fmt.Errorf("sequence: %w: %s", runErr, strings.TrimSpace(string(output)))
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
if err == nil {
|
||||||
|
err = exportSkeletonGLB(dir, model.SkeletonKey)
|
||||||
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
g.mu.Lock()
|
g.mu.Lock()
|
||||||
@ -259,6 +340,10 @@ func (g *gallery) worker() {
|
|||||||
func main() {
|
func main() {
|
||||||
addr := flag.String("addr", "127.0.0.1:8090", "listen address")
|
addr := flag.String("addr", "127.0.0.1:8090", "listen address")
|
||||||
motion := flag.String("motion-model", "models/kimodo-smplx-rp-v1-f32.gguf", "motion GGUF")
|
motion := flag.String("motion-model", "models/kimodo-smplx-rp-v1-f32.gguf", "motion GGUF")
|
||||||
|
somaRP := flag.String("soma-rp-model", "models/kimodo-soma-rp-v1.1-f32.gguf", "SOMA RP v1.1 motion GGUF")
|
||||||
|
somaSEED := flag.String("soma-seed-model", "models/kimodo-soma-seed-v1.1-f32.gguf", "SOMA SEED v1.1 motion GGUF")
|
||||||
|
g1RP := flag.String("g1-rp-model", "models/kimodo-g1-rp-v1-f32.gguf", "G1 RP v1 motion GGUF")
|
||||||
|
g1SEED := flag.String("g1-seed-model", "models/kimodo-g1-seed-v1-f32.gguf", "G1 SEED v1 motion GGUF")
|
||||||
text := flag.String("text-bundle", "generated/llm2vec-text-bundle", "native LLM2Vec component directory")
|
text := flag.String("text-bundle", "generated/llm2vec-text-bundle", "native LLM2Vec component directory")
|
||||||
generator := flag.String("generator", "build/debug/kmd-generate", "native text-to-motion command")
|
generator := flag.String("generator", "build/debug/kmd-generate", "native text-to-motion command")
|
||||||
output := flag.String("output", "demo-output", "persistent gallery directory")
|
output := flag.String("output", "demo-output", "persistent gallery directory")
|
||||||
@ -266,12 +351,24 @@ func main() {
|
|||||||
if err := os.MkdirAll(*output, 0755); err != nil {
|
if err := os.MkdirAll(*output, 0755); err != nil {
|
||||||
log.Fatal(err)
|
log.Fatal(err)
|
||||||
}
|
}
|
||||||
|
makeModel := func(id, label, skeletonLabel, skeletonKey, upstream, license, licenseURL, path string, commercial bool) motionModel {
|
||||||
|
definition := skeletonDefinitions[skeletonKey]
|
||||||
|
model := motionModel{ID: id, Label: label, Skeleton: skeletonLabel, SkeletonKey: skeletonKey, Upstream: upstream, License: license, LicenseURL: licenseURL, Commercial: commercial, Parents: definition.parents, Offsets: definition.offsets, Motion: path}
|
||||||
|
if info, err := os.Stat(path); err == nil && info.Mode().IsRegular() {
|
||||||
|
model.Available = true
|
||||||
|
} else {
|
||||||
|
model.Reason = "GGUF not found at " + path
|
||||||
|
}
|
||||||
|
return model
|
||||||
|
}
|
||||||
|
const internalLicense = "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/"
|
||||||
|
const openLicense = "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"
|
||||||
models := map[string]motionModel{
|
models := map[string]motionModel{
|
||||||
"smplx-rp-v1": {ID: "smplx-rp-v1", Label: "SMPL-X RP v1", Skeleton: "SMPL-X 22 joints", Upstream: "nvidia/Kimodo-SMPLX-RP-v1", Available: true, Motion: *motion},
|
"smplx-rp-v1": makeModel("smplx-rp-v1", "SMPL-X RP v1", "SMPL-X 22 joints", "smplx22", "nvidia/Kimodo-SMPLX-RP-v1", "NVIDIA Internal Scientific R&D (non-commercial)", internalLicense, *motion, false),
|
||||||
"soma-rp-v1.1": {ID: "soma-rp-v1.1", Label: "SOMA RP v1.1", Skeleton: "SOMA 30 joints", Upstream: "nvidia/Kimodo-SOMA-RP-v1.1", Reason: "SOMA decoder and GGML conversion are being added"},
|
"soma-rp-v1.1": makeModel("soma-rp-v1.1", "SOMA RP v1.1", "SOMA compact 30-joint control skeleton", "soma30", "nvidia/Kimodo-SOMA-RP-v1.1", "NVIDIA Open Model License", openLicense, *somaRP, true),
|
||||||
"soma-seed-v1.1": {ID: "soma-seed-v1.1", Label: "SOMA SEED v1.1", Skeleton: "SOMA 30 joints", Upstream: "nvidia/Kimodo-SOMA-SEED-v1.1", Reason: "SOMA decoder and GGML conversion are being added"},
|
"soma-seed-v1.1": makeModel("soma-seed-v1.1", "SOMA SEED v1.1", "SOMA compact 30-joint control skeleton", "soma30", "nvidia/Kimodo-SOMA-SEED-v1.1", "NVIDIA Open Model License", openLicense, *somaSEED, true),
|
||||||
"g1-rp-v1": {ID: "g1-rp-v1", Label: "G1 RP v1", Skeleton: "Unitree G1 34 joints", Upstream: "nvidia/Kimodo-G1-RP-v1", Reason: "G1 decoder and GGML conversion are being added"},
|
"g1-rp-v1": makeModel("g1-rp-v1", "G1 RP v1", "Unitree G1 34 joints", "g1skel34", "nvidia/Kimodo-G1-RP-v1", "NVIDIA Open Model License", openLicense, *g1RP, true),
|
||||||
"g1-seed-v1": {ID: "g1-seed-v1", Label: "G1 SEED v1", Skeleton: "Unitree G1 34 joints", Upstream: "nvidia/Kimodo-G1-SEED-v1", Reason: "G1 decoder and GGML conversion are being added"},
|
"g1-seed-v1": makeModel("g1-seed-v1", "G1 SEED v1", "Unitree G1 34 joints", "g1skel34", "nvidia/Kimodo-G1-SEED-v1", "NVIDIA Open Model License", openLicense, *g1SEED, true),
|
||||||
}
|
}
|
||||||
g := &gallery{items: map[string]*animation{}, output: *output, queue: make(chan string, 32), generator: *generator, motion: *motion, text: *text, models: models}
|
g := &gallery{items: map[string]*animation{}, output: *output, queue: make(chan string, 32), generator: *generator, motion: *motion, text: *text, models: models}
|
||||||
entries, _ := filepath.Glob(filepath.Join(*output, "*.json"))
|
entries, _ := filepath.Glob(filepath.Join(*output, "*.json"))
|
||||||
@ -283,6 +380,15 @@ func main() {
|
|||||||
var a animation
|
var a animation
|
||||||
if json.Unmarshal(b, &a) == nil {
|
if json.Unmarshal(b, &a) == nil {
|
||||||
g.items[a.ID] = &a
|
g.items[a.ID] = &a
|
||||||
|
if a.Status == "ready" {
|
||||||
|
model, ok := models[a.Model]
|
||||||
|
if !ok {
|
||||||
|
model = models["smplx-rp-v1"]
|
||||||
|
}
|
||||||
|
if err := exportSkeletonGLB(filepath.Join(*output, a.ID), model.SkeletonKey); err != nil && !os.IsNotExist(err) {
|
||||||
|
log.Printf("export existing animation %s: %v", a.ID, err)
|
||||||
|
}
|
||||||
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
go g.worker()
|
go g.worker()
|
||||||
@ -400,7 +506,7 @@ func main() {
|
|||||||
})
|
})
|
||||||
mux.HandleFunc("/api/animations/", func(w http.ResponseWriter, r *http.Request) {
|
mux.HandleFunc("/api/animations/", func(w http.ResponseWriter, r *http.Request) {
|
||||||
parts := strings.Split(strings.TrimPrefix(r.URL.Path, "/api/animations/"), "/")
|
parts := strings.Split(strings.TrimPrefix(r.URL.Path, "/api/animations/"), "/")
|
||||||
if len(parts) != 2 || (parts[1] != "root.f32" && parts[1] != "rotations.f32") {
|
if len(parts) != 2 || (parts[1] != "root.f32" && parts[1] != "rotations.f32" && parts[1] != "animation.glb") {
|
||||||
http.NotFound(w, r)
|
http.NotFound(w, r)
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
@ -415,7 +521,23 @@ func main() {
|
|||||||
if parts[1] == "rotations.f32" {
|
if parts[1] == "rotations.f32" {
|
||||||
name = "local_rotations_xyzw.f32"
|
name = "local_rotations_xyzw.f32"
|
||||||
}
|
}
|
||||||
|
if parts[1] == "animation.glb" {
|
||||||
|
name = "animation.glb"
|
||||||
|
w.Header().Set("Content-Type", "model/gltf-binary")
|
||||||
|
w.Header().Set("Content-Disposition", "attachment; filename=kimodo-"+a.ID+".glb")
|
||||||
|
// A GLB is a compact asset; read it directly so browsers always receive
|
||||||
|
// it as a download rather than invoking any path-cleaning redirects.
|
||||||
|
data, err := os.ReadFile(filepath.Join(g.output, a.ID, name))
|
||||||
|
if err != nil {
|
||||||
|
http.NotFound(w, r)
|
||||||
|
return
|
||||||
|
}
|
||||||
|
w.Header().Set("Content-Length", fmt.Sprint(len(data)))
|
||||||
|
_, _ = w.Write(data)
|
||||||
|
return
|
||||||
|
} else {
|
||||||
w.Header().Set("Content-Type", "application/octet-stream")
|
w.Header().Set("Content-Type", "application/octet-stream")
|
||||||
|
}
|
||||||
w.Header().Set("Cache-Control", "no-store")
|
w.Header().Set("Cache-Control", "no-store")
|
||||||
http.ServeFile(w, r, filepath.Join(g.output, a.ID, name))
|
http.ServeFile(w, r, filepath.Join(g.output, a.ID, name))
|
||||||
})
|
})
|
||||||
|
|||||||
55
demo/main_test.go
Normal file
55
demo/main_test.go
Normal file
@ -0,0 +1,55 @@
|
|||||||
|
package main
|
||||||
|
|
||||||
|
import (
|
||||||
|
"encoding/binary"
|
||||||
|
"encoding/json"
|
||||||
|
"os"
|
||||||
|
"path/filepath"
|
||||||
|
"testing"
|
||||||
|
)
|
||||||
|
|
||||||
|
func TestWriteSkeletonGLB(t *testing.T) {
|
||||||
|
for _, skeletonKey := range []string{"smplx22", "soma30", "g1skel34"} {
|
||||||
|
t.Run(skeletonKey, func(t *testing.T) {
|
||||||
|
skeleton := skeletonDefinitions[skeletonKey]
|
||||||
|
path := filepath.Join(t.TempDir(), "animation.glb")
|
||||||
|
roots := []float32{0, 0, 0, 1, 0, 0}
|
||||||
|
rotations := make([]float32, 2*len(skeleton.parents)*4)
|
||||||
|
for frame := 0; frame < 2; frame++ {
|
||||||
|
for joint := range skeleton.parents {
|
||||||
|
rotations[(frame*len(skeleton.parents)+joint)*4+3] = 1
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if err := writeSkeletonGLB(path, roots, rotations, skeleton); err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
assertSkeletonGLB(t, path, len(skeleton.parents))
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func assertSkeletonGLB(t *testing.T, path string, expectedJoints int) {
|
||||||
|
t.Helper()
|
||||||
|
b, err := os.ReadFile(path)
|
||||||
|
if err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
if len(b) < 20 || binary.LittleEndian.Uint32(b) != 0x46546c67 || binary.LittleEndian.Uint32(b[4:]) != 2 || int(binary.LittleEndian.Uint32(b[8:])) != len(b) {
|
||||||
|
t.Fatalf("invalid GLB header")
|
||||||
|
}
|
||||||
|
jsonLength := int(binary.LittleEndian.Uint32(b[12:]))
|
||||||
|
if binary.LittleEndian.Uint32(b[16:]) != 0x4e4f534a || 20+jsonLength > len(b) {
|
||||||
|
t.Fatalf("invalid GLB JSON chunk")
|
||||||
|
}
|
||||||
|
var document struct {
|
||||||
|
Asset map[string]string `json:"asset"`
|
||||||
|
Nodes []json.RawMessage `json:"nodes"`
|
||||||
|
Animations []json.RawMessage `json:"animations"`
|
||||||
|
}
|
||||||
|
if err := json.Unmarshal(b[20:20+jsonLength], &document); err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
if document.Asset["version"] != "2.0" || len(document.Nodes) != expectedJoints || len(document.Animations) != 1 {
|
||||||
|
t.Fatalf("unexpected GLB document: %s", b[20:20+jsonLength])
|
||||||
|
}
|
||||||
|
}
|
||||||
@ -5,6 +5,7 @@ window.addEventListener('load', async () => {
|
|||||||
const generate = document.querySelector('#generate');
|
const generate = document.querySelector('#generate');
|
||||||
if (!prompt || !form || !generate) return;
|
if (!prompt || !form || !generate) return;
|
||||||
const models = await fetch('/api/models').then(r => r.json());
|
const models = await fetch('/api/models').then(r => r.json());
|
||||||
|
window.kimodoModels = models;
|
||||||
|
|
||||||
const modelLabel = document.createElement('label');
|
const modelLabel = document.createElement('label');
|
||||||
modelLabel.htmlFor = 'motionModel'; modelLabel.textContent = 'Motion model';
|
modelLabel.htmlFor = 'motionModel'; modelLabel.textContent = 'Motion model';
|
||||||
@ -19,7 +20,14 @@ window.addEventListener('load', async () => {
|
|||||||
const modelHint = document.createElement('div'); modelHint.className = 'hint';
|
const modelHint = document.createElement('div'); modelHint.className = 'hint';
|
||||||
const updateModel = () => {
|
const updateModel = () => {
|
||||||
const model = models.find(item => item.id === select.value);
|
const model = models.find(item => item.id === select.value);
|
||||||
modelHint.textContent = model.available ? `${model.skeleton} · ${model.upstream}` : `${model.skeleton} · ${model.reason}`;
|
if (!model) return;
|
||||||
|
const title = document.querySelector('.eyebrow');
|
||||||
|
if (title) title.textContent = `${model.label} · Vulkan`;
|
||||||
|
modelHint.classList.toggle('license-warning', !model.commercial);
|
||||||
|
const terms = model.commercial ? 'commercial use permitted under NVIDIA Open Model License' : '⚠ non-commercial research use only';
|
||||||
|
const detail = model.available ? `${model.skeleton} · ${model.upstream} · ` : `${model.skeleton} · ${model.reason} · `;
|
||||||
|
const link = document.createElement('a'); link.href = model.license_url; link.target = '_blank'; link.rel = 'noreferrer'; link.textContent = terms;
|
||||||
|
modelHint.replaceChildren(document.createTextNode(detail), link);
|
||||||
};
|
};
|
||||||
select.onchange = updateModel;
|
select.onchange = updateModel;
|
||||||
form.insertBefore(modelLabel, prompt); form.insertBefore(select, prompt); form.insertBefore(modelHint, prompt); updateModel();
|
form.insertBefore(modelLabel, prompt); form.insertBefore(select, prompt); form.insertBefore(modelHint, prompt); updateModel();
|
||||||
|
|||||||
19
demo/skeletons_extra.go
Normal file
19
demo/skeletons_extra.go
Normal file
@ -0,0 +1,19 @@
|
|||||||
|
package main
|
||||||
|
|
||||||
|
// Copied from NVIDIA Kimodo's Apache-2.0 skeleton definitions. Offsets are
|
||||||
|
// the parent-local differences extracted from the official neutral-joint
|
||||||
|
// assets in the trusted reference container.
|
||||||
|
func init() {
|
||||||
|
skeletonDefinitions["soma30"] = skeletonDefinition{
|
||||||
|
key: "soma30",
|
||||||
|
names: []string{"Hips", "Spine1", "Spine2", "Chest", "Neck1", "Neck2", "Head", "Jaw", "LeftEye", "RightEye", "LeftShoulder", "LeftArm", "LeftForeArm", "LeftHand", "LeftHandThumbEnd", "LeftHandMiddleEnd", "RightShoulder", "RightArm", "RightForeArm", "RightHand", "RightHandThumbEnd", "RightHandMiddleEnd", "LeftLeg", "LeftShin", "LeftFoot", "LeftToeBase", "RightLeg", "RightShin", "RightFoot", "RightToeBase"},
|
||||||
|
parents: []int{-1, 0, 1, 2, 3, 4, 5, 6, 6, 6, 3, 10, 11, 12, 13, 13, 3, 16, 17, 18, 19, 19, 0, 22, 23, 24, 0, 26, 27, 28},
|
||||||
|
offsets: [][3]float32{{0, 0, 0}, {-.00013727, .0500376256, -.00053726669}, {-1.86574103e-9, .0712530139, -.000298248546}, {-5.75188398e-9, .0755006305, -.00815970992}, {-.00181676517, .263112953, -.00553348292}, {-2.85102231e-8, .0770939664, .0230258546}, {-4.5975437e-8, .0612891595, .0195370861}, {2.63687901e-5, .0047559225, .0309494062}, {.0320638079, .0538020513, .0758688308}, {-.0322244017, .05361869, .0755823359}, {.0162165175, .232371641, .0511341324}, {.149198457, 2.19397873e-8, -.0550232576}, {.287393078, 2.50268389e-9, -2.58787737e-5}, {.270939812, -7.06625108e-9, 2.60897248e-5}, {.122686267, -.0322017573, .0483306876}, {.190119595, -.00312878387, -.000339570373}, {-.0138011824, .231803086, .0521415786}, {-.150371962, 1.17387901e-7, -.0554560437}, {-.287366393, 1.87628082e-8, -2.59709359e-5}, {-.271336198, -1.16767401e-9, 2.61269368e-5}, {-.122642483, -.0321145448, .0480403904}, {-.190005945, -.00306615542, -.0003157343}, {.10043214, -.0843452671, .0259565473}, {-1e-8, -.432217537, -.00802912805}, {1e-8, -.421550959, -.0348152298}, {0, -.0505947206, .132315294}, {-.10047278, -.0829525995, .0262031695}, {1e-8, -.433622059, -.00805555828}, {2e-8, -.421173943, -.0347839785}, {-3.42907669e-9, -.0507960932, .132841956}},
|
||||||
|
}
|
||||||
|
skeletonDefinitions["g1skel34"] = skeletonDefinition{
|
||||||
|
key: "g1skel34",
|
||||||
|
names: []string{"pelvis_skel", "left_hip_pitch_skel", "left_hip_roll_skel", "left_hip_yaw_skel", "left_knee_skel", "left_ankle_pitch_skel", "left_ankle_roll_skel", "left_toe_base", "right_hip_pitch_skel", "right_hip_roll_skel", "right_hip_yaw_skel", "right_knee_skel", "right_ankle_pitch_skel", "right_ankle_roll_skel", "right_toe_base", "waist_yaw_skel", "waist_roll_skel", "waist_pitch_skel", "left_shoulder_pitch_skel", "left_shoulder_roll_skel", "left_shoulder_yaw_skel", "left_elbow_skel", "left_wrist_roll_skel", "left_wrist_pitch_skel", "left_wrist_yaw_skel", "left_hand_roll_skel", "right_shoulder_pitch_skel", "right_shoulder_roll_skel", "right_shoulder_yaw_skel", "right_elbow_skel", "right_wrist_roll_skel", "right_wrist_pitch_skel", "right_wrist_yaw_skel", "right_hand_roll_skel"},
|
||||||
|
parents: []int{-1, 0, 1, 2, 3, 4, 5, 6, 0, 8, 9, 10, 11, 12, 13, 0, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 17, 26, 27, 28, 29, 30, 31, 32},
|
||||||
|
offsets: [][3]float32{{0, 0, 0}, {.064452, -.1027, 0}, {.052, -.030465, 0}, {0, -.12412, .025001}, {.0021489, -.17734, -.078273}, {-.000094445, -.30001, 0}, {0, -.017558, 0}, {0, -.035, .14}, {-.064452, -.1027, 0}, {-.052, -.030465, 0}, {0, -.12412, .025001}, {-.0021489, -.17734, -.078273}, {.000094445, -.30001, 0}, {0, -.017558, 0}, {0, -.035, .14}, {0, 0, 0}, {0, .044, -.0039635}, {0, 0, 0}, {.10022, .24778, .0039563}, {.038, -.013831, 0}, {.00624, -.1032, 0}, {0, -.080518, .015783}, {.00188791, -.01, .1}, {0, 0, .038}, {0, 0, .046}, {0, 0, .1}, {-.10021, .24778, .0039563}, {-.038, -.013831, 0}, {-.00624, -.1032, 0}, {0, -.080518, .015783}, {-.00188791, -.01, .1}, {0, 0, .038}, {0, 0, .046}, {0, 0, .1}},
|
||||||
|
}
|
||||||
|
}
|
||||||
@ -32,7 +32,7 @@ def parse_args() -> argparse.Namespace:
|
|||||||
parser.add_argument("--seed", required=True, type=int)
|
parser.add_argument("--seed", required=True, type=int)
|
||||||
parser.add_argument("--device", default="cuda")
|
parser.add_argument("--device", default="cuda")
|
||||||
parser.add_argument("--checkpoint-dir", type=Path,
|
parser.add_argument("--checkpoint-dir", type=Path,
|
||||||
help="local directory containing Kimodo-SMPLX-RP-v1; never download at capture time")
|
help="local directory containing the selected Kimodo checkpoint; never download at capture time")
|
||||||
parser.add_argument("--zero-embedding", action="store_true",
|
parser.add_argument("--zero-embedding", action="store_true",
|
||||||
help="use a deterministic [1,1,4096] zero embedding; enables motion-only fixtures")
|
help="use a deterministic [1,1,4096] zero embedding; enables motion-only fixtures")
|
||||||
parser.add_argument("--text-base", type=Path,
|
parser.add_argument("--text-base", type=Path,
|
||||||
@ -113,8 +113,21 @@ def main() -> None:
|
|||||||
raise SystemExit("--zero-embedding cannot be combined with real text model paths")
|
raise SystemExit("--zero-embedding cannot be combined with real text model paths")
|
||||||
if args.checkpoint_dir:
|
if args.checkpoint_dir:
|
||||||
checkpoint = args.checkpoint_dir.resolve()
|
checkpoint = args.checkpoint_dir.resolve()
|
||||||
if not (checkpoint / "Kimodo-SMPLX-RP-v1" / "config.yaml").is_file():
|
model_folders = {
|
||||||
raise SystemExit("--checkpoint-dir must contain Kimodo-SMPLX-RP-v1/config.yaml")
|
"kimodo-smplx-rp": "Kimodo-SMPLX-RP-v1",
|
||||||
|
"kimodo-smplx-rp-v1": "Kimodo-SMPLX-RP-v1",
|
||||||
|
"kimodo-soma-rp": "Kimodo-SOMA-RP-v1.1",
|
||||||
|
"kimodo-soma-rp-v1.1": "Kimodo-SOMA-RP-v1.1",
|
||||||
|
"kimodo-soma-seed": "Kimodo-SOMA-SEED-v1.1",
|
||||||
|
"kimodo-soma-seed-v1.1": "Kimodo-SOMA-SEED-v1.1",
|
||||||
|
"kimodo-g1-rp": "Kimodo-G1-RP-v1",
|
||||||
|
"kimodo-g1-rp-v1": "Kimodo-G1-RP-v1",
|
||||||
|
"kimodo-g1-seed": "Kimodo-G1-SEED-v1",
|
||||||
|
"kimodo-g1-seed-v1": "Kimodo-G1-SEED-v1",
|
||||||
|
}
|
||||||
|
folder = model_folders.get(args.model)
|
||||||
|
if folder is None or not (checkpoint / folder / "config.yaml").is_file():
|
||||||
|
raise SystemExit("--checkpoint-dir does not contain the selected official Kimodo model")
|
||||||
# This is deliberately set only for the reference subprocess. It
|
# This is deliberately set only for the reference subprocess. It
|
||||||
# prevents a missing local model from silently falling back to HF.
|
# prevents a missing local model from silently falling back to HF.
|
||||||
import os
|
import os
|
||||||
|
|||||||
@ -1,5 +1,5 @@
|
|||||||
#!/usr/bin/env python3
|
#!/usr/bin/env python3
|
||||||
"""Convert the Kimodo SMPL-X safetensors checkpoint to a self-describing GGUF.
|
"""Convert a supported Kimodo motion safetensors checkpoint to GGUF.
|
||||||
|
|
||||||
This converter deliberately implements only the safe safetensors and NPY
|
This converter deliberately implements only the safe safetensors and NPY
|
||||||
formats. It never imports torch, never deserializes pickle, and writes to a
|
formats. It never imports torch, never deserializes pickle, and writes to a
|
||||||
@ -22,6 +22,15 @@ GGUF_MAGIC, GGUF_VERSION, GGML_TYPE_F32 = 0x46554747, 3, 0
|
|||||||
TYPE_UINT64, TYPE_STRING, TYPE_FLOAT32 = 10, 8, 6
|
TYPE_UINT64, TYPE_STRING, TYPE_FLOAT32 = 10, 8, 6
|
||||||
TYPE_UINT32 = 4
|
TYPE_UINT32 = 4
|
||||||
|
|
||||||
|
MODEL_SPECS = {
|
||||||
|
"nvidia/Kimodo-SMPLX-RP-v1": ("smplx22", "SMPLXSkeleton22", 22, False,
|
||||||
|
"nvidia-internal-scientific-research-and-development-model-license"),
|
||||||
|
"nvidia/Kimodo-SOMA-RP-v1.1": ("soma30", "SOMASkeleton30", 30, True, "nvidia-open-model-license"),
|
||||||
|
"nvidia/Kimodo-SOMA-SEED-v1.1": ("soma30", "SOMASkeleton30", 30, True, "nvidia-open-model-license"),
|
||||||
|
"nvidia/Kimodo-G1-RP-v1": ("g1skel34", "G1Skeleton34", 34, True, "nvidia-open-model-license"),
|
||||||
|
"nvidia/Kimodo-G1-SEED-v1": ("g1skel34", "G1Skeleton34", 34, True, "nvidia-open-model-license"),
|
||||||
|
}
|
||||||
|
|
||||||
@dataclass(frozen=True)
|
@dataclass(frozen=True)
|
||||||
class Tensor:
|
class Tensor:
|
||||||
name: str
|
name: str
|
||||||
@ -183,7 +192,7 @@ def copy_range(dst, tensor: Tensor) -> None:
|
|||||||
|
|
||||||
def main() -> None:
|
def main() -> None:
|
||||||
p = argparse.ArgumentParser(description=__doc__)
|
p = argparse.ArgumentParser(description=__doc__)
|
||||||
p.add_argument("--input", required=True, type=Path, help="downloaded Kimodo-SMPLX-RP-v1 directory")
|
p.add_argument("--input", required=True, type=Path, help="downloaded Kimodo model directory")
|
||||||
p.add_argument("--output", required=True, type=Path)
|
p.add_argument("--output", required=True, type=Path)
|
||||||
args = p.parse_args()
|
args = p.parse_args()
|
||||||
root = args.input.resolve()
|
root = args.input.resolve()
|
||||||
@ -195,22 +204,33 @@ def main() -> None:
|
|||||||
for part in ("global_root", "local_root", "body"):
|
for part in ("global_root", "local_root", "body"):
|
||||||
for stat in ("mean", "std"):
|
for stat in ("mean", "std"):
|
||||||
tensors.append(read_npy(root / "stats" / "motion" / part / f"{stat}.npy", f"stats.{part}.{stat}"))
|
tensors.append(read_npy(root / "stats" / "motion" / part / f"{stat}.npy", f"stats.{part}.{stat}"))
|
||||||
revision = (root / "REVISION").read_text(encoding="utf-8").split()[0]
|
revision_fields = (root / "REVISION").read_text(encoding="utf-8").split()
|
||||||
|
if len(revision_fields) != 2 or revision_fields[1] not in MODEL_SPECS:
|
||||||
|
raise SystemExit("REVISION does not identify a supported official Kimodo model")
|
||||||
|
revision, model_id = revision_fields
|
||||||
|
skeleton, skeleton_class, joints, commercial, license_name = MODEL_SPECS[model_id]
|
||||||
|
config = (root / "config.yaml").read_text(encoding="utf-8")
|
||||||
|
if f"_target_: kimodo.skeleton.{skeleton_class}" not in config:
|
||||||
|
raise SystemExit("config.yaml skeleton does not match REVISION model identity")
|
||||||
|
motion_dim = 9 + 12 * joints
|
||||||
|
body_dim = motion_dim - 5
|
||||||
meta = [
|
meta = [
|
||||||
metadata_string("general.architecture", "kimodo-motion"),
|
metadata_string("general.architecture", "kimodo-motion"),
|
||||||
metadata_string("general.name", "Kimodo-SMPLX-RP-v1"),
|
metadata_string("general.name", model_id.removeprefix("nvidia/")),
|
||||||
# GGML's own loader requires general.alignment to be UINT32.
|
# GGML's own loader requires general.alignment to be UINT32.
|
||||||
metadata_uint32("general.alignment", ALIGNMENT),
|
metadata_uint32("general.alignment", ALIGNMENT),
|
||||||
metadata_uint("kimodo.format_version", 1),
|
metadata_uint("kimodo.format_version", 1),
|
||||||
metadata_string("kimodo.skeleton", "smplx22"),
|
metadata_string("kimodo.skeleton", skeleton),
|
||||||
metadata_string("kimodo.model_identity", f"nvidia/Kimodo-SMPLX-RP-v1@{revision}"),
|
metadata_string("kimodo.model_identity", f"{model_id}@{revision}"),
|
||||||
|
metadata_string("kimodo.license", license_name),
|
||||||
|
metadata_uint("kimodo.commercial_use", int(commercial)),
|
||||||
metadata_string("kimodo.source_revision", revision),
|
metadata_string("kimodo.source_revision", revision),
|
||||||
metadata_string("kimodo.source_sha256", sha256(ckpt)),
|
metadata_string("kimodo.source_sha256", sha256(ckpt)),
|
||||||
metadata_uint("kimodo.text_embedding_width", 4096),
|
metadata_uint("kimodo.text_embedding_width", 4096),
|
||||||
metadata_uint("kimodo.motion_dim", 273),
|
metadata_uint("kimodo.motion_dim", motion_dim),
|
||||||
metadata_uint("kimodo.global_root_dim", 5),
|
metadata_uint("kimodo.global_root_dim", 5),
|
||||||
metadata_uint("kimodo.local_root_dim", 4),
|
metadata_uint("kimodo.local_root_dim", 4),
|
||||||
metadata_uint("kimodo.body_dim", 268),
|
metadata_uint("kimodo.body_dim", body_dim),
|
||||||
metadata_uint("kimodo.hidden_size", 1024),
|
metadata_uint("kimodo.hidden_size", 1024),
|
||||||
metadata_uint("kimodo.layers", 16),
|
metadata_uint("kimodo.layers", 16),
|
||||||
metadata_uint("kimodo.heads", 8),
|
metadata_uint("kimodo.heads", 8),
|
||||||
|
|||||||
@ -4,19 +4,20 @@ set -euo pipefail
|
|||||||
export HF_HUB_DISABLE_PROGRESS_BARS=1
|
export HF_HUB_DISABLE_PROGRESS_BARS=1
|
||||||
|
|
||||||
ORG="${GGUF_ORG:-LocalAI-io}"
|
ORG="${GGUF_ORG:-LocalAI-io}"
|
||||||
MOTION_REPO_DEFAULT="$ORG/Kimodo-SMPLX-RP-v1-GGML"
|
|
||||||
TEXT_REPO_DEFAULT="$ORG/Llama-3-Kimodo-GGML"
|
TEXT_REPO_DEFAULT="$ORG/Llama-3-Kimodo-GGML"
|
||||||
|
|
||||||
usage() {
|
usage() {
|
||||||
printf '%s\n' "usage: $0 --output DIR [--motion-repo HF_REPO] [--text-repo HF_REPO] [--revision REVISION] [--motion-only]" >&2
|
printf '%s\n' "usage: $0 --output DIR [--model MODEL]... [--motion-repo HF_REPO] [--text-repo HF_REPO] [--revision REVISION] [--motion-only]" >&2
|
||||||
|
printf '%s\n' "models: soma-rp-v1.1, soma-seed-v1.1, g1-rp-v1, g1-seed-v1" >&2
|
||||||
exit 2
|
exit 2
|
||||||
}
|
}
|
||||||
|
|
||||||
output='' motion_repo="$MOTION_REPO_DEFAULT" text_repo="$TEXT_REPO_DEFAULT" revision='main' motion_only=0
|
output='' motion_repo_override='' text_repo="$TEXT_REPO_DEFAULT" revision='main' motion_only=0 models=()
|
||||||
while [ "$#" -gt 0 ]; do
|
while [ "$#" -gt 0 ]; do
|
||||||
case "$1" in
|
case "$1" in
|
||||||
--output) [ "$#" -ge 2 ] || usage; output=$2; shift 2 ;;
|
--output) [ "$#" -ge 2 ] || usage; output=$2; shift 2 ;;
|
||||||
--motion-repo) [ "$#" -ge 2 ] || usage; motion_repo=$2; shift 2 ;;
|
--model) [ "$#" -ge 2 ] || usage; models+=("$2"); shift 2 ;;
|
||||||
|
--motion-repo) [ "$#" -ge 2 ] || usage; motion_repo_override=$2; shift 2 ;;
|
||||||
--text-repo) [ "$#" -ge 2 ] || usage; text_repo=$2; shift 2 ;;
|
--text-repo) [ "$#" -ge 2 ] || usage; text_repo=$2; shift 2 ;;
|
||||||
--revision) [ "$#" -ge 2 ] || usage; revision=$2; shift 2 ;;
|
--revision) [ "$#" -ge 2 ] || usage; revision=$2; shift 2 ;;
|
||||||
--motion-only) motion_only=1; shift ;;
|
--motion-only) motion_only=1; shift ;;
|
||||||
@ -25,6 +26,8 @@ while [ "$#" -gt 0 ]; do
|
|||||||
done
|
done
|
||||||
[ -n "$output" ] || usage
|
[ -n "$output" ] || usage
|
||||||
command -v hf >/dev/null || { echo "hf not found; enter the Nix shell first" >&2; exit 1; }
|
command -v hf >/dev/null || { echo "hf not found; enter the Nix shell first" >&2; exit 1; }
|
||||||
|
[ "${#models[@]}" -gt 0 ] || models=(soma-rp-v1.1)
|
||||||
|
[ -z "$motion_repo_override" ] || [ "${#models[@]}" -eq 1 ] || { echo "--motion-repo requires exactly one --model" >&2; exit 2; }
|
||||||
|
|
||||||
mkdir -p "$output"
|
mkdir -p "$output"
|
||||||
|
|
||||||
@ -70,7 +73,17 @@ print("verified native Kimodo GGUF bundle")
|
|||||||
PY
|
PY
|
||||||
}
|
}
|
||||||
|
|
||||||
download_and_verify "$motion_repo" "models/kimodo-smplx-rp-v1-f32.gguf"
|
for model in "${models[@]}"; do
|
||||||
|
case "$model" in
|
||||||
|
soma-rp-v1.1) motion_repo="$ORG/Kimodo-SOMA-RP-v1.1-GGML"; motion_file='models/kimodo-soma-rp-v1.1-f32.gguf' ;;
|
||||||
|
soma-seed-v1.1) motion_repo="$ORG/Kimodo-SOMA-SEED-v1.1-GGML"; motion_file='models/kimodo-soma-seed-v1.1-f32.gguf' ;;
|
||||||
|
g1-rp-v1) motion_repo="$ORG/Kimodo-G1-RP-v1-GGML"; motion_file='models/kimodo-g1-rp-v1-f32.gguf' ;;
|
||||||
|
g1-seed-v1) motion_repo="$ORG/Kimodo-G1-SEED-v1-GGML"; motion_file='models/kimodo-g1-seed-v1-f32.gguf' ;;
|
||||||
|
*) echo "unknown motion model: $model" >&2; usage ;;
|
||||||
|
esac
|
||||||
|
[ -z "$motion_repo_override" ] || motion_repo=$motion_repo_override
|
||||||
|
download_and_verify "$motion_repo" "$motion_file"
|
||||||
|
done
|
||||||
if [ "$motion_only" -eq 0 ]; then
|
if [ "$motion_only" -eq 0 ]; then
|
||||||
download_and_verify "$text_repo" "generated/llm2vec-text-bundle/*"
|
download_and_verify "$text_repo" "generated/llm2vec-text-bundle/*"
|
||||||
fi
|
fi
|
||||||
|
|||||||
@ -6,15 +6,17 @@ set -euo pipefail
|
|||||||
export HF_HUB_DISABLE_PROGRESS_BARS=1
|
export HF_HUB_DISABLE_PROGRESS_BARS=1
|
||||||
|
|
||||||
usage() {
|
usage() {
|
||||||
printf '%s\n' "usage: $0 --output DIR [--revision REVISION] [--with-text]" >&2
|
printf '%s\n' "usage: $0 --output DIR [--revision REVISION] [--model NAME]... [--with-text]" >&2
|
||||||
exit 2
|
exit 2
|
||||||
}
|
}
|
||||||
|
|
||||||
output='' revision='main' with_text=0
|
output='' revision='main' with_text=0
|
||||||
|
models=()
|
||||||
while [ "$#" -gt 0 ]; do
|
while [ "$#" -gt 0 ]; do
|
||||||
case "$1" in
|
case "$1" in
|
||||||
--output) [ "$#" -ge 2 ] || usage; output=$2; shift 2 ;;
|
--output) [ "$#" -ge 2 ] || usage; output=$2; shift 2 ;;
|
||||||
--revision) [ "$#" -ge 2 ] || usage; revision=$2; shift 2 ;;
|
--revision) [ "$#" -ge 2 ] || usage; revision=$2; shift 2 ;;
|
||||||
|
--model) [ "$#" -ge 2 ] || usage; models+=("$2"); shift 2 ;;
|
||||||
--with-text) with_text=1; shift ;;
|
--with-text) with_text=1; shift ;;
|
||||||
*) usage ;;
|
*) usage ;;
|
||||||
esac
|
esac
|
||||||
@ -52,7 +54,18 @@ download() {
|
|||||||
printf '%s %s\n' "$sha" "$repo" > "$target/REVISION"
|
printf '%s %s\n' "$sha" "$repo" > "$target/REVISION"
|
||||||
}
|
}
|
||||||
|
|
||||||
download nvidia/Kimodo-SMPLX-RP-v1 Kimodo-SMPLX-RP-v1
|
if [ "${#models[@]}" -eq 0 ]; then models=(smplx-rp-v1); fi
|
||||||
|
for model in "${models[@]}"; do
|
||||||
|
case "$model" in
|
||||||
|
smplx-rp-v1) repo=nvidia/Kimodo-SMPLX-RP-v1; folder=Kimodo-SMPLX-RP-v1 ;;
|
||||||
|
soma-rp-v1.1) repo=nvidia/Kimodo-SOMA-RP-v1.1; folder=Kimodo-SOMA-RP-v1.1 ;;
|
||||||
|
soma-seed-v1.1) repo=nvidia/Kimodo-SOMA-SEED-v1.1; folder=Kimodo-SOMA-SEED-v1.1 ;;
|
||||||
|
g1-rp-v1) repo=nvidia/Kimodo-G1-RP-v1; folder=Kimodo-G1-RP-v1 ;;
|
||||||
|
g1-seed-v1) repo=nvidia/Kimodo-G1-SEED-v1; folder=Kimodo-G1-SEED-v1 ;;
|
||||||
|
*) echo "Unknown Kimodo model: $model" >&2; usage ;;
|
||||||
|
esac
|
||||||
|
download "$repo" "$folder"
|
||||||
|
done
|
||||||
if [ "$with_text" -eq 1 ]; then
|
if [ "$with_text" -eq 1 ]; then
|
||||||
# The MNTP repo is a LoRA adapter, not the Llama base checkpoint. Keep all
|
# The MNTP repo is a LoRA adapter, not the Llama base checkpoint. Keep all
|
||||||
# three identities separately so converter provenance cannot confuse them.
|
# three identities separately so converter provenance cannot confuse them.
|
||||||
|
|||||||
4
scripts/hf/Kimodo-G1-RP-v1-GGML/NOTICE
Normal file
4
scripts/hf/Kimodo-G1-RP-v1-GGML/NOTICE
Normal file
@ -0,0 +1,4 @@
|
|||||||
|
Licensed by NVIDIA Corporation under the NVIDIA Open Model License.
|
||||||
|
|
||||||
|
Upstream model: nvidia/Kimodo-G1-RP-v1. This GGUF conversion grants no
|
||||||
|
additional rights.
|
||||||
25
scripts/hf/Kimodo-G1-RP-v1-GGML/README.md
Normal file
25
scripts/hf/Kimodo-G1-RP-v1-GGML/README.md
Normal file
@ -0,0 +1,25 @@
|
|||||||
|
---
|
||||||
|
license: other
|
||||||
|
library_name: ggml
|
||||||
|
base_model: nvidia/Kimodo-G1-RP-v1
|
||||||
|
base_model_relation: quantized
|
||||||
|
tags: [gguf, ggml, text-to-motion, unitree-g1, kimodo]
|
||||||
|
---
|
||||||
|
|
||||||
|
# Kimodo-G1-RP-v1-GGML
|
||||||
|
|
||||||
|
Native F32 GGML/GGUF conversion of
|
||||||
|
[nvidia/Kimodo-G1-RP-v1](https://huggingface.co/nvidia/Kimodo-G1-RP-v1),
|
||||||
|
targeting the 34-joint Unitree G1 skeleton. Its reusable Llama-derived text
|
||||||
|
encoder is distributed separately as
|
||||||
|
[`Llama-3-Kimodo-GGML`](https://huggingface.co/LocalAI-io/Llama-3-Kimodo-GGML).
|
||||||
|
|
||||||
|
The model is installed at `models/kimodo-g1-rp-v1-f32.gguf` by
|
||||||
|
`scripts/download_gguf_weights.sh --output "$PWD" --model g1-rp-v1`.
|
||||||
|
|
||||||
|
## Provenance and licence
|
||||||
|
|
||||||
|
Converted from upstream revision `3020ad8c419c244e0429d360163730c63c4ed011`.
|
||||||
|
`MANIFEST.json` records the source revision and SHA-256 of the GGUF. The model
|
||||||
|
remains subject to the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/).
|
||||||
|
This conversion grants no additional rights.
|
||||||
4
scripts/hf/Kimodo-G1-SEED-v1-GGML/NOTICE
Normal file
4
scripts/hf/Kimodo-G1-SEED-v1-GGML/NOTICE
Normal file
@ -0,0 +1,4 @@
|
|||||||
|
Licensed by NVIDIA Corporation under the NVIDIA Open Model License.
|
||||||
|
|
||||||
|
Upstream model: nvidia/Kimodo-G1-SEED-v1. This GGUF conversion grants no
|
||||||
|
additional rights.
|
||||||
25
scripts/hf/Kimodo-G1-SEED-v1-GGML/README.md
Normal file
25
scripts/hf/Kimodo-G1-SEED-v1-GGML/README.md
Normal file
@ -0,0 +1,25 @@
|
|||||||
|
---
|
||||||
|
license: other
|
||||||
|
library_name: ggml
|
||||||
|
base_model: nvidia/Kimodo-G1-SEED-v1
|
||||||
|
base_model_relation: quantized
|
||||||
|
tags: [gguf, ggml, text-to-motion, unitree-g1, kimodo]
|
||||||
|
---
|
||||||
|
|
||||||
|
# Kimodo-G1-SEED-v1-GGML
|
||||||
|
|
||||||
|
Native F32 GGML/GGUF conversion of
|
||||||
|
[nvidia/Kimodo-G1-SEED-v1](https://huggingface.co/nvidia/Kimodo-G1-SEED-v1),
|
||||||
|
targeting the 34-joint Unitree G1 skeleton. Its reusable Llama-derived text
|
||||||
|
encoder is distributed separately as
|
||||||
|
[`Llama-3-Kimodo-GGML`](https://huggingface.co/LocalAI-io/Llama-3-Kimodo-GGML).
|
||||||
|
|
||||||
|
The model is installed at `models/kimodo-g1-seed-v1-f32.gguf` by
|
||||||
|
`scripts/download_gguf_weights.sh --output "$PWD" --model g1-seed-v1`.
|
||||||
|
|
||||||
|
## Provenance and licence
|
||||||
|
|
||||||
|
Converted from upstream revision `5e6f2c7e18c2ab834c8d7983b9dcce701e5c6097`.
|
||||||
|
`MANIFEST.json` records the source revision and SHA-256 of the GGUF. The model
|
||||||
|
remains subject to the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/).
|
||||||
|
This conversion grants no additional rights.
|
||||||
@ -1,3 +1,4 @@
|
|||||||
Kimodo-SMPLX-RP-v1 source model: NVIDIA. This converted distribution remains
|
Kimodo-SMPLX-RP-v1 source model: NVIDIA. The NVIDIA Internal Scientific
|
||||||
subject to the NVIDIA Internal Scientific Research and Development Model License
|
Research and Development Model License limits derivative models to internal,
|
||||||
and is for non-commercial research use only.
|
non-production R&D and prohibits their distribution. This notice is retained
|
||||||
|
for local conversion records; it does not authorize a converted distribution.
|
||||||
|
|||||||
@ -6,30 +6,31 @@ base_model_relation: quantized
|
|||||||
tags: [gguf, ggml, text-to-motion, smplx, kimodo]
|
tags: [gguf, ggml, text-to-motion, smplx, kimodo]
|
||||||
---
|
---
|
||||||
|
|
||||||
# Kimodo-SMPLX-RP-v1-GGML
|
# Oops — Kimodo-SMPLX-RP-v1 is local-conversion only
|
||||||
|
|
||||||
Native F32 GGML/GGUF conversion of
|
The kimodo.cpp converter can produce a local F32 GGML/GGUF representation of
|
||||||
[nvidia/Kimodo-SMPLX-RP-v1](https://huggingface.co/nvidia/Kimodo-SMPLX-RP-v1),
|
[nvidia/Kimodo-SMPLX-RP-v1](https://huggingface.co/nvidia/Kimodo-SMPLX-RP-v1),
|
||||||
the SMPL-X 22-joint text-and-constraint conditioned motion diffusion model.
|
the SMPL-X 22-joint text-and-constraint conditioned motion diffusion model.
|
||||||
This repository contains only the diffusion model; its reusable Llama-derived
|
It is not a redistributable GGUF release.
|
||||||
text encoder is distributed separately as
|
|
||||||
[`Llama-3-Kimodo-GGML`](https://huggingface.co/LocalAI-io/Llama-3-Kimodo-GGML).
|
|
||||||
|
|
||||||
From a kimodo.cpp checkout with the Hugging Face CLI installed, install both with:
|
We originally published the converted weights here, then noticed that the
|
||||||
|
upstream NVIDIA Internal Scientific Research and Development Model License
|
||||||
|
explicitly prohibits distributing derivative models. Oops. The GGUF, manifest,
|
||||||
|
and checksums have therefore been removed; this card remains so that existing
|
||||||
|
links explain what happened instead of becoming a mysterious 404.
|
||||||
|
|
||||||
```sh
|
If someone at NVIDIA is willing to give LocalAI-io written permission to
|
||||||
scripts/download_gguf_weights.sh --output "$PWD"
|
redistribute this checkpoint as GGML/GGUF, that would be very welcome. We would
|
||||||
```
|
be happy to restore the conversion with its upstream provenance and verified
|
||||||
|
parity results.
|
||||||
The model is installed at `models/kimodo-smplx-rp-v1-f32.gguf`. Use
|
|
||||||
`--motion-only` when supplying a precomputed LLM2Vec embedding.
|
|
||||||
|
|
||||||
## Provenance and licence
|
## Provenance and licence
|
||||||
|
|
||||||
Converted by kimodo.cpp from upstream commit
|
The local converter targets upstream revision
|
||||||
`1419ba56b734c48bbafb41fefa84088ca94583b5`. `MANIFEST.json` records the
|
`1419ba56b734c48bbafb41fefa84088ca94583b5`.
|
||||||
source revision and SHA-256 of the GGUF.
|
|
||||||
|
|
||||||
Kimodo-SMPLX-RP-v1 is for non-commercial research use only and remains subject
|
Kimodo-SMPLX-RP-v1 remains subject to the
|
||||||
to the [NVIDIA Internal Scientific Research and Development Model License](https://huggingface.co/nvidia/Kimodo-SMPLX-RP-v1).
|
[NVIDIA Internal Scientific Research and Development Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/).
|
||||||
This conversion grants no additional rights.
|
That licence limits the checkpoint and derivative models to internal,
|
||||||
|
non-production R&D and prohibits their distribution. Converting the weights to
|
||||||
|
GGUF does not grant additional rights.
|
||||||
|
|||||||
4
scripts/hf/Kimodo-SOMA-RP-v1.1-GGML/NOTICE
Normal file
4
scripts/hf/Kimodo-SOMA-RP-v1.1-GGML/NOTICE
Normal file
@ -0,0 +1,4 @@
|
|||||||
|
Licensed by NVIDIA Corporation under the NVIDIA Open Model License.
|
||||||
|
|
||||||
|
Upstream model: nvidia/Kimodo-SOMA-RP-v1.1. This GGUF conversion grants no
|
||||||
|
additional rights.
|
||||||
25
scripts/hf/Kimodo-SOMA-RP-v1.1-GGML/README.md
Normal file
25
scripts/hf/Kimodo-SOMA-RP-v1.1-GGML/README.md
Normal file
@ -0,0 +1,25 @@
|
|||||||
|
---
|
||||||
|
license: other
|
||||||
|
library_name: ggml
|
||||||
|
base_model: nvidia/Kimodo-SOMA-RP-v1.1
|
||||||
|
base_model_relation: quantized
|
||||||
|
tags: [gguf, ggml, text-to-motion, soma, kimodo]
|
||||||
|
---
|
||||||
|
|
||||||
|
# Kimodo-SOMA-RP-v1.1-GGML
|
||||||
|
|
||||||
|
Native F32 GGML/GGUF conversion of
|
||||||
|
[nvidia/Kimodo-SOMA-RP-v1.1](https://huggingface.co/nvidia/Kimodo-SOMA-RP-v1.1).
|
||||||
|
The model predicts the compact SOMA 30-joint control skeleton. Its reusable
|
||||||
|
Llama-derived text encoder is distributed separately as
|
||||||
|
[`Llama-3-Kimodo-GGML`](https://huggingface.co/LocalAI-io/Llama-3-Kimodo-GGML).
|
||||||
|
|
||||||
|
The model is installed at `models/kimodo-soma-rp-v1.1-f32.gguf` by
|
||||||
|
`scripts/download_gguf_weights.sh --output "$PWD" --model soma-rp-v1.1`.
|
||||||
|
|
||||||
|
## Provenance and licence
|
||||||
|
|
||||||
|
Converted from upstream revision `6c9233af1180b8151e3c4703477104af5dce9dd5`.
|
||||||
|
`MANIFEST.json` records the source revision and SHA-256 of the GGUF. The model
|
||||||
|
remains subject to the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/).
|
||||||
|
This conversion grants no additional rights.
|
||||||
4
scripts/hf/Kimodo-SOMA-SEED-v1.1-GGML/NOTICE
Normal file
4
scripts/hf/Kimodo-SOMA-SEED-v1.1-GGML/NOTICE
Normal file
@ -0,0 +1,4 @@
|
|||||||
|
Licensed by NVIDIA Corporation under the NVIDIA Open Model License.
|
||||||
|
|
||||||
|
Upstream model: nvidia/Kimodo-SOMA-SEED-v1.1. This GGUF conversion grants no
|
||||||
|
additional rights.
|
||||||
25
scripts/hf/Kimodo-SOMA-SEED-v1.1-GGML/README.md
Normal file
25
scripts/hf/Kimodo-SOMA-SEED-v1.1-GGML/README.md
Normal file
@ -0,0 +1,25 @@
|
|||||||
|
---
|
||||||
|
license: other
|
||||||
|
library_name: ggml
|
||||||
|
base_model: nvidia/Kimodo-SOMA-SEED-v1.1
|
||||||
|
base_model_relation: quantized
|
||||||
|
tags: [gguf, ggml, text-to-motion, soma, kimodo]
|
||||||
|
---
|
||||||
|
|
||||||
|
# Kimodo-SOMA-SEED-v1.1-GGML
|
||||||
|
|
||||||
|
Native F32 GGML/GGUF conversion of
|
||||||
|
[nvidia/Kimodo-SOMA-SEED-v1.1](https://huggingface.co/nvidia/Kimodo-SOMA-SEED-v1.1).
|
||||||
|
The model predicts the compact SOMA 30-joint control skeleton. Its reusable
|
||||||
|
Llama-derived text encoder is distributed separately as
|
||||||
|
[`Llama-3-Kimodo-GGML`](https://huggingface.co/LocalAI-io/Llama-3-Kimodo-GGML).
|
||||||
|
|
||||||
|
The model is installed at `models/kimodo-soma-seed-v1.1-f32.gguf` by
|
||||||
|
`scripts/download_gguf_weights.sh --output "$PWD" --model soma-seed-v1.1`.
|
||||||
|
|
||||||
|
## Provenance and licence
|
||||||
|
|
||||||
|
Converted from upstream revision `aae3af194322c60d21bc44062b64c3fec912be50`.
|
||||||
|
`MANIFEST.json` records the source revision and SHA-256 of the GGUF. The model
|
||||||
|
remains subject to the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/).
|
||||||
|
This conversion grants no additional rights.
|
||||||
@ -23,15 +23,54 @@ ROOT = Path(__file__).resolve().parent.parent
|
|||||||
HF_ORG = "LocalAI-io" # Hugging Face organisation; GitHub is localai-org.
|
HF_ORG = "LocalAI-io" # Hugging Face organisation; GitHub is localai-org.
|
||||||
DEFAULT_REPOS = {
|
DEFAULT_REPOS = {
|
||||||
"text": f"{HF_ORG}/Llama-3-Kimodo-GGML",
|
"text": f"{HF_ORG}/Llama-3-Kimodo-GGML",
|
||||||
"motion": f"{HF_ORG}/Kimodo-SMPLX-RP-v1-GGML",
|
|
||||||
}
|
}
|
||||||
MOTION_NAME = "kimodo-smplx-rp-v1-f32.gguf"
|
MOTION_MODELS = {
|
||||||
|
"smplx-rp-v1": {
|
||||||
|
"repo": f"{HF_ORG}/Kimodo-SMPLX-RP-v1-GGML",
|
||||||
|
"source": "nvidia/Kimodo-SMPLX-RP-v1",
|
||||||
|
"folder": "Kimodo-SMPLX-RP-v1",
|
||||||
|
"revision": "1419ba56b734c48bbafb41fefa84088ca94583b5",
|
||||||
|
"file": "kimodo-smplx-rp-v1-f32.gguf",
|
||||||
|
"redistributable": False,
|
||||||
|
},
|
||||||
|
"soma-rp-v1.1": {
|
||||||
|
"repo": f"{HF_ORG}/Kimodo-SOMA-RP-v1.1-GGML",
|
||||||
|
"source": "nvidia/Kimodo-SOMA-RP-v1.1",
|
||||||
|
"folder": "Kimodo-SOMA-RP-v1.1",
|
||||||
|
"revision": "6c9233af1180b8151e3c4703477104af5dce9dd5",
|
||||||
|
"file": "kimodo-soma-rp-v1.1-f32.gguf",
|
||||||
|
"redistributable": True,
|
||||||
|
},
|
||||||
|
"soma-seed-v1.1": {
|
||||||
|
"repo": f"{HF_ORG}/Kimodo-SOMA-SEED-v1.1-GGML",
|
||||||
|
"source": "nvidia/Kimodo-SOMA-SEED-v1.1",
|
||||||
|
"folder": "Kimodo-SOMA-SEED-v1.1",
|
||||||
|
"revision": "aae3af194322c60d21bc44062b64c3fec912be50",
|
||||||
|
"file": "kimodo-soma-seed-v1.1-f32.gguf",
|
||||||
|
"redistributable": True,
|
||||||
|
},
|
||||||
|
"g1-rp-v1": {
|
||||||
|
"repo": f"{HF_ORG}/Kimodo-G1-RP-v1-GGML",
|
||||||
|
"source": "nvidia/Kimodo-G1-RP-v1",
|
||||||
|
"folder": "Kimodo-G1-RP-v1",
|
||||||
|
"revision": "3020ad8c419c244e0429d360163730c63c4ed011",
|
||||||
|
"file": "kimodo-g1-rp-v1-f32.gguf",
|
||||||
|
"redistributable": True,
|
||||||
|
},
|
||||||
|
"g1-seed-v1": {
|
||||||
|
"repo": f"{HF_ORG}/Kimodo-G1-SEED-v1-GGML",
|
||||||
|
"source": "nvidia/Kimodo-G1-SEED-v1",
|
||||||
|
"folder": "Kimodo-G1-SEED-v1",
|
||||||
|
"revision": "5e6f2c7e18c2ab834c8d7983b9dcce701e5c6097",
|
||||||
|
"file": "kimodo-g1-seed-v1-f32.gguf",
|
||||||
|
"redistributable": True,
|
||||||
|
},
|
||||||
|
}
|
||||||
TEXT_NAMES = (
|
TEXT_NAMES = (
|
||||||
"tokenizer.gguf", "embedding.gguf", "final-norm.gguf",
|
"tokenizer.gguf", "embedding.gguf", "final-norm.gguf",
|
||||||
*(f"layer-{index:02d}.gguf" for index in range(32)),
|
*(f"layer-{index:02d}.gguf" for index in range(32)),
|
||||||
)
|
)
|
||||||
SOURCE_REVISIONS = {
|
SOURCE_REVISIONS = {
|
||||||
"nvidia/Kimodo-SMPLX-RP-v1": "1419ba56b734c48bbafb41fefa84088ca94583b5",
|
|
||||||
"meta-llama/Meta-Llama-3-8B-Instruct": "8afb486c1db24fe5011ec46dfbe5b5dccdb575c2",
|
"meta-llama/Meta-Llama-3-8B-Instruct": "8afb486c1db24fe5011ec46dfbe5b5dccdb575c2",
|
||||||
"McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp": "31474e395ada192e8ed1586db6be79fb3b70c9c0",
|
"McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp": "31474e395ada192e8ed1586db6be79fb3b70c9c0",
|
||||||
"McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised": "baa8ebf04a1c2500e61288e7dad65e8ae42601a7",
|
"McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised": "baa8ebf04a1c2500e61288e7dad65e8ae42601a7",
|
||||||
@ -47,24 +86,23 @@ def digest(path: Path) -> str:
|
|||||||
return value.hexdigest()
|
return value.hexdigest()
|
||||||
|
|
||||||
|
|
||||||
def require_revision(repo: str) -> None:
|
def require_revision(repo: str, expected: str, folder: str | None = None) -> None:
|
||||||
revision = ROOT / "models" / {
|
revision = ROOT / "models" / (folder or {
|
||||||
"nvidia/Kimodo-SMPLX-RP-v1": "Kimodo-SMPLX-RP-v1",
|
|
||||||
"meta-llama/Meta-Llama-3-8B-Instruct": "llama3-8b-instruct-base",
|
"meta-llama/Meta-Llama-3-8B-Instruct": "llama3-8b-instruct-base",
|
||||||
"McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp": "llm2vec-mntp-adapter",
|
"McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp": "llm2vec-mntp-adapter",
|
||||||
"McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised": "llm2vec-adapter",
|
"McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised": "llm2vec-adapter",
|
||||||
}[repo] / "REVISION"
|
}[repo]) / "REVISION"
|
||||||
if not revision.is_file():
|
if not revision.is_file():
|
||||||
raise ValueError(f"missing provenance file: {revision}")
|
raise ValueError(f"missing provenance file: {revision}")
|
||||||
actual = revision.read_text(encoding="utf-8").split()[0]
|
actual = revision.read_text(encoding="utf-8").split()[0]
|
||||||
if actual != SOURCE_REVISIONS[repo]:
|
if actual != expected:
|
||||||
raise ValueError(f"unexpected {repo} revision: {actual} (expected {SOURCE_REVISIONS[repo]})")
|
raise ValueError(f"unexpected {repo} revision: {actual} (expected {expected})")
|
||||||
|
|
||||||
|
|
||||||
def artifacts(component: str, motion: Path, bundle: Path) -> list[tuple[Path, str]]:
|
def artifacts(component: str, motion: Path, motion_name: str, bundle: Path) -> list[tuple[Path, str]]:
|
||||||
result: list[tuple[Path, str]] = []
|
result: list[tuple[Path, str]] = []
|
||||||
if component == "motion":
|
if component == "motion":
|
||||||
result.append((motion, f"models/{MOTION_NAME}"))
|
result.append((motion, f"models/{motion_name}"))
|
||||||
else:
|
else:
|
||||||
result.extend((bundle / name, f"generated/llm2vec-text-bundle/{name}") for name in TEXT_NAMES)
|
result.extend((bundle / name, f"generated/llm2vec-text-bundle/{name}") for name in TEXT_NAMES)
|
||||||
for source, destination in result:
|
for source, destination in result:
|
||||||
@ -82,7 +120,9 @@ def artifacts(component: str, motion: Path, bundle: Path) -> list[tuple[Path, st
|
|||||||
|
|
||||||
def main() -> int:
|
def main() -> int:
|
||||||
parser = argparse.ArgumentParser(description=__doc__)
|
parser = argparse.ArgumentParser(description=__doc__)
|
||||||
parser.add_argument("--motion", type=Path, default=ROOT / "models" / MOTION_NAME)
|
parser.add_argument("--motion", type=Path, default=None,
|
||||||
|
help="motion GGUF (defaults to the selected model's converted output)")
|
||||||
|
parser.add_argument("--motion-model", choices=tuple(MOTION_MODELS), default="soma-rp-v1.1")
|
||||||
parser.add_argument("--text-bundle", type=Path,
|
parser.add_argument("--text-bundle", type=Path,
|
||||||
default=ROOT / "generated/llm2vec-text-bundle")
|
default=ROOT / "generated/llm2vec-text-bundle")
|
||||||
parser.add_argument("--component", choices=("text", "motion"), required=True,
|
parser.add_argument("--component", choices=("text", "motion"), required=True,
|
||||||
@ -93,21 +133,28 @@ def main() -> int:
|
|||||||
parser.add_argument("--confirm-upstream-licences", action="store_true",
|
parser.add_argument("--confirm-upstream-licences", action="store_true",
|
||||||
help="required with --upload; confirms authority to redistribute all inputs")
|
help="required with --upload; confirms authority to redistribute all inputs")
|
||||||
args = parser.parse_args()
|
args = parser.parse_args()
|
||||||
repo = args.repo or DEFAULT_REPOS[args.component]
|
motion_spec = MOTION_MODELS[args.motion_model]
|
||||||
card_dir = ROOT / "scripts/hf" / ("Llama-3-Kimodo-GGML" if args.component == "text" else "Kimodo-SMPLX-RP-v1-GGML")
|
if args.component == "motion" and args.upload and not motion_spec["redistributable"]:
|
||||||
|
print("error: the SMPL-X checkpoint licence prohibits distributing Derivative Models; local conversion only",
|
||||||
|
file=sys.stderr)
|
||||||
|
return 2
|
||||||
|
motion = args.motion or ROOT / "models" / motion_spec["file"]
|
||||||
|
repo = args.repo or (DEFAULT_REPOS["text"] if args.component == "text" else motion_spec["repo"])
|
||||||
|
card_dir = ROOT / "scripts/hf" / ("Llama-3-Kimodo-GGML" if args.component == "text" else repo.rsplit("/", 1)[1])
|
||||||
card = card_dir / "README.md"
|
card = card_dir / "README.md"
|
||||||
notice = card_dir / "NOTICE"
|
notice = card_dir / "NOTICE"
|
||||||
relevant_sources = (SOURCE_REVISIONS if args.component == "text"
|
relevant_sources = (SOURCE_REVISIONS if args.component == "text"
|
||||||
else {"nvidia/Kimodo-SMPLX-RP-v1": SOURCE_REVISIONS["nvidia/Kimodo-SMPLX-RP-v1"]})
|
else {motion_spec["source"]: motion_spec["revision"]})
|
||||||
|
|
||||||
try:
|
try:
|
||||||
if not card.is_file() or not notice.is_file():
|
if not card.is_file() or not notice.is_file():
|
||||||
raise ValueError("version-controlled model card or NOTICE is missing")
|
raise ValueError("version-controlled model card or NOTICE is missing")
|
||||||
if args.component == "text" and not LLAMA_LICENSE.is_file():
|
if args.component == "text" and not LLAMA_LICENSE.is_file():
|
||||||
raise ValueError("Meta Llama 3 licence is missing")
|
raise ValueError("Meta Llama 3 licence is missing")
|
||||||
for source_repo in relevant_sources:
|
for source_repo, revision in relevant_sources.items():
|
||||||
require_revision(source_repo)
|
folder = motion_spec["folder"] if args.component == "motion" else None
|
||||||
files = artifacts(args.component, args.motion, args.text_bundle)
|
require_revision(source_repo, revision, folder)
|
||||||
|
files = artifacts(args.component, motion, motion_spec["file"], args.text_bundle)
|
||||||
except ValueError as error:
|
except ValueError as error:
|
||||||
print(f"error: {error}", file=sys.stderr)
|
print(f"error: {error}", file=sys.stderr)
|
||||||
return 1
|
return 1
|
||||||
|
|||||||
@ -90,9 +90,10 @@ std::expected<std::vector<float>, std::string> run_two_stage_denoiser(
|
|||||||
std::span<const float> embedding, std::span<const float> timesteps,
|
std::span<const float> embedding, std::span<const float> timesteps,
|
||||||
std::span<const float> headings, std::span<const float> mask,
|
std::span<const float> headings, std::span<const float> mask,
|
||||||
std::size_t batch, std::size_t frames) {
|
std::size_t batch, std::size_t frames) {
|
||||||
if (!batch || !frames || x.size()!=batch*frames*546 || mask.size()!=batch*frames)
|
const size_t dim=weights.motion_dim(), root_input_dim=2*dim, body_input_dim=2*dim-1;
|
||||||
|
if (!batch || !frames || !dim || x.size()!=batch*frames*root_input_dim || mask.size()!=batch*frames)
|
||||||
return std::unexpected("invalid two-stage denoiser input dimensions");
|
return std::unexpected("invalid two-stage denoiser input dimensions");
|
||||||
auto root=run_motion_transformer(weights,"root_model.",x,546,embedding,timesteps,headings,batch,frames);
|
auto root=run_motion_transformer(weights,"root_model.",x,root_input_dim,embedding,timesteps,headings,batch,frames);
|
||||||
if(!root)return std::unexpected(root.error());
|
if(!root)return std::unexpected(root.error());
|
||||||
auto gm=weights.f32_values("stats.global_root.mean"), gs=weights.f32_values("stats.global_root.std"), lm=weights.f32_values("stats.local_root.mean"), ls=weights.f32_values("stats.local_root.std");
|
auto gm=weights.f32_values("stats.global_root.mean"), gs=weights.f32_values("stats.global_root.std"), lm=weights.f32_values("stats.local_root.mean"), ls=weights.f32_values("stats.local_root.std");
|
||||||
if(!gm)return std::unexpected(gm.error());
|
if(!gm)return std::unexpected(gm.error());
|
||||||
@ -101,16 +102,16 @@ std::expected<std::vector<float>, std::string> run_two_stage_denoiser(
|
|||||||
if(!ls)return std::unexpected(ls.error());
|
if(!ls)return std::unexpected(ls.error());
|
||||||
auto local=global_root_to_local_root(*root,mask,batch,frames,*gm,*gs,*lm,*ls);
|
auto local=global_root_to_local_root(*root,mask,batch,frames,*gm,*gs,*lm,*ls);
|
||||||
if(!local)return std::unexpected(local.error());
|
if(!local)return std::unexpected(local.error());
|
||||||
std::vector<float> body_input(batch*frames*545);
|
std::vector<float> body_input(batch*frames*body_input_dim);
|
||||||
for(std::size_t b=0;b<batch;++b) for(std::size_t t=0;t<frames;++t) {
|
for(std::size_t b=0;b<batch;++b) for(std::size_t t=0;t<frames;++t) {
|
||||||
const auto src=(b*frames+t)*546, dst=(b*frames+t)*545;
|
const auto src=(b*frames+t)*root_input_dim, dst=(b*frames+t)*body_input_dim;
|
||||||
std::memcpy(body_input.data()+dst,local->data()+(b*frames+t)*4,4*sizeof(float));
|
std::memcpy(body_input.data()+dst,local->data()+(b*frames+t)*4,4*sizeof(float));
|
||||||
std::memcpy(body_input.data()+dst+4,x.data()+src+5,541*sizeof(float));
|
std::memcpy(body_input.data()+dst+4,x.data()+src+5,(root_input_dim-5)*sizeof(float));
|
||||||
}
|
}
|
||||||
auto body=run_motion_transformer(weights,"body_model.",body_input,545,embedding,timesteps,headings,batch,frames);
|
auto body=run_motion_transformer(weights,"body_model.",body_input,body_input_dim,embedding,timesteps,headings,batch,frames);
|
||||||
if(!body)return std::unexpected(body.error());
|
if(!body)return std::unexpected(body.error());
|
||||||
std::vector<float> output(batch*frames*273);
|
std::vector<float> output(batch*frames*dim);
|
||||||
for(std::size_t b=0;b<batch;++b)for(std::size_t t=0;t<frames;++t){const auto r=(b*frames+t)*5, q=(b*frames+t)*268, o=(b*frames+t)*273;std::memcpy(output.data()+o,root->data()+r,5*sizeof(float));std::memcpy(output.data()+o+5,body->data()+q,268*sizeof(float));}
|
for(std::size_t b=0;b<batch;++b)for(std::size_t t=0;t<frames;++t){const auto r=(b*frames+t)*5, q=(b*frames+t)*(dim-5), o=(b*frames+t)*dim;std::memcpy(output.data()+o,root->data()+r,5*sizeof(float));std::memcpy(output.data()+o+5,body->data()+q,(dim-5)*sizeof(float));}
|
||||||
return output;
|
return output;
|
||||||
}
|
}
|
||||||
|
|
||||||
@ -118,7 +119,7 @@ std::expected<std::vector<float>, std::string> run_separated_cfg_denoiser(
|
|||||||
const ggml_motion_weights &weights, std::span<const float> motion,
|
const ggml_motion_weights &weights, std::span<const float> motion,
|
||||||
std::span<const float> embedding, float timestep, float text_weight,
|
std::span<const float> embedding, float timestep, float text_weight,
|
||||||
float constraint_weight, std::size_t frames) {
|
float constraint_weight, std::size_t frames) {
|
||||||
const std::vector<float> empty(frames*273, 0.f);
|
const std::vector<float> empty(frames*weights.motion_dim(), 0.f);
|
||||||
return run_separated_cfg_denoiser_conditioned(weights, motion, embedding, empty, empty,
|
return run_separated_cfg_denoiser_conditioned(weights, motion, embedding, empty, empty,
|
||||||
timestep, 0.f, text_weight, constraint_weight, frames);
|
timestep, 0.f, text_weight, constraint_weight, frames);
|
||||||
}
|
}
|
||||||
@ -128,25 +129,26 @@ std::expected<std::vector<float>, std::string> run_separated_cfg_denoiser_condit
|
|||||||
std::span<const float> embedding, std::span<const float> observed,
|
std::span<const float> embedding, std::span<const float> observed,
|
||||||
std::span<const float> observed_mask, float timestep, float heading,
|
std::span<const float> observed_mask, float timestep, float heading,
|
||||||
float text_weight, float constraint_weight, std::size_t frames) {
|
float text_weight, float constraint_weight, std::size_t frames) {
|
||||||
if (motion.size()!=frames*273 || embedding.size()!=4096 || !std::isfinite(timestep) || !std::isfinite(text_weight) || !std::isfinite(constraint_weight))
|
const size_t dim=weights.motion_dim();
|
||||||
|
if (!dim || motion.size()!=frames*dim || embedding.size()!=4096 || !std::isfinite(timestep) || !std::isfinite(text_weight) || !std::isfinite(constraint_weight))
|
||||||
return std::unexpected("invalid separated CFG denoiser input");
|
return std::unexpected("invalid separated CFG denoiser input");
|
||||||
if (observed.size()!=frames*273 || observed_mask.size()!=frames*273 || !std::isfinite(heading))
|
if (observed.size()!=frames*dim || observed_mask.size()!=frames*dim || !std::isfinite(heading))
|
||||||
return std::unexpected("invalid separated CFG condition dimensions");
|
return std::unexpected("invalid separated CFG condition dimensions");
|
||||||
constexpr size_t cfg_batch=3; std::vector<float> extended(cfg_batch*frames*546), text(cfg_batch*4096), times(cfg_batch,timestep), headings(cfg_batch,heading), mask(cfg_batch*frames,1.f);
|
constexpr size_t cfg_batch=3; std::vector<float> extended(cfg_batch*frames*2*dim), text(cfg_batch*4096), times(cfg_batch,timestep), headings(cfg_batch,heading), mask(cfg_batch*frames,1.f);
|
||||||
for(size_t b=0;b<cfg_batch;++b) for(size_t t=0;t<frames;++t) {
|
for(size_t b=0;b<cfg_batch;++b) for(size_t t=0;t<frames;++t) {
|
||||||
auto *dst=extended.data()+(b*frames+t)*546;
|
auto *dst=extended.data()+(b*frames+t)*2*dim;
|
||||||
std::memcpy(dst,motion.data()+t*273,273*sizeof(float));
|
std::memcpy(dst,motion.data()+t*dim,dim*sizeof(float));
|
||||||
// Upstream separated CFG is [text, constraint, unconditional]. Only
|
// Upstream separated CFG is [text, constraint, unconditional]. Only
|
||||||
// the constraint branch receives observed motion and its feature mask.
|
// the constraint branch receives observed motion and its feature mask.
|
||||||
if (b==1) for (size_t d=0;d<273;++d) dst[d]=motion[t*273+d]*(1.f-observed_mask[t*273+d])+observed[t*273+d]*observed_mask[t*273+d];
|
if (b==1) for (size_t d=0;d<dim;++d) dst[d]=motion[t*dim+d]*(1.f-observed_mask[t*dim+d])+observed[t*dim+d]*observed_mask[t*dim+d];
|
||||||
if (b==1) std::memcpy(dst+273,observed_mask.data()+t*273,273*sizeof(float));
|
if (b==1) std::memcpy(dst+dim,observed_mask.data()+t*dim,dim*sizeof(float));
|
||||||
}
|
}
|
||||||
// Only branch zero has text. Branch one is constraint-only; branch two is
|
// Only branch zero has text. Branch one is constraint-only; branch two is
|
||||||
// unconditional. This is the upstream separated-CFG batch order.
|
// unconditional. This is the upstream separated-CFG batch order.
|
||||||
std::memcpy(text.data(),embedding.data(),4096*sizeof(float));
|
std::memcpy(text.data(),embedding.data(),4096*sizeof(float));
|
||||||
auto all=run_two_stage_denoiser(weights,extended,text,times,headings,mask,cfg_batch,frames);
|
auto all=run_two_stage_denoiser(weights,extended,text,times,headings,mask,cfg_batch,frames);
|
||||||
if(!all)return std::unexpected(all.error());
|
if(!all)return std::unexpected(all.error());
|
||||||
std::vector<float> result(frames*273);
|
std::vector<float> result(frames*dim);
|
||||||
for(size_t i=0;i<result.size();++i) result[i]=(*all)[2*result.size()+i]+text_weight*((*all)[i]-(*all)[2*result.size()+i])+constraint_weight*((*all)[result.size()+i]-(*all)[2*result.size()+i]);
|
for(size_t i=0;i<result.size();++i) result[i]=(*all)[2*result.size()+i]+text_weight*((*all)[i]-(*all)[2*result.size()+i])+constraint_weight*((*all)[result.size()+i]-(*all)[2*result.size()+i]);
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
@ -155,7 +157,7 @@ std::expected<std::vector<float>, std::string> sample_motion_from_noise(
|
|||||||
const ggml_motion_weights &weights, std::span<const float> initial,
|
const ggml_motion_weights &weights, std::span<const float> initial,
|
||||||
std::span<const float> embedding, std::size_t frames, unsigned steps,
|
std::span<const float> embedding, std::size_t frames, unsigned steps,
|
||||||
float text_weight, float constraint_weight) {
|
float text_weight, float constraint_weight) {
|
||||||
if(initial.size()!=frames*273) return std::unexpected("invalid initial motion noise dimensions");
|
if(initial.size()!=frames*weights.motion_dim()) return std::unexpected("invalid initial motion noise dimensions");
|
||||||
auto schedule=make_cosine_schedule(1000,steps); if(!schedule)return std::unexpected(schedule.error());
|
auto schedule=make_cosine_schedule(1000,steps); if(!schedule)return std::unexpected(schedule.error());
|
||||||
std::vector<float> state(initial.begin(),initial.end()), next(state.size());
|
std::vector<float> state(initial.begin(),initial.end()), next(state.size());
|
||||||
for(unsigned i=steps;i-->0;) {
|
for(unsigned i=steps;i-->0;) {
|
||||||
@ -173,7 +175,7 @@ std::expected<std::vector<float>, std::string> sample_motion_from_noise_conditio
|
|||||||
std::span<const float> embedding, std::span<const float> observed,
|
std::span<const float> embedding, std::span<const float> observed,
|
||||||
std::span<const float> observed_mask, float heading, std::size_t frames,
|
std::span<const float> observed_mask, float heading, std::size_t frames,
|
||||||
unsigned steps, float text_weight, float constraint_weight) {
|
unsigned steps, float text_weight, float constraint_weight) {
|
||||||
if(initial.size()!=frames*273 || observed.size()!=initial.size() || observed_mask.size()!=initial.size())
|
if(initial.size()!=frames*weights.motion_dim() || observed.size()!=initial.size() || observed_mask.size()!=initial.size())
|
||||||
return std::unexpected("invalid conditioned motion noise dimensions");
|
return std::unexpected("invalid conditioned motion noise dimensions");
|
||||||
auto schedule=make_cosine_schedule(1000,steps); if(!schedule)return std::unexpected(schedule.error());
|
auto schedule=make_cosine_schedule(1000,steps); if(!schedule)return std::unexpected(schedule.error());
|
||||||
std::vector<float> state(initial.begin(),initial.end()), next(state.size());
|
std::vector<float> state(initial.begin(),initial.end()), next(state.size());
|
||||||
|
|||||||
@ -34,15 +34,15 @@ std::expected<std::vector<float>, std::string> run_motion_transformer(
|
|||||||
std::span<const float> headings, std::size_t batch, std::size_t frames);
|
std::span<const float> headings, std::size_t batch, std::size_t frames);
|
||||||
|
|
||||||
// Exact two-stage Kimodo denoiser for concatenated motion/mask inputs
|
// Exact two-stage Kimodo denoiser for concatenated motion/mask inputs
|
||||||
// [B,T,546]. Returned clean prediction is [B,T,273].
|
// [B,T,2*motion_dim]. Returned clean prediction is [B,T,motion_dim].
|
||||||
std::expected<std::vector<float>, std::string> run_two_stage_denoiser(
|
std::expected<std::vector<float>, std::string> run_two_stage_denoiser(
|
||||||
const ggml_motion_weights &weights, std::span<const float> motion_and_mask,
|
const ggml_motion_weights &weights, std::span<const float> motion_and_mask,
|
||||||
std::span<const float> text_embedding, std::span<const float> timesteps,
|
std::span<const float> text_embedding, std::span<const float> timesteps,
|
||||||
std::span<const float> headings, std::span<const float> motion_mask,
|
std::span<const float> headings, std::span<const float> motion_mask,
|
||||||
std::size_t batch, std::size_t frames);
|
std::size_t batch, std::size_t frames);
|
||||||
|
|
||||||
// Unconstrained separated CFG wrapper. `motion` is [T,273], embedding is
|
// Unconstrained separated CFG wrapper. `motion` is [T,motion_dim], embedding
|
||||||
// [4096], and the result is one clean [T,273] prediction.
|
// is [4096], and the result is one clean prediction.
|
||||||
std::expected<std::vector<float>, std::string> run_separated_cfg_denoiser(
|
std::expected<std::vector<float>, std::string> run_separated_cfg_denoiser(
|
||||||
const ggml_motion_weights &weights, std::span<const float> motion,
|
const ggml_motion_weights &weights, std::span<const float> motion,
|
||||||
std::span<const float> embedding, float timestep, float text_weight,
|
std::span<const float> embedding, float timestep, float text_weight,
|
||||||
@ -54,7 +54,7 @@ std::expected<std::vector<float>, std::string> sample_motion_from_noise(
|
|||||||
std::span<const float> embedding, std::size_t frames, unsigned steps,
|
std::span<const float> embedding, std::size_t frames, unsigned steps,
|
||||||
float text_weight, float constraint_weight);
|
float text_weight, float constraint_weight);
|
||||||
|
|
||||||
// Multi-prompt transition sampler. `observed` and `observed_mask` are [T,273]
|
// Multi-prompt transition sampler. `observed` and `observed_mask` are [T,motion_dim]
|
||||||
// normalized motion-representation values/masks. This mirrors the upstream
|
// normalized motion-representation values/masks. This mirrors the upstream
|
||||||
// concat-mask denoiser: text, constraint, and unconditional CFG branches.
|
// concat-mask denoiser: text, constraint, and unconditional CFG branches.
|
||||||
std::expected<std::vector<float>, std::string> sample_motion_from_noise_conditioned(
|
std::expected<std::vector<float>, std::string> sample_motion_from_noise_conditioned(
|
||||||
|
|||||||
@ -41,7 +41,7 @@ int main(int argc, char **argv) try {
|
|||||||
const std::filesystem::path output(argv[7]); std::filesystem::create_directories(output);
|
const std::filesystem::path output(argv[7]); std::filesystem::create_directories(output);
|
||||||
write_f32(output / "root_positions.f32", motion->root_positions);
|
write_f32(output / "root_positions.f32", motion->root_positions);
|
||||||
write_f32(output / "local_rotations_xyzw.f32", motion->local_rotations_xyzw);
|
write_f32(output / "local_rotations_xyzw.f32", motion->local_rotations_xyzw);
|
||||||
std::cout << "generated " << motion->frames << " SMPL-X22 sequence frames\n";
|
std::cout << "generated " << motion->frames << " frames with " << motion->joints << " joints\n";
|
||||||
return 0;
|
return 0;
|
||||||
}
|
}
|
||||||
if (argc != 8) {
|
if (argc != 8) {
|
||||||
@ -63,7 +63,7 @@ int main(int argc, char **argv) try {
|
|||||||
std::filesystem::create_directories(output);
|
std::filesystem::create_directories(output);
|
||||||
write_f32(output / "root_positions.f32", motion->root_positions);
|
write_f32(output / "root_positions.f32", motion->root_positions);
|
||||||
write_f32(output / "local_rotations_xyzw.f32", motion->local_rotations_xyzw);
|
write_f32(output / "local_rotations_xyzw.f32", motion->local_rotations_xyzw);
|
||||||
std::cout << "generated " << motion->frames << " SMPL-X22 frames\n";
|
std::cout << "generated " << motion->frames << " frames with " << motion->joints << " joints\n";
|
||||||
return 0;
|
return 0;
|
||||||
} catch (const std::exception &error) {
|
} catch (const std::exception &error) {
|
||||||
std::cerr << error.what() << '\n';
|
std::cerr << error.what() << '\n';
|
||||||
|
|||||||
@ -61,6 +61,9 @@ std::expected<std::unique_ptr<ggml_motion_weights>, std::string> ggml_motion_wei
|
|||||||
if (!checked) return std::unexpected(checked.error());
|
if (!checked) return std::unexpected(checked.error());
|
||||||
if (auto valid = validate_motion_gguf(*checked); !valid) return std::unexpected(valid.error());
|
if (auto valid = validate_motion_gguf(*checked); !valid) return std::unexpected(valid.error());
|
||||||
auto result = std::unique_ptr<ggml_motion_weights>(new ggml_motion_weights);
|
auto result = std::unique_ptr<ggml_motion_weights>(new ggml_motion_weights);
|
||||||
|
result->skeleton_ = checked->strings.at("kimodo.skeleton");
|
||||||
|
result->motion_dim_ = static_cast<size_t>(checked->uints.at("kimodo.motion_dim"));
|
||||||
|
result->body_dim_ = static_cast<size_t>(checked->uints.at("kimodo.body_dim"));
|
||||||
gguf_init_params params{true, &result->context_};
|
gguf_init_params params{true, &result->context_};
|
||||||
result->gguf_ = gguf_init_from_file(std::string(path).c_str(), params);
|
result->gguf_ = gguf_init_from_file(std::string(path).c_str(), params);
|
||||||
if (!result->gguf_ || !result->context_) return std::unexpected("GGML could not load checked motion GGUF");
|
if (!result->gguf_ || !result->context_) return std::unexpected("GGML could not load checked motion GGUF");
|
||||||
|
|||||||
@ -1,5 +1,6 @@
|
|||||||
#pragma once
|
#pragma once
|
||||||
|
|
||||||
|
#include <cstddef>
|
||||||
#include <expected>
|
#include <expected>
|
||||||
#include <memory>
|
#include <memory>
|
||||||
#include <string>
|
#include <string>
|
||||||
@ -27,6 +28,9 @@ public:
|
|||||||
ggml_tensor *tensor(std::string_view name) const;
|
ggml_tensor *tensor(std::string_view name) const;
|
||||||
std::expected<std::vector<float>, std::string> f32_values(std::string_view name) const;
|
std::expected<std::vector<float>, std::string> f32_values(std::string_view name) const;
|
||||||
ggml_backend *backend() const noexcept { return backend_; }
|
ggml_backend *backend() const noexcept { return backend_; }
|
||||||
|
std::string_view skeleton_key() const noexcept { return skeleton_; }
|
||||||
|
std::size_t motion_dim() const noexcept { return motion_dim_; }
|
||||||
|
std::size_t body_dim() const noexcept { return body_dim_; }
|
||||||
|
|
||||||
private:
|
private:
|
||||||
ggml_motion_weights() = default;
|
ggml_motion_weights() = default;
|
||||||
@ -34,6 +38,9 @@ private:
|
|||||||
gguf_context *gguf_ = nullptr;
|
gguf_context *gguf_ = nullptr;
|
||||||
ggml_backend *backend_ = nullptr;
|
ggml_backend *backend_ = nullptr;
|
||||||
ggml_backend_buffer *buffer_ = nullptr;
|
ggml_backend_buffer *buffer_ = nullptr;
|
||||||
|
std::string skeleton_;
|
||||||
|
std::size_t motion_dim_ = 0;
|
||||||
|
std::size_t body_dim_ = 0;
|
||||||
};
|
};
|
||||||
|
|
||||||
} // namespace kimodo::detail
|
} // namespace kimodo::detail
|
||||||
|
|||||||
11
src/gguf.cpp
11
src/gguf.cpp
@ -1,4 +1,5 @@
|
|||||||
#include "gguf.hpp"
|
#include "gguf.hpp"
|
||||||
|
#include "skeleton.hpp"
|
||||||
|
|
||||||
#include <algorithm>
|
#include <algorithm>
|
||||||
#include <array>
|
#include <array>
|
||||||
@ -106,8 +107,14 @@ std::expected<void, std::string> validate_motion_gguf(const gguf_file &file) {
|
|||||||
if (format == file.uints.end() || format->second != 1)
|
if (format == file.uints.end() || format->second != 1)
|
||||||
return std::unexpected("unsupported Kimodo motion GGUF format");
|
return std::unexpected("unsupported Kimodo motion GGUF format");
|
||||||
const auto skeleton = file.strings.find("kimodo.skeleton");
|
const auto skeleton = file.strings.find("kimodo.skeleton");
|
||||||
if (skeleton == file.strings.end() || skeleton->second != "smplx22")
|
if (skeleton == file.strings.end() || !find_skeleton(skeleton->second))
|
||||||
return std::unexpected("first runtime supports only smplx22 skeletons");
|
return std::unexpected("motion GGUF has an unsupported skeleton");
|
||||||
|
const auto &spec = *find_skeleton(skeleton->second);
|
||||||
|
const auto motion_dim = file.uints.find("kimodo.motion_dim");
|
||||||
|
const auto body_dim = file.uints.find("kimodo.body_dim");
|
||||||
|
if (motion_dim == file.uints.end() || motion_dim->second != spec.motion_dim() ||
|
||||||
|
body_dim == file.uints.end() || body_dim->second != spec.body_dim())
|
||||||
|
return std::unexpected("motion GGUF dimensions do not match its skeleton");
|
||||||
const auto width = file.uints.find("kimodo.text_embedding_width");
|
const auto width = file.uints.find("kimodo.text_embedding_width");
|
||||||
if (width == file.uints.end() || width->second != 4096)
|
if (width == file.uints.end() || width->second != 4096)
|
||||||
return std::unexpected("motion GGUF has incompatible text embedding width");
|
return std::unexpected("motion GGUF has incompatible text embedding width");
|
||||||
|
|||||||
@ -22,5 +22,5 @@ int main(int argc, char **argv) {
|
|||||||
}
|
}
|
||||||
gguf_free(file); ggml_free(tensor_context);
|
gguf_free(file); ggml_free(tensor_context);
|
||||||
#endif
|
#endif
|
||||||
std::puts("Kimodo SMPL-X motion GGUF: valid (414 F32 tensors)");
|
std::puts("Kimodo motion GGUF: valid (414 F32 tensors)");
|
||||||
}
|
}
|
||||||
|
|||||||
@ -1,5 +1,6 @@
|
|||||||
#include <kimodo/kimodo.hpp>
|
#include <kimodo/kimodo.hpp>
|
||||||
#include "gguf.hpp"
|
#include "gguf.hpp"
|
||||||
|
#include "skeleton.hpp"
|
||||||
#ifdef KIMODO_HAVE_GGML
|
#ifdef KIMODO_HAVE_GGML
|
||||||
#include "ggml_weights.hpp"
|
#include "ggml_weights.hpp"
|
||||||
#include "denoiser.hpp"
|
#include "denoiser.hpp"
|
||||||
@ -15,6 +16,7 @@ namespace kimodo {
|
|||||||
struct model::impl {
|
struct model::impl {
|
||||||
detail::gguf_file motion;
|
detail::gguf_file motion;
|
||||||
std::string motion_path;
|
std::string motion_path;
|
||||||
|
const detail::skeleton_spec *skeleton = nullptr;
|
||||||
#ifdef KIMODO_HAVE_GGML
|
#ifdef KIMODO_HAVE_GGML
|
||||||
mutable std::unique_ptr<detail::ggml_motion_weights> weights;
|
mutable std::unique_ptr<detail::ggml_motion_weights> weights;
|
||||||
std::unique_ptr<detail::llm_text_encoder> text;
|
std::unique_ptr<detail::llm_text_encoder> text;
|
||||||
@ -30,6 +32,7 @@ std::expected<std::unique_ptr<model>, std::string> model::load(std::string_view
|
|||||||
auto state = std::make_unique<impl>();
|
auto state = std::make_unique<impl>();
|
||||||
state->motion = std::move(*file);
|
state->motion = std::move(*file);
|
||||||
state->motion_path = std::string(motion_path);
|
state->motion_path = std::string(motion_path);
|
||||||
|
state->skeleton = detail::find_skeleton(state->motion.strings.at("kimodo.skeleton"));
|
||||||
#ifdef KIMODO_HAVE_GGML
|
#ifdef KIMODO_HAVE_GGML
|
||||||
if (!text_path.empty()) {
|
if (!text_path.empty()) {
|
||||||
auto text = detail::llm_text_encoder::load(text_path);
|
auto text = detail::llm_text_encoder::load(text_path);
|
||||||
@ -74,7 +77,8 @@ std::expected<motion_data, std::string> model::generate_embedding(
|
|||||||
}
|
}
|
||||||
std::mt19937_64 rng(seed);
|
std::mt19937_64 rng(seed);
|
||||||
std::normal_distribution<float> normal(0.f, 1.f);
|
std::normal_distribution<float> normal(0.f, 1.f);
|
||||||
std::vector<float> noise(static_cast<size_t>(frames)*273);
|
const size_t motion_dim=impl_->skeleton->motion_dim();
|
||||||
|
std::vector<float> noise(static_cast<size_t>(frames)*motion_dim);
|
||||||
for (float &value : noise) value = normal(rng);
|
for (float &value : noise) value = normal(rng);
|
||||||
auto sampled = detail::sample_motion_from_noise(*impl_->weights, noise, embedding, frames, steps, text_cfg, constraint_cfg);
|
auto sampled = detail::sample_motion_from_noise(*impl_->weights, noise, embedding, frames, steps, text_cfg, constraint_cfg);
|
||||||
if (!sampled) return std::unexpected(sampled.error());
|
if (!sampled) return std::unexpected(sampled.error());
|
||||||
@ -84,10 +88,10 @@ std::expected<motion_data, std::string> model::generate_embedding(
|
|||||||
if (!global_std) return std::unexpected(global_std.error());
|
if (!global_std) return std::unexpected(global_std.error());
|
||||||
if (!body_mean) return std::unexpected(body_mean.error());
|
if (!body_mean) return std::unexpected(body_mean.error());
|
||||||
if (!body_std) return std::unexpected(body_std.error());
|
if (!body_std) return std::unexpected(body_std.error());
|
||||||
auto decoded=detail::decode_smplx22(*sampled,frames,*global_mean,*global_std,*body_mean,*body_std);
|
auto decoded=detail::decode_motion(*sampled,frames,*impl_->skeleton,*global_mean,*global_std,*body_mean,*body_std);
|
||||||
if (!decoded) return std::unexpected(decoded.error());
|
if (!decoded) return std::unexpected(decoded.error());
|
||||||
motion_data result;
|
motion_data result;
|
||||||
result.frames=frames; result.joints=22;
|
result.frames=frames; result.joints=static_cast<unsigned>(impl_->skeleton->joints());
|
||||||
result.local_rotations_xyzw=std::move(decoded->local_xyzw);
|
result.local_rotations_xyzw=std::move(decoded->local_xyzw);
|
||||||
result.root_positions=std::move(decoded->root_positions);
|
result.root_positions=std::move(decoded->root_positions);
|
||||||
return result;
|
return result;
|
||||||
@ -127,22 +131,23 @@ std::expected<motion_data, std::string> model::generate_text_sequence(
|
|||||||
const auto sampled_frames = static_cast<size_t>(segment.frames) +
|
const auto sampled_frames = static_cast<size_t>(segment.frames) +
|
||||||
(index == 0 ? 0 : transition_frames);
|
(index == 0 ? 0 : transition_frames);
|
||||||
embeddings.push_back(*embedding);
|
embeddings.push_back(*embedding);
|
||||||
noise.emplace_back(sampled_frames*273);
|
noise.emplace_back(sampled_frames*impl_->skeleton->motion_dim());
|
||||||
for (float &value : noise.back()) value=normal(rng);
|
for (float &value : noise.back()) value=normal(rng);
|
||||||
sampled.push_back({embeddings.back(), noise.back(), segment.frames});
|
sampled.push_back({embeddings.back(), noise.back(), segment.frames});
|
||||||
}
|
}
|
||||||
auto joined=detail::sample_motion_sequence_from_noise(*impl_->weights,sampled,transition_frames,steps,text_cfg,constraint_cfg);
|
auto joined=detail::sample_motion_sequence_from_noise(*impl_->weights,sampled,transition_frames,steps,text_cfg,constraint_cfg);
|
||||||
if (!joined) return std::unexpected(joined.error());
|
if (!joined) return std::unexpected(joined.error());
|
||||||
const auto frames=static_cast<unsigned>(joined->size()/273);
|
const size_t motion_dim=impl_->skeleton->motion_dim(), body_dim=impl_->skeleton->body_dim();
|
||||||
|
const auto frames=static_cast<unsigned>(joined->size()/motion_dim);
|
||||||
auto normalized=*joined;
|
auto normalized=*joined;
|
||||||
for (size_t row=0; row<frames; ++row) {
|
for (size_t row=0; row<frames; ++row) {
|
||||||
auto *value=normalized.data()+row*273;
|
auto *value=normalized.data()+row*motion_dim;
|
||||||
for (size_t d=0; d<5; ++d) value[d]=(value[d]-(*gm)[d])/std::sqrt((*gs)[d]*(*gs)[d]+1.e-5F);
|
for (size_t d=0; d<5; ++d) value[d]=(value[d]-(*gm)[d])/std::sqrt((*gs)[d]*(*gs)[d]+1.e-5F);
|
||||||
for (size_t d=0; d<268; ++d) value[5+d]=(value[5+d]-(*bm)[d])/std::sqrt((*bs)[d]*(*bs)[d]+1.e-5F);
|
for (size_t d=0; d<body_dim; ++d) value[5+d]=(value[5+d]-(*bm)[d])/std::sqrt((*bs)[d]*(*bs)[d]+1.e-5F);
|
||||||
}
|
}
|
||||||
auto decoded=detail::decode_smplx22(normalized,frames,*gm,*gs,*bm,*bs);
|
auto decoded=detail::decode_motion(normalized,frames,*impl_->skeleton,*gm,*gs,*bm,*bs);
|
||||||
if (!decoded) return std::unexpected(decoded.error());
|
if (!decoded) return std::unexpected(decoded.error());
|
||||||
motion_data result; result.frames=frames; result.joints=22;
|
motion_data result; result.frames=frames; result.joints=static_cast<unsigned>(impl_->skeleton->joints());
|
||||||
result.local_rotations_xyzw=std::move(decoded->local_xyzw); result.root_positions=std::move(decoded->root_positions);
|
result.local_rotations_xyzw=std::move(decoded->local_xyzw); result.root_positions=std::move(decoded->root_positions);
|
||||||
return result;
|
return result;
|
||||||
#else
|
#else
|
||||||
|
|||||||
@ -1,13 +1,14 @@
|
|||||||
#include "motion_decode.hpp"
|
#include "motion_decode.hpp"
|
||||||
#include <array>
|
#include "skeleton.hpp"
|
||||||
#include <cmath>
|
#include <cmath>
|
||||||
|
#include <vector>
|
||||||
namespace kimodo::detail { namespace {
|
namespace kimodo::detail { namespace {
|
||||||
constexpr int parent[22]={-1,0,0,0,1,2,3,4,5,6,7,8,9,9,9,12,13,14,16,17,18,19};
|
|
||||||
struct M{float v[9];};
|
struct M{float v[9];};
|
||||||
M mul(const M&a,const M&b){M r{};for(int i=0;i<3;++i)for(int j=0;j<3;++j)for(int k=0;k<3;++k)r.v[i*3+j]+=a.v[i*3+k]*b.v[k*3+j];return r;}
|
M mul(const M&a,const M&b){M r{};for(int i=0;i<3;++i)for(int j=0;j<3;++j)for(int k=0;k<3;++k)r.v[i*3+j]+=a.v[i*3+k]*b.v[k*3+j];return r;}
|
||||||
M tr(const M&a){M r{};for(int i=0;i<3;++i)for(int j=0;j<3;++j)r.v[i*3+j]=a.v[j*3+i];return r;}
|
M tr(const M&a){M r{};for(int i=0;i<3;++i)for(int j=0;j<3;++j)r.v[i*3+j]=a.v[j*3+i];return r;}
|
||||||
M six(const float*x){float n=std::sqrt(x[0]*x[0]+x[1]*x[1]+x[2]*x[2]);float a[3]={x[0]/n,x[1]/n,x[2]/n};float z[3]={a[1]*x[5]-a[2]*x[4],a[2]*x[3]-a[0]*x[5],a[0]*x[4]-a[1]*x[3]};n=std::sqrt(z[0]*z[0]+z[1]*z[1]+z[2]*z[2]);for(float&v:z)v/=n;float b[3]={z[1]*a[2]-z[2]*a[1],z[2]*a[0]-z[0]*a[2],z[0]*a[1]-z[1]*a[0]};return M{{a[0],b[0],z[0],a[1],b[1],z[1],a[2],b[2],z[2]}};}
|
M six(const float*x){float n=std::sqrt(x[0]*x[0]+x[1]*x[1]+x[2]*x[2]);float a[3]={x[0]/n,x[1]/n,x[2]/n};float z[3]={a[1]*x[5]-a[2]*x[4],a[2]*x[3]-a[0]*x[5],a[0]*x[4]-a[1]*x[3]};n=std::sqrt(z[0]*z[0]+z[1]*z[1]+z[2]*z[2]);for(float&v:z)v/=n;float b[3]={z[1]*a[2]-z[2]*a[1],z[2]*a[0]-z[0]*a[2],z[0]*a[1]-z[1]*a[0]};return M{{a[0],b[0],z[0],a[1],b[1],z[1],a[2],b[2],z[2]}};}
|
||||||
void quat(const M&m,float*q){float w,x,y,z,t=m.v[0]+m.v[4]+m.v[8];if(t>0){float s=2*std::sqrt(t+1);w=.25f*s;x=(m.v[7]-m.v[5])/s;y=(m.v[2]-m.v[6])/s;z=(m.v[3]-m.v[1])/s;}else if(m.v[0]>m.v[4]&&m.v[0]>m.v[8]){float s=2*std::sqrt(1+m.v[0]-m.v[4]-m.v[8]);w=(m.v[7]-m.v[5])/s;x=.25f*s;y=(m.v[1]+m.v[3])/s;z=(m.v[2]+m.v[6])/s;}else if(m.v[4]>m.v[8]){float s=2*std::sqrt(1+m.v[4]-m.v[0]-m.v[8]);w=(m.v[2]-m.v[6])/s;x=(m.v[1]+m.v[3])/s;y=.25f*s;z=(m.v[5]+m.v[7])/s;}else{float s=2*std::sqrt(1+m.v[8]-m.v[0]-m.v[4]);w=(m.v[3]-m.v[1])/s;x=(m.v[2]+m.v[6])/s;y=(m.v[5]+m.v[7])/s;z=.25f*s;}q[0]=x;q[1]=y;q[2]=z;q[3]=w;}
|
void quat(const M&m,float*q){float w,x,y,z,t=m.v[0]+m.v[4]+m.v[8];if(t>0){float s=2*std::sqrt(t+1);w=.25f*s;x=(m.v[7]-m.v[5])/s;y=(m.v[2]-m.v[6])/s;z=(m.v[3]-m.v[1])/s;}else if(m.v[0]>m.v[4]&&m.v[0]>m.v[8]){float s=2*std::sqrt(1+m.v[0]-m.v[4]-m.v[8]);w=(m.v[7]-m.v[5])/s;x=.25f*s;y=(m.v[1]+m.v[3])/s;z=(m.v[2]+m.v[6])/s;}else if(m.v[4]>m.v[8]){float s=2*std::sqrt(1+m.v[4]-m.v[0]-m.v[8]);w=(m.v[2]-m.v[6])/s;x=(m.v[1]+m.v[3])/s;y=.25f*s;z=(m.v[5]+m.v[7])/s;}else{float s=2*std::sqrt(1+m.v[8]-m.v[0]-m.v[4]);w=(m.v[3]-m.v[1])/s;x=(m.v[2]+m.v[6])/s;y=(m.v[5]+m.v[7])/s;z=.25f*s;}q[0]=x;q[1]=y;q[2]=z;q[3]=w;}
|
||||||
}
|
}
|
||||||
std::expected<decoded_motion,std::string> decode_smplx22(std::span<const float>x,size_t T,std::span<const float>gm,std::span<const float>gs,std::span<const float>bm,std::span<const float>bs){if(x.size()!=T*273||gm.size()!=5||gs.size()!=5||bm.size()!=268||bs.size()!=268)return std::unexpected("invalid SMPL-X decode inputs");decoded_motion o;o.local_xyzw.resize(T*22*4);o.root_positions.resize(T*3);auto scale=[](float s){return std::sqrt(s*s+1.e-5f);};for(size_t t=0;t<T;++t){const float*in=x.data()+t*273;std::array<float,273> f{};for(int i=0;i<5;++i)f[i]=in[i]*scale(gs[i])+gm[i];for(int i=0;i<268;++i)f[5+i]=in[5+i]*scale(bs[i])+bm[i];o.root_positions[t*3]=f[0]+f[5];o.root_positions[t*3+1]=f[6];o.root_positions[t*3+2]=f[2]+f[7];M g[22],l[22];for(int j=0;j<22;++j)g[j]=six(f.data()+71+j*6);for(int j=0;j<22;++j)l[j]=parent[j]<0?g[j]:mul(tr(g[parent[j]]),g[j]);for(int j=0;j<22;++j)quat(l[j],o.local_xyzw.data()+(t*22+j)*4);}return o;}
|
std::expected<decoded_motion,std::string> decode_motion(std::span<const float>x,size_t T,const skeleton_spec&s,std::span<const float>gm,std::span<const float>gs,std::span<const float>bm,std::span<const float>bs){const size_t D=s.motion_dim(),J=s.joints(),body=D-5,rotation=5+3*J;if(x.size()!=T*D||gm.size()!=5||gs.size()!=5||bm.size()!=body||bs.size()!=body)return std::unexpected("invalid "+std::string(s.key)+" decode inputs");decoded_motion o;o.local_xyzw.resize(T*J*4);o.root_positions.resize(T*3);auto scale=[](float v){return std::sqrt(v*v+1.e-5f);};std::vector<float>f(D);std::vector<M>g(J),l(J);for(size_t t=0;t<T;++t){const float*in=x.data()+t*D;for(size_t i=0;i<5;++i)f[i]=in[i]*scale(gs[i])+gm[i];for(size_t i=0;i<body;++i)f[5+i]=in[5+i]*scale(bs[i])+bm[i];o.root_positions[t*3]=f[0]+f[5];o.root_positions[t*3+1]=f[6];o.root_positions[t*3+2]=f[2]+f[7];for(size_t j=0;j<J;++j)g[j]=six(f.data()+rotation+j*6);for(size_t j=0;j<J;++j)l[j]=s.parents[j]<0?g[j]:mul(tr(g[static_cast<size_t>(s.parents[j])]),g[j]);for(size_t j=0;j<J;++j)quat(l[j],o.local_xyzw.data()+(t*J+j)*4);}return o;}
|
||||||
|
std::expected<decoded_motion,std::string> decode_smplx22(std::span<const float>x,size_t T,std::span<const float>gm,std::span<const float>gs,std::span<const float>bm,std::span<const float>bs){return decode_motion(x,T,smplx22_spec,gm,gs,bm,bs);}
|
||||||
}
|
}
|
||||||
|
|||||||
@ -4,6 +4,8 @@
|
|||||||
#include <string>
|
#include <string>
|
||||||
#include <vector>
|
#include <vector>
|
||||||
namespace kimodo::detail {
|
namespace kimodo::detail {
|
||||||
|
struct skeleton_spec;
|
||||||
struct decoded_motion { std::vector<float> local_xyzw, root_positions; };
|
struct decoded_motion { std::vector<float> local_xyzw, root_positions; };
|
||||||
|
std::expected<decoded_motion,std::string> decode_motion(std::span<const float> normalized, std::size_t frames, const skeleton_spec &skeleton, std::span<const float> global_mean, std::span<const float> global_std, std::span<const float> body_mean, std::span<const float> body_std);
|
||||||
std::expected<decoded_motion,std::string> decode_smplx22(std::span<const float> normalized, std::size_t frames, std::span<const float> global_mean, std::span<const float> global_std, std::span<const float> body_mean, std::span<const float> body_std);
|
std::expected<decoded_motion,std::string> decode_smplx22(std::span<const float> normalized, std::size_t frames, std::span<const float> global_mean, std::span<const float> global_std, std::span<const float> body_mean, std::span<const float> body_std);
|
||||||
}
|
}
|
||||||
|
|||||||
@ -3,6 +3,7 @@
|
|||||||
#include "denoiser.hpp"
|
#include "denoiser.hpp"
|
||||||
#include "ggml_weights.hpp"
|
#include "ggml_weights.hpp"
|
||||||
#include "motion_decode.hpp"
|
#include "motion_decode.hpp"
|
||||||
|
#include "skeleton.hpp"
|
||||||
|
|
||||||
#include <algorithm>
|
#include <algorithm>
|
||||||
#include <cmath>
|
#include <cmath>
|
||||||
@ -54,10 +55,11 @@ int main(int argc, char **argv) try {
|
|||||||
const std::filesystem::path fixture(argv[2]), output(argv[5]);
|
const std::filesystem::path fixture(argv[2]), output(argv[5]);
|
||||||
const auto embedding = read_f32(fixture / "text_features.f32");
|
const auto embedding = read_f32(fixture / "text_features.f32");
|
||||||
const auto noise = read_f32(fixture / "sampling_initial_noise.f32");
|
const auto noise = read_f32(fixture / "sampling_initial_noise.f32");
|
||||||
if (embedding.size() != 4096 || noise.size() != frames * 273)
|
|
||||||
throw std::runtime_error("fixture does not match requested [1,1,4096] embedding and [1,T,273] noise");
|
|
||||||
auto weights = kimodo::detail::ggml_motion_weights::load(argv[1]);
|
auto weights = kimodo::detail::ggml_motion_weights::load(argv[1]);
|
||||||
if (!weights) throw std::runtime_error(weights.error());
|
if (!weights) throw std::runtime_error(weights.error());
|
||||||
|
const auto *skeleton=kimodo::detail::find_skeleton((*weights)->skeleton_key());
|
||||||
|
if (!skeleton || embedding.size() != 4096 || noise.size() != frames * skeleton->motion_dim())
|
||||||
|
throw std::runtime_error("fixture does not match the requested embedding and model motion dimensions");
|
||||||
auto sampled = kimodo::detail::sample_motion_from_noise(**weights, noise, embedding, frames, steps, 2.f, 2.f);
|
auto sampled = kimodo::detail::sample_motion_from_noise(**weights, noise, embedding, frames, steps, 2.f, 2.f);
|
||||||
if (!sampled) throw std::runtime_error(sampled.error());
|
if (!sampled) throw std::runtime_error(sampled.error());
|
||||||
auto gm = (**weights).f32_values("stats.global_root.mean");
|
auto gm = (**weights).f32_values("stats.global_root.mean");
|
||||||
@ -65,7 +67,7 @@ int main(int argc, char **argv) try {
|
|||||||
auto bm = (**weights).f32_values("stats.body.mean");
|
auto bm = (**weights).f32_values("stats.body.mean");
|
||||||
auto bs = (**weights).f32_values("stats.body.std");
|
auto bs = (**weights).f32_values("stats.body.std");
|
||||||
if (!gm || !gs || !bm || !bs) throw std::runtime_error("missing motion normalisation tensors");
|
if (!gm || !gs || !bm || !bs) throw std::runtime_error("missing motion normalisation tensors");
|
||||||
auto decoded = kimodo::detail::decode_smplx22(*sampled, frames, *gm, *gs, *bm, *bs);
|
auto decoded = kimodo::detail::decode_motion(*sampled, frames, *skeleton, *gm, *gs, *bm, *bs);
|
||||||
if (!decoded) throw std::runtime_error(decoded.error());
|
if (!decoded) throw std::runtime_error(decoded.error());
|
||||||
std::filesystem::create_directories(output);
|
std::filesystem::create_directories(output);
|
||||||
write_f32(output / "sampling_final_state.f32", *sampled);
|
write_f32(output / "sampling_final_state.f32", *sampled);
|
||||||
|
|||||||
142
src/sequence.cpp
142
src/sequence.cpp
@ -1,132 +1,72 @@
|
|||||||
#include "denoiser.hpp"
|
#include "denoiser.hpp"
|
||||||
#include "ggml_weights.hpp"
|
#include "ggml_weights.hpp"
|
||||||
|
#include "skeleton.hpp"
|
||||||
|
|
||||||
#include <algorithm>
|
#include <algorithm>
|
||||||
#include <array>
|
|
||||||
#include <cmath>
|
#include <cmath>
|
||||||
|
#include <vector>
|
||||||
|
|
||||||
namespace kimodo::detail {
|
namespace kimodo::detail {
|
||||||
namespace {
|
namespace {
|
||||||
constexpr int parent[22]={-1,0,0,0,1,2,3,4,5,6,7,8,9,9,9,12,13,14,16,17,18,19};
|
|
||||||
constexpr float offset[22][3]={{0,0,0},{.052299179F,-.093935639F,-.027606763F},{-.057192899F,-.106548190F,-.022217851F},{-.001495834F,.112929940F,-.024981268F},{.058866613F,-.416441321F,-.006556974F},{-.048074268F,-.397559673F,-.014061437F},{.006900469F,.145636231F,-.006858510F},{-.041737989F,-.437583506F,-.029511765F},{.014489345F,-.446852267F,-.018029511F},{-.010334037F,.056081813F,.021115851F},{.049293540F,-.065279245F,.126259089F},{-.040575184F,-.065286517F,.127075911F},{-.011025756F,.171365142F,-.028827066F},{.047724526F,.087643057F,-.008375450F},{-.046636276F,.086612143F,-.014864366F},{.024654359F,.175390735F,.024463326F},{.126284808F,.057680372F,-.013885141F},{-.109341696F,.053674292F,-.009117880F},{.272907287F,-.069853373F,-.039094493F},{-.292028785F,-.035440356F,-.024564851F},{.276173830F,.021254137F,-.002478220F},{-.271878421F,-.004834589F,-.016445294F}};
|
|
||||||
struct mat { double v[9]; };
|
struct mat { double v[9]; };
|
||||||
mat mul(const mat&a,const mat&b){mat r{};for(int i=0;i<3;++i)for(int j=0;j<3;++j)for(int k=0;k<3;++k)r.v[i*3+j]+=a.v[i*3+k]*b.v[k*3+j];return r;}
|
mat mul(const mat&a,const mat&b){mat r{};for(int i=0;i<3;++i)for(int j=0;j<3;++j)for(int k=0;k<3;++k)r.v[i*3+j]+=a.v[i*3+k]*b.v[k*3+j];return r;}
|
||||||
mat trans(const mat&a){mat r{};for(int i=0;i<3;++i)for(int j=0;j<3;++j)r.v[i*3+j]=a.v[j*3+i];return r;}
|
mat trans(const mat&a){mat r{};for(int i=0;i<3;++i)for(int j=0;j<3;++j)r.v[i*3+j]=a.v[j*3+i];return r;}
|
||||||
mat cont6(const float*x){double a[3]={x[0],x[1],x[2]},n=std::sqrt(a[0]*a[0]+a[1]*a[1]+a[2]*a[2]);for(double&q:a)q/=n;double z[3]={a[1]*x[5]-a[2]*x[4],a[2]*x[3]-a[0]*x[5],a[0]*x[4]-a[1]*x[3]};n=std::sqrt(z[0]*z[0]+z[1]*z[1]+z[2]*z[2]);for(double&q:z)q/=n;double b[3]={z[1]*a[2]-z[2]*a[1],z[2]*a[0]-z[0]*a[2],z[0]*a[1]-z[1]*a[0]};return{{a[0],b[0],z[0],a[1],b[1],z[1],a[2],b[2],z[2]}};}
|
mat cont6(const float*x){double a[3]={x[0],x[1],x[2]},n=std::sqrt(a[0]*a[0]+a[1]*a[1]+a[2]*a[2]);for(double&q:a)q/=n;double z[3]={a[1]*x[5]-a[2]*x[4],a[2]*x[3]-a[0]*x[5],a[0]*x[4]-a[1]*x[3]};n=std::sqrt(z[0]*z[0]+z[1]*z[1]+z[2]*z[2]);for(double&q:z)q/=n;double b[3]={z[1]*a[2]-z[2]*a[1],z[2]*a[0]-z[0]*a[2],z[0]*a[1]-z[1]*a[0]};return{{a[0],b[0],z[0],a[1],b[1],z[1],a[2],b[2],z[2]}};}
|
||||||
void rotate(const mat&m,const float *x,float *o){for(int i=0;i<3;++i)o[i]=static_cast<float>(m.v[i*3]*x[0]+m.v[i*3+1]*x[1]+m.v[i*3+2]*x[2]);}
|
void rotate(const mat&m,const std::array<float,3>&x,float*o){for(int i=0;i<3;++i)o[i]=static_cast<float>(m.v[i*3]*x[0]+m.v[i*3+1]*x[1]+m.v[i*3+2]*x[2]);}
|
||||||
|
|
||||||
|
// Reconstruct the full-body/end-effector condition used by upstream
|
||||||
|
// `_multiprompt`, generalized over the three released skeleton layouts.
|
||||||
|
float condition_row(const float *raw, const skeleton_spec &s, float *value) {
|
||||||
|
const size_t D=s.motion_dim(),J=s.joints(),rotation_begin=5+3*J;
|
||||||
|
std::copy_n(raw,D,value);
|
||||||
|
std::vector<mat> decoded(J),local(J),global(J);
|
||||||
|
for(size_t j=0;j<J;++j)decoded[j]=cont6(value+rotation_begin+j*6);
|
||||||
|
for(size_t j=0;j<J;++j)local[j]=s.parents[j]<0?decoded[j]:mul(trans(decoded[static_cast<size_t>(s.parents[j])]),decoded[j]);
|
||||||
|
const float root[3]={value[0]+value[5],value[6],value[2]+value[7]};
|
||||||
|
std::vector<std::array<float,3>> posed(J);
|
||||||
|
for(size_t j=0;j<J;++j){const int parent=s.parents[j];if(parent<0){global[j]=local[j];posed[j]={root[0],root[1],root[2]};}else{global[j]=mul(global[static_cast<size_t>(parent)],local[j]);float offset[3];rotate(global[static_cast<size_t>(parent)],s.offsets[j],offset);for(int k=0;k<3;++k)posed[j][k]=posed[static_cast<size_t>(parent)][k]+offset[k];}}
|
||||||
|
const auto right=s.hips[0],left=s.hips[1];
|
||||||
|
const float angle=std::atan2(posed[right][2]-posed[left][2],-(posed[right][0]-posed[left][0]));
|
||||||
|
value[1]=root[1];value[3]=std::cos(angle);value[4]=std::sin(angle);
|
||||||
|
for(size_t j=0;j<J;++j){value[5+j*3]=posed[j][0]-value[0];value[6+j*3]=posed[j][1];value[7+j*3]=posed[j][2]-value[2];}
|
||||||
|
for(unsigned joint:s.end_effectors)for(int d=0;d<6;++d)value[rotation_begin+joint*6+static_cast<size_t>(d)]=static_cast<float>(global[joint].v[(d%3)*3+d/3]);
|
||||||
|
return angle;
|
||||||
}
|
}
|
||||||
|
}
|
||||||
|
|
||||||
std::expected<sequence_transition, std::string> prepare_sequence_transition(
|
std::expected<sequence_transition, std::string> prepare_sequence_transition(
|
||||||
const ggml_motion_weights &, std::span<const float> previous,
|
const ggml_motion_weights &weights, std::span<const float> previous,
|
||||||
std::size_t continuation_frames, unsigned transition_frames) {
|
std::size_t continuation_frames, unsigned transition_frames) {
|
||||||
constexpr size_t features = 273;
|
const auto *s=find_skeleton(weights.skeleton_key());
|
||||||
const size_t overlap=transition_frames;
|
if(!s)return std::unexpected("unsupported sequence skeleton");
|
||||||
if (!overlap || overlap>=continuation_frames || previous.size()<=(overlap*features))
|
const size_t D=s->motion_dim(),J=s->joints(),rotation_begin=5+3*J,rotation_end=rotation_begin+6*J,overlap=transition_frames;
|
||||||
|
if(!overlap||overlap>=continuation_frames||previous.size()<=overlap*D||previous.size()%D)
|
||||||
return std::unexpected("invalid sequence transition");
|
return std::unexpected("invalid sequence transition");
|
||||||
sequence_transition result;
|
sequence_transition result;
|
||||||
result.observed.resize((continuation_frames+overlap)*features);
|
result.observed.resize((continuation_frames+overlap)*D);
|
||||||
result.observed_mask.resize(result.observed.size());
|
result.observed_mask.resize(result.observed.size());
|
||||||
const size_t previous_start=previous.size()-overlap*features;
|
const size_t previous_start=previous.size()-overlap*D;
|
||||||
constexpr std::array<std::pair<size_t, size_t>, 3> constrained = {{{0, 71}, {113, 125}, {191, 203}}};
|
std::vector<float> value(D);
|
||||||
for (size_t frame=0; frame<overlap; ++frame) {
|
for(size_t frame=0;frame<overlap;++frame){const size_t base=frame*D;condition_row(previous.data()+previous_start+base,*s,value.data());std::copy_n(value.data(),rotation_end,result.observed.data()+base);std::fill(result.observed_mask.begin()+static_cast<std::ptrdiff_t>(base),result.observed_mask.begin()+static_cast<std::ptrdiff_t>(base+rotation_begin),1.F);for(unsigned joint:s->end_effectors){const size_t first=base+rotation_begin+joint*6;std::fill(result.observed_mask.begin()+static_cast<std::ptrdiff_t>(first),result.observed_mask.begin()+static_cast<std::ptrdiff_t>(first+6),1.F);}}
|
||||||
const size_t base=frame*features;
|
result.origin_x=result.observed[0];result.origin_z=result.observed[2];
|
||||||
std::array<float, features> value{};
|
for(size_t frame=0;frame<overlap;++frame){auto*row=result.observed.data()+frame*D;row[0]-=result.origin_x;row[2]-=result.origin_z;}
|
||||||
const float *raw=previous.data()+previous_start+base;
|
result.first_heading=condition_row(previous.data()+previous_start,*s,value.data());
|
||||||
std::copy_n(raw,features,value.data());
|
|
||||||
mat decoded[22],local[22],global[22]; for(int j=0;j<22;++j)decoded[j]=cont6(value.data()+71+j*6);
|
|
||||||
for(int j=0;j<22;++j) local[j]=parent[j]<0?decoded[j]:mul(trans(decoded[parent[j]]),decoded[j]);
|
|
||||||
float root[3]={value[0]+value[5],value[6],value[2]+value[7]}, posed[22][3]{};
|
|
||||||
for(int j=0;j<22;++j){if(parent[j]<0){global[j]=local[j];posed[j][0]=root[0];posed[j][1]=root[1];posed[j][2]=root[2];}else{global[j]=mul(global[parent[j]],local[j]);float d[3];rotate(global[parent[j]],offset[j],d);for(int k=0;k<3;++k)posed[j][k]=posed[parent[j]][k]+d[k];}}
|
|
||||||
// FullBodyConstraintSet: smooth root, root Y, heading, all joint
|
|
||||||
// positions; EndEffectorConstraintSet adds its four rotation blocks.
|
|
||||||
value[0]=value[0]; value[1]=root[1]; value[2]=value[2];
|
|
||||||
// `compute_heading_angle`: right hip minus left hip.
|
|
||||||
const float dx=posed[2][0]-posed[1][0], dz=posed[2][2]-posed[1][2], angle=std::atan2(dz,-dx);
|
|
||||||
value[3]=std::cos(angle); value[4]=std::sin(angle);
|
|
||||||
for(int j=0;j<22;++j){value[5+j*3]=posed[j][0]-value[0];value[6+j*3]=posed[j][1];value[7+j*3]=posed[j][2]-value[2];}
|
|
||||||
for(int j: {7,8,20,21}) for(int d=0;d<6;++d)
|
|
||||||
value[71+j*6+d]=static_cast<float>(global[j].v[(d%3)*3+d/3]);
|
|
||||||
std::copy_n(value.data(),203,result.observed.data()+base);
|
|
||||||
for (const auto &[first,last] : constrained)
|
|
||||||
std::fill(result.observed_mask.begin()+static_cast<std::ptrdiff_t>(base+first),
|
|
||||||
result.observed_mask.begin()+static_cast<std::ptrdiff_t>(base+last),1.F);
|
|
||||||
}
|
|
||||||
result.origin_x=result.observed[0];
|
|
||||||
result.origin_z=result.observed[2];
|
|
||||||
for (size_t frame=0; frame<overlap; ++frame) {
|
|
||||||
auto *row=result.observed.data()+frame*features;
|
|
||||||
row[0]-=result.origin_x;
|
|
||||||
row[2]-=result.origin_z;
|
|
||||||
}
|
|
||||||
// First heading comes from the first retained full-body constraint.
|
|
||||||
const size_t first=(previous.size()-overlap*features);
|
|
||||||
const float *raw=previous.data()+first;
|
|
||||||
std::array<float, features> value{}; std::copy_n(raw,features,value.data());
|
|
||||||
mat decoded[22],local[22],global[22]; for(int j=0;j<22;++j)decoded[j]=cont6(value.data()+71+j*6);
|
|
||||||
for(int j=0;j<22;++j)local[j]=parent[j]<0?decoded[j]:mul(trans(decoded[parent[j]]),decoded[j]);
|
|
||||||
float root[3]={value[0]+value[5],value[6],value[2]+value[7]}, posed[22][3]{};
|
|
||||||
for(int j=0;j<22;++j){if(parent[j]<0){global[j]=local[j];for(int k=0;k<3;++k)posed[j][k]=root[k];}else{global[j]=mul(global[parent[j]],local[j]);float d[3];rotate(global[parent[j]],offset[j],d);for(int k=0;k<3;++k)posed[j][k]=posed[parent[j]][k]+d[k];}}
|
|
||||||
result.first_heading=std::atan2(posed[2][2]-posed[1][2],-(posed[2][0]-posed[1][0]));
|
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
|
|
||||||
std::expected<std::vector<float>, std::string> sample_motion_sequence_from_noise(
|
std::expected<std::vector<float>, std::string> sample_motion_sequence_from_noise(
|
||||||
const ggml_motion_weights &weights, std::span<const sampled_sequence_segment> segments,
|
const ggml_motion_weights &weights, std::span<const sampled_sequence_segment> segments,
|
||||||
unsigned transition_frames, unsigned steps, float text_weight, float constraint_weight) {
|
unsigned transition_frames, unsigned steps, float text_weight, float constraint_weight) {
|
||||||
constexpr size_t features = 273;
|
const size_t D=weights.motion_dim(),body=D-5;
|
||||||
if (segments.empty() || !transition_frames)
|
if(segments.empty()||!transition_frames||!D)return std::unexpected("sequence requires segments and a transition");
|
||||||
return std::unexpected("sequence requires segments and a transition");
|
|
||||||
auto gm=weights.f32_values("stats.global_root.mean"),gs=weights.f32_values("stats.global_root.std");
|
auto gm=weights.f32_values("stats.global_root.mean"),gs=weights.f32_values("stats.global_root.std");
|
||||||
auto bm=weights.f32_values("stats.body.mean"),bs=weights.f32_values("stats.body.std");
|
auto bm=weights.f32_values("stats.body.mean"),bs=weights.f32_values("stats.body.std");
|
||||||
if (!gm || !gs || !bm || !bs) return std::unexpected("motion GGUF lacks motion statistics");
|
if(!gm||!gs||!bm||!bs||gm->size()!=5||gs->size()!=5||bm->size()!=body||bs->size()!=body)return std::unexpected("motion GGUF lacks compatible motion statistics");
|
||||||
// Upstream Stats normalizes with sqrt(std^2 + 1e-5), rather than raw std.
|
|
||||||
auto scale=[](float stddev){return std::sqrt(stddev*stddev+1.e-5F);};
|
auto scale=[](float stddev){return std::sqrt(stddev*stddev+1.e-5F);};
|
||||||
auto unnormalize = [&](std::vector<float> &motion) { for(size_t row=0;row<motion.size()/features;++row) { auto *v=motion.data()+row*features; for(size_t d=0;d<5;++d)v[d]=v[d]*scale((*gs)[d])+(*gm)[d]; for(size_t d=0;d<268;++d)v[5+d]=v[5+d]*scale((*bs)[d])+(*bm)[d]; } };
|
auto unnormalize=[&](std::vector<float>&motion){for(size_t row=0;row<motion.size()/D;++row){auto*v=motion.data()+row*D;for(size_t d=0;d<5;++d)v[d]=v[d]*scale((*gs)[d])+(*gm)[d];for(size_t d=0;d<body;++d)v[5+d]=v[5+d]*scale((*bs)[d])+(*bm)[d];}};
|
||||||
auto normalize = [&](std::vector<float> &motion) { for(size_t row=0;row<motion.size()/features;++row) { auto *v=motion.data()+row*features; for(size_t d=0;d<5;++d)v[d]=(v[d]-(*gm)[d])/scale((*gs)[d]); for(size_t d=0;d<268;++d)v[5+d]=(v[5+d]-(*bm)[d])/scale((*bs)[d]); } };
|
auto normalize=[&](std::vector<float>&motion){for(size_t row=0;row<motion.size()/D;++row){auto*v=motion.data()+row*D;for(size_t d=0;d<5;++d)v[d]=(v[d]-(*gm)[d])/scale((*gs)[d]);for(size_t d=0;d<body;++d)v[5+d]=(v[5+d]-(*bm)[d])/scale((*bs)[d]);}};
|
||||||
|
|
||||||
std::vector<float> joined,previous;
|
std::vector<float> joined,previous;
|
||||||
for (size_t index=0; index<segments.size(); ++index) {
|
for(size_t index=0;index<segments.size();++index){const auto&segment=segments[index];const size_t sampled_frames=segment.frames+(index?transition_frames:0);if(segment.frames<2||segment.embedding.size()!=4096||segment.initial_noise.size()!=sampled_frames*D)return std::unexpected("invalid sampled sequence segment");std::vector<float>current;if(!index){auto sampled=sample_motion_from_noise(weights,segment.initial_noise,segment.embedding,sampled_frames,steps,text_weight,constraint_weight);if(!sampled)return std::unexpected(sampled.error());current=std::move(*sampled);unnormalize(current);}else{const size_t overlap=transition_frames;if(overlap>=segment.frames||previous.size()<overlap*D)return std::unexpected("transition must be shorter than every following segment");auto transition=prepare_sequence_transition(weights,previous,segment.frames,transition_frames);if(!transition)return std::unexpected(transition.error());const float origin_x=transition->origin_x,origin_z=transition->origin_z;normalize(transition->observed);auto sampled=sample_motion_from_noise_conditioned(weights,segment.initial_noise,segment.embedding,transition->observed,transition->observed_mask,transition->first_heading,sampled_frames,steps,text_weight,constraint_weight);if(!sampled)return std::unexpected(sampled.error());current=std::move(*sampled);unnormalize(current);for(size_t frame=0;frame<sampled_frames;++frame){auto*row=current.data()+frame*D;row[0]+=origin_x;row[2]+=origin_z;}const size_t start=joined.size()-overlap*D;for(size_t frame=0;frame<overlap;++frame){const float alpha=overlap==1?.5F:1.F-float(frame)/float(overlap-1);for(size_t d=0;d<D;++d)joined[start+frame*D+d]=alpha*joined[start+frame*D+d]+(1.F-alpha)*current[frame*D+d];}joined.insert(joined.end(),current.begin()+static_cast<std::ptrdiff_t>(overlap*D),current.end());}if(!index)joined=current;previous=std::move(current);}
|
||||||
const auto &segment=segments[index];
|
|
||||||
const size_t sampled_frames=segment.frames+(index ? transition_frames : 0);
|
|
||||||
if (segment.frames < 2 || segment.embedding.size()!=4096 ||
|
|
||||||
segment.initial_noise.size()!=sampled_frames*features)
|
|
||||||
return std::unexpected("invalid sampled sequence segment");
|
|
||||||
std::vector<float> current;
|
|
||||||
if (!index) {
|
|
||||||
auto sampled=sample_motion_from_noise(weights,segment.initial_noise,segment.embedding,
|
|
||||||
sampled_frames,steps,text_weight,constraint_weight);
|
|
||||||
if (!sampled) return std::unexpected(sampled.error());
|
|
||||||
current=std::move(*sampled);
|
|
||||||
unnormalize(current);
|
|
||||||
} else {
|
|
||||||
const size_t overlap=transition_frames;
|
|
||||||
if (overlap >= segment.frames || previous.size()<overlap*features)
|
|
||||||
return std::unexpected("transition must be shorter than every following segment");
|
|
||||||
auto transition=prepare_sequence_transition(weights,previous,segment.frames,transition_frames);
|
|
||||||
if (!transition) return std::unexpected(transition.error());
|
|
||||||
const float origin_x=transition->origin_x;
|
|
||||||
const float origin_z=transition->origin_z;
|
|
||||||
normalize(transition->observed);
|
|
||||||
auto sampled=sample_motion_from_noise_conditioned(weights,segment.initial_noise,segment.embedding,
|
|
||||||
transition->observed,transition->observed_mask,transition->first_heading,sampled_frames,steps,text_weight,constraint_weight);
|
|
||||||
if (!sampled) return std::unexpected(sampled.error());
|
|
||||||
current=std::move(*sampled);
|
|
||||||
unnormalize(current);
|
|
||||||
for (size_t frame=0; frame<sampled_frames; ++frame) {
|
|
||||||
auto *row=current.data()+frame*features;
|
|
||||||
row[0]+=origin_x;
|
|
||||||
row[2]+=origin_z;
|
|
||||||
}
|
|
||||||
const size_t start=joined.size()-overlap*features;
|
|
||||||
for (size_t frame=0; frame<overlap; ++frame) {
|
|
||||||
const float alpha=overlap==1?.5F:1.F-float(frame)/float(overlap-1);
|
|
||||||
for (size_t d=0; d<features; ++d)
|
|
||||||
joined[start+frame*features+d]=alpha*joined[start+frame*features+d]+(1.F-alpha)*current[frame*features+d];
|
|
||||||
}
|
|
||||||
joined.insert(joined.end(),current.begin()+static_cast<std::ptrdiff_t>(overlap*features),current.end());
|
|
||||||
}
|
|
||||||
if (!index) joined=current;
|
|
||||||
previous=std::move(current);
|
|
||||||
}
|
|
||||||
return joined;
|
return joined;
|
||||||
}
|
}
|
||||||
} // namespace kimodo::detail
|
} // namespace kimodo::detail
|
||||||
|
|||||||
101
src/skeleton.hpp
Normal file
101
src/skeleton.hpp
Normal file
@ -0,0 +1,101 @@
|
|||||||
|
#pragma once
|
||||||
|
|
||||||
|
#include <array>
|
||||||
|
#include <cstddef>
|
||||||
|
#include <span>
|
||||||
|
#include <string_view>
|
||||||
|
|
||||||
|
namespace kimodo::detail {
|
||||||
|
|
||||||
|
// Joint names and parent graphs are copied from NVIDIA Kimodo's Apache-2.0
|
||||||
|
// kimodo/skeleton/definitions.py. Parent-local offsets were extracted from
|
||||||
|
// the accompanying joints.p assets in the trusted reference container.
|
||||||
|
struct skeleton_spec {
|
||||||
|
std::string_view key;
|
||||||
|
std::span<const std::string_view> names;
|
||||||
|
std::span<const int> parents;
|
||||||
|
std::span<const std::array<float, 3>> offsets;
|
||||||
|
std::array<unsigned, 2> hips; // right, left
|
||||||
|
std::array<unsigned, 4> end_effectors; // left foot, right foot, left hand, right hand
|
||||||
|
|
||||||
|
[[nodiscard]] constexpr std::size_t joints() const noexcept { return names.size(); }
|
||||||
|
[[nodiscard]] constexpr std::size_t motion_dim() const noexcept { return 9 + 12 * joints(); }
|
||||||
|
[[nodiscard]] constexpr std::size_t body_dim() const noexcept { return motion_dim() - 5; }
|
||||||
|
};
|
||||||
|
|
||||||
|
inline constexpr std::array<std::string_view,22> smplx22_names{
|
||||||
|
std::string_view{"pelvis"}, "left_hip", "right_hip", "spine1", "left_knee", "right_knee",
|
||||||
|
"spine2", "left_ankle", "right_ankle", "spine3", "left_foot", "right_foot", "neck",
|
||||||
|
"left_collar", "right_collar", "head", "left_shoulder", "right_shoulder", "left_elbow",
|
||||||
|
"right_elbow", "left_wrist", "right_wrist"};
|
||||||
|
inline constexpr std::array smplx22_parents{-1,0,0,0,1,2,3,4,5,6,7,8,9,9,9,12,13,14,16,17,18,19};
|
||||||
|
inline constexpr std::array<std::array<float,3>,22> smplx22_offsets{{
|
||||||
|
{0,0,0},{.052299179F,-.093935639F,-.027606763F},{-.057192899F,-.106548190F,-.022217851F},
|
||||||
|
{-.001495834F,.112929940F,-.024981268F},{.058866613F,-.416441321F,-.006556974F},
|
||||||
|
{-.048074268F,-.397559673F,-.014061437F},{.006900469F,.145636231F,-.006858510F},
|
||||||
|
{-.041737989F,-.437583506F,-.029511765F},{.014489345F,-.446852267F,-.018029511F},
|
||||||
|
{-.010334037F,.056081813F,.021115851F},{.049293540F,-.065279245F,.126259089F},
|
||||||
|
{-.040575184F,-.065286517F,.127075911F},{-.011025756F,.171365142F,-.028827066F},
|
||||||
|
{.047724526F,.087643057F,-.008375450F},{-.046636276F,.086612143F,-.014864366F},
|
||||||
|
{.024654359F,.175390735F,.024463326F},{.126284808F,.057680372F,-.013885141F},
|
||||||
|
{-.109341696F,.053674292F,-.009117880F},{.272907287F,-.069853373F,-.039094493F},
|
||||||
|
{-.292028785F,-.035440356F,-.024564851F},{.276173830F,.021254137F,-.002478220F},
|
||||||
|
{-.271878421F,-.004834589F,-.016445294F}}};
|
||||||
|
|
||||||
|
inline constexpr std::array<std::string_view,30> soma30_names{
|
||||||
|
std::string_view{"Hips"}, "Spine1", "Spine2", "Chest", "Neck1", "Neck2", "Head", "Jaw",
|
||||||
|
"LeftEye", "RightEye", "LeftShoulder", "LeftArm", "LeftForeArm", "LeftHand",
|
||||||
|
"LeftHandThumbEnd", "LeftHandMiddleEnd", "RightShoulder", "RightArm", "RightForeArm",
|
||||||
|
"RightHand", "RightHandThumbEnd", "RightHandMiddleEnd", "LeftLeg", "LeftShin", "LeftFoot",
|
||||||
|
"LeftToeBase", "RightLeg", "RightShin", "RightFoot", "RightToeBase"};
|
||||||
|
inline constexpr std::array soma30_parents{-1,0,1,2,3,4,5,6,6,6,3,10,11,12,13,13,3,16,17,18,19,19,0,22,23,24,0,26,27,28};
|
||||||
|
inline constexpr std::array<std::array<float,3>,30> soma30_offsets{{
|
||||||
|
{0,0,0},{-.00013727F,.0500376256F,-.00053726669F},{-1.86574103e-9F,.0712530139F,-.000298248546F},
|
||||||
|
{-5.75188398e-9F,.0755006305F,-.00815970992F},{-.00181676517F,.263112953F,-.00553348292F},
|
||||||
|
{-2.85102231e-8F,.0770939664F,.0230258546F},{-4.5975437e-8F,.0612891595F,.0195370861F},
|
||||||
|
{2.63687901e-5F,.0047559225F,.0309494062F},{.0320638079F,.0538020513F,.0758688308F},
|
||||||
|
{-.0322244017F,.05361869F,.0755823359F},{.0162165175F,.232371641F,.0511341324F},
|
||||||
|
{.149198457F,2.19397873e-8F,-.0550232576F},{.287393078F,2.50268389e-9F,-2.58787737e-5F},
|
||||||
|
{.270939812F,-7.06625108e-9F,2.60897248e-5F},{.122686267F,-.0322017573F,.0483306876F},
|
||||||
|
{.190119595F,-.00312878387F,-.000339570373F},{-.0138011824F,.231803086F,.0521415786F},
|
||||||
|
{-.150371962F,1.17387901e-7F,-.0554560437F},{-.287366393F,1.87628082e-8F,-2.59709359e-5F},
|
||||||
|
{-.271336198F,-1.16767401e-9F,2.61269368e-5F},{-.122642483F,-.0321145448F,.0480403904F},
|
||||||
|
{-.190005945F,-.00306615542F,-.0003157343F},{.10043214F,-.0843452671F,.0259565473F},
|
||||||
|
{-1e-8F,-.432217537F,-.00802912805F},{1e-8F,-.421550959F,-.0348152298F},
|
||||||
|
{0,-.0505947206F,.132315294F},{-.10047278F,-.0829525995F,.0262031695F},
|
||||||
|
{1e-8F,-.433622059F,-.00805555828F},{2e-8F,-.421173943F,-.0347839785F},
|
||||||
|
{-3.42907669e-9F,-.0507960932F,.132841956F}}};
|
||||||
|
|
||||||
|
inline constexpr std::array<std::string_view,34> g1skel34_names{
|
||||||
|
std::string_view{"pelvis_skel"}, "left_hip_pitch_skel", "left_hip_roll_skel", "left_hip_yaw_skel",
|
||||||
|
"left_knee_skel", "left_ankle_pitch_skel", "left_ankle_roll_skel", "left_toe_base",
|
||||||
|
"right_hip_pitch_skel", "right_hip_roll_skel", "right_hip_yaw_skel", "right_knee_skel",
|
||||||
|
"right_ankle_pitch_skel", "right_ankle_roll_skel", "right_toe_base", "waist_yaw_skel",
|
||||||
|
"waist_roll_skel", "waist_pitch_skel", "left_shoulder_pitch_skel", "left_shoulder_roll_skel",
|
||||||
|
"left_shoulder_yaw_skel", "left_elbow_skel", "left_wrist_roll_skel", "left_wrist_pitch_skel",
|
||||||
|
"left_wrist_yaw_skel", "left_hand_roll_skel", "right_shoulder_pitch_skel",
|
||||||
|
"right_shoulder_roll_skel", "right_shoulder_yaw_skel", "right_elbow_skel",
|
||||||
|
"right_wrist_roll_skel", "right_wrist_pitch_skel", "right_wrist_yaw_skel", "right_hand_roll_skel"};
|
||||||
|
inline constexpr std::array g1skel34_parents{-1,0,1,2,3,4,5,6,0,8,9,10,11,12,13,0,15,16,17,18,19,20,21,22,23,24,17,26,27,28,29,30,31,32};
|
||||||
|
inline constexpr std::array<std::array<float,3>,34> g1skel34_offsets{{
|
||||||
|
{0,0,0},{.064452F,-.1027F,0},{.052F,-.030465F,0},{0,-.12412F,.025001F},
|
||||||
|
{.0021489F,-.17734F,-.078273F},{-.000094445F,-.30001F,0},{0,-.017558F,0},{0,-.035F,.14F},
|
||||||
|
{-.064452F,-.1027F,0},{-.052F,-.030465F,0},{0,-.12412F,.025001F},{-.0021489F,-.17734F,-.078273F},
|
||||||
|
{.000094445F,-.30001F,0},{0,-.017558F,0},{0,-.035F,.14F},{0,0,0},{0,.044F,-.0039635F},
|
||||||
|
{0,0,0},{.10022F,.24778F,.0039563F},{.038F,-.013831F,0},{.00624F,-.1032F,0},
|
||||||
|
{0,-.080518F,.015783F},{.00188791F,-.01F,.1F},{0,0,.038F},{0,0,.046F},{0,0,.1F},
|
||||||
|
{-.10021F,.24778F,.0039563F},{-.038F,-.013831F,0},{-.00624F,-.1032F,0},
|
||||||
|
{0,-.080518F,.015783F},{-.00188791F,-.01F,.1F},{0,0,.038F},{0,0,.046F},{0,0,.1F}}};
|
||||||
|
|
||||||
|
inline constexpr skeleton_spec smplx22_spec{"smplx22", smplx22_names, smplx22_parents, smplx22_offsets, {2,1}, {7,8,20,21}};
|
||||||
|
inline constexpr skeleton_spec soma30_spec{"soma30", soma30_names, soma30_parents, soma30_offsets, {26,22}, {24,28,13,19}};
|
||||||
|
inline constexpr skeleton_spec g1skel34_spec{"g1skel34", g1skel34_names, g1skel34_parents, g1skel34_offsets, {8,1}, {6,13,24,32}};
|
||||||
|
|
||||||
|
inline constexpr const skeleton_spec *find_skeleton(std::string_view key) noexcept {
|
||||||
|
if (key == smplx22_spec.key) return &smplx22_spec;
|
||||||
|
if (key == soma30_spec.key) return &soma30_spec;
|
||||||
|
if (key == g1skel34_spec.key) return &g1skel34_spec;
|
||||||
|
return nullptr;
|
||||||
|
}
|
||||||
|
|
||||||
|
} // namespace kimodo::detail
|
||||||
@ -1,4 +1,5 @@
|
|||||||
#include <kimodo/kimodo.hpp>
|
#include <kimodo/kimodo.hpp>
|
||||||
#include <array>
|
#include <array>
|
||||||
#include <cstdio>
|
#include <cstdio>
|
||||||
int main(int argc,char**argv){if(argc!=2)return 2;auto m=kimodo::model::load(argv[1]);if(!m){std::fprintf(stderr,"%s\n",m.error().c_str());return 1;}std::array<float,kimodo::embedding_width> e{};auto r=(*m)->generate_embedding(e,2,1,42,2.f,2.f);if(!r){std::fprintf(stderr,"%s\n",r.error().c_str());return 1;}if(r->frames!=2||r->joints!=22||r->root_positions.size()!=6||r->local_rotations_xyzw.size()!=176)return 1;return 0;}
|
#include <fstream>
|
||||||
|
int main(int argc,char**argv){if(argc<2||argc>4)return 2;const unsigned joints=argc>=3?static_cast<unsigned>(std::stoul(argv[2])):22;auto m=kimodo::model::load(argv[1]);if(!m){std::fprintf(stderr,"%s\n",m.error().c_str());return 1;}std::array<float,kimodo::embedding_width> e{};auto r=(*m)->generate_embedding(e,2,1,42,2.f,2.f);if(!r){std::fprintf(stderr,"%s\n",r.error().c_str());return 1;}if(r->frames!=2||r->joints!=joints||r->root_positions.size()!=6||r->local_rotations_xyzw.size()!=2*joints*4)return 1;if(argc==4){std::ofstream out(argv[3],std::ios::binary);out.write(reinterpret_cast<const char*>(r->root_positions.data()),static_cast<std::streamsize>(r->root_positions.size()*sizeof(float)));out.write(reinterpret_cast<const char*>(r->local_rotations_xyzw.data()),static_cast<std::streamsize>(r->local_rotations_xyzw.size()*sizeof(float)));if(!out)return 1;}return 0;}
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user