Serkan Sakar
|
f65286e1fb
|
add memory saver to controlnet
|
2025-03-02 19:28:19 +01:00 |
|
Serkan Sakar
|
50752f58f4
|
Memory usage optimizations
|
2025-02-28 20:43:01 +01:00 |
|
filipstrand
|
821238284a
|
Fix: Handle edge case for img2img
|
2025-02-14 05:21:35 +01:00 |
|
filipstrand
|
74173f543e
|
Let before-loop callback accept latents and let StepwiseHandler include initial latent
|
2025-02-14 05:21:18 +01:00 |
|
filipstrand
|
3cecfae75b
|
Refactor model config
|
2025-02-12 22:27:34 +01:00 |
|
filipstrand
|
e3b2a65aa6
|
Allow 3-bit and 6-bit quantization (mlx > v0.21.0)
|
2025-02-12 22:27:34 +01:00 |
|
filipstrand
|
09d75e46b8
|
Add PromptCache: Small optimization for repeated generations with same prompt
|
2025-02-12 22:27:34 +01:00 |
|
filipstrand
|
3601baf75e
|
Implement general callback mechanism
|
2025-02-09 15:27:06 +01:00 |
|
filipstrand
|
e4af40e4ee
|
Refactor: Remove ConfigControlnet
|
2025-02-09 14:37:23 +01:00 |
|
filipstrand
|
22f98fc5a4
|
Refactor: Add separate Flux initializer
|
2025-02-09 14:37:23 +01:00 |
|
filipstrand
|
b5db14b3c6
|
Add descriptive comments for attention computations
|
2025-02-02 19:12:07 +01:00 |
|
filipstrand
|
0485cf07c2
|
Refactor: Transformer blocks
|
2025-02-02 19:12:07 +01:00 |
|
filipstrand
|
0d9a5d626f
|
Refactor: Transformer & Flux
|
2025-02-02 19:12:07 +01:00 |
|
filipstrand
|
fa99cf0cc8
|
Refactor: Controlnet transformer & Flux controlnet
|
2025-02-02 16:45:27 +01:00 |
|
filipstrand
|
010610e33b
|
Remove comments
|
2025-01-28 00:04:35 +01:00 |
|
filipstrand
|
f94edc4c3b
|
Some fixes: Removed time in plotting, fix off-by-one error in training spec, update y-axis on loss plot
|
2025-01-27 23:48:03 +01:00 |
|
Alessandro
|
401da9fd75
|
Rebased on main (by filipstrand)
|
2025-01-27 23:15:27 +01:00 |
|
Filip Strand
|
cb93e1aaf6
|
Merge pull request #120 from anthonywu/renamer-uv-script-tool
Batch Image Renamer tool as an isolated uv run script
|
2025-01-27 22:23:18 +01:00 |
|
Anthony Wu
|
9053bcd6d8
|
Batch Image Renamer tool as an isolated uv run script
|
2025-01-22 13:25:59 -08:00 |
|
Filip Strand
|
4bea7b9668
|
Merge pull request #118 from anthonywu/run-n-seeds-auto-seeds
support multiple seeds batch generation
|
2025-01-22 19:58:51 +01:00 |
|
filipstrand
|
807b243e56
|
Support variable numbers of transformer blocks
|
2025-01-22 08:18:39 +01:00 |
|
Anthony Wu
|
af01fab7d5
|
support multiple seeds batch generation
|
2025-01-21 18:14:24 -08:00 |
|
filipstrand
|
6fbbc9e5f7
|
Update missing model config lookup
|
2025-01-19 23:23:19 +01:00 |
|
filipstrand
|
398cf082c3
|
Fix string formating
|
2025-01-19 19:49:57 +01:00 |
|
filipstrand
|
21a98b1369
|
Small updates
|
2025-01-19 15:19:17 +01:00 |
|
Anthony Wu
|
344ac90c74
|
comprehensive ModelConfig refactor to support compatible HuggingFace dev/schnell models
|
2025-01-17 06:27:33 -08:00 |
|
filipstrand
|
16a0225b41
|
Specify precision for causal attention mask
|
2025-01-14 21:32:02 +01:00 |
|
filipstrand
|
9954e7fb45
|
Unify attention mechanism in single and joint attention blocks
|
2025-01-14 20:16:48 +01:00 |
|
filipstrand
|
f0e82ad67f
|
Optimization: Use fast SDPA (no speedup for me on tests, but a bit cleaner)
Had to update reference test images, but visually no difference
|
2025-01-14 20:16:23 +01:00 |
|
filipstrand
|
4c0aff9168
|
Fix bug with quantization level being str instead of int
|
2024-12-23 12:21:06 +01:00 |
|
filipstrand
|
bae49c8145
|
Dreambooth v1
|
2024-12-22 19:42:37 +01:00 |
|
filipstrand
|
ce387921c5
|
Add named args for height and width for clarity
|
2024-10-29 20:12:50 +01:00 |
|
filipstrand
|
82973f9e95
|
Fix bug: swap width <--> height
|
2024-10-29 20:12:50 +01:00 |
|
filipstrand
|
4e2a10b1b9
|
Rewrite img2img latent creation to emphasize the linear interp between latent and noise
|
2024-10-29 19:19:59 +01:00 |
|
filipstrand
|
ea6202b49f
|
Add img2img example in readme
|
2024-10-28 00:32:57 +01:00 |
|
Anthony Wu
|
960447f92e
|
update type hint
|
2024-10-26 20:24:28 -07:00 |
|
Anthony Wu
|
98d7ef5751
|
update: do not require model arg, add controlnet_save_canny, fix bugs, add tests
|
2024-10-26 20:22:32 -07:00 |
|
Anthony Wu
|
ffaf562a8c
|
fix type hint in test file
|
2024-10-26 10:29:33 -07:00 |
|
Anthony Wu
|
351cc8bbf1
|
support metadata files as CLI arg supplier
|
2024-10-20 09:18:49 -07:00 |
|
filipstrand
|
2ed0628e58
|
Light refactoring: Move latent creation to separate class
|
2024-10-20 11:49:43 +02:00 |
|
filipstrand
|
f08c667e1a
|
Remove vae type alias from runtime_config.py
|
2024-10-20 11:05:45 +02:00 |
|
Anthony Wu
|
1160d4e8b2
|
controlnet files: revert the refactoring done in #77
|
2024-10-20 01:06:02 -07:00 |
|
Anthony Wu
|
6201a93d4a
|
tests and fixes for image to image
|
2024-10-20 00:48:45 -07:00 |
|
Anthony Wu
|
f963b7a9b2
|
image to image implementation
|
2024-10-12 10:46:20 -07:00 |
|
filipstrand
|
9c7e857082
|
Add type hinting to CommandLineParser
|
2024-10-12 14:35:11 +02:00 |
|
Anthony Wu
|
796e9e8305
|
refactor argparser
|
2024-10-11 15:03:52 -07:00 |
|
Anthony Wu
|
9b6cd01171
|
introduce ruff isort
|
2024-10-10 11:56:14 -07:00 |
|
Filip Strand
|
faaf905667
|
Merge pull request #71 from anthonywu/typos-check
introduce pre-commit typos check
|
2024-10-10 20:31:21 +02:00 |
|
filipstrand
|
8ec5410a56
|
Mark stepwise feature as experimental for now
|
2024-10-10 07:43:19 +02:00 |
|
Anthony Wu
|
19867d5bb7
|
introduce pre-commit typos check
|
2024-10-09 14:20:49 -07:00 |
|