monster/Qwen-Image-Layered-MRP-MLX
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
461 Commits 1 Branch 1 Tag 122 MiB
a255e4f0bb
Commit Graph

129 Commits

Author SHA1 Message Date
Zimeng Xiong
a255e4f0bb Add chunked saving for low memory, add pre-quantized models to README
Some checks failed
Fast Tests / fast-tests (push) Has been cancelled
Details
2025-12-22 08:46:28 -08:00
Zimeng Xiong
fe6936449d Add Qwen-Image-Layered support for image decomposition into RGBA layers 
This PR adds support for the Qwen-Image-Layered model, which decomposes an input
image into semantically disentangled RGBA layers for layer-based editing workflows.

## Features
- New CLI command: \`mflux-generate-qwen-layered\`
- Decomposes images into N RGBA layers (default 4)
- Supports 6-bit quantization for ~29GB memory usage (vs 55GB BF16)
- Resolution buckets: 640 and 1024

## Architecture
- RGBA-VAE (4-channel) with 3D temporal convolutions for layer handling
- Layer3D RoPE: 3D positional encoding [layer, height, width]
- Uses base QwenTransformer with extended RoPE for multi-layer sequences
- Condition image encoded as layer_index=-1 for proper decomposition

## New Files
- \`src/mflux/models/qwen_layered/\` - Full model implementation
  - \`model/qwen_layered_vae/\` - RGBA-VAE encoder/decoder
  - \`model/qwen_layered_transformer/\` - Layer3D RoPE
  - \`weights/\` - Weight mapping and definitions
  - \`variants/i2l/\` - Image-to-Layers pipeline
  - \`cli/\` - Command-line interface

## Usage
\`\`\`sh
mflux-generate-qwen-layered \\
  --image input.png \\
  --layers 4 \\
  --steps 50 \\
  -q 6 \\
  --output-dir ./layers
\`\`\`

## Documentation
Added comprehensive documentation to README.md including:
- TOC entry
- CLI argument reference
- Usage examples and tips
- Memory requirements

Tested on M4 Max 48GB with 6-bit quantization.
 2025-12-22 08:08:20 -08:00
filipstrand
d70c8edb8c Add small README note on pre-quantized models on Huggingface 2025-12-17 21:22:35 +01:00
filipstrand
ef5fce289a Update documentation temporarily for prerelease to enable v.5.0rc of transformers 2025-12-03 23:01:21 +01:00
filipstrand
c5f8b73d9d Fix import 2025-12-03 22:50:02 +01:00
Filip Strand
8e5609132c
Release 0.13.0 (#289) 2025-12-03 22:40:44 +01:00
Filip Strand
37d202d0df
Add support for Z-image Turbo & major improvements for weight loading and parameter resolution (#284) 2025-12-03 15:19:32 +01:00
filipstrand
38b1b538fe Fix trailing spaces after backslashes in shell examples 
Remove trailing spaces after backslashes in FIBO command examples.
These caused shell line continuation to break when users copy-pasted
the commands, resulting in 'command not found' errors.
 2025-11-27 16:50:46 +01:00
Filip Strand
c2c860f4de
Add Bria FIBO support (#279) 
Co-authored-by: Filip Strand <filip@host-022.local>
 2025-11-27 13:01:55 +01:00
Filip Strand
2e92984125
Release 0.11.1 (#278) 
Co-authored-by: Filip Strand <filip@Host-022.local>
 2025-11-13 01:05:29 +01:00
Filip Strand
d314aa6889
Release 0.11.0 (#271) 2025-10-14 00:34:27 +02:00
Alessandro Rizzo
83354c3921
Add XMP/IPTC metadata support (#267) 
Co-authored-by: filipstrand <strand.filip@gmail.com>
 2025-10-12 14:45:28 +02:00
Filip Strand
98e03a46f2
Add Qwen Image support (#269) 2025-10-06 07:41:14 +02:00
Anthony Wu
0d9af4f380
Python 3.13 sentencepiece and torch unblocked (#259) 
Co-authored-by: Anthony Wu <pls-file-gh-issue@users.noreply.github.com>
 2025-08-31 22:06:26 +02:00
Filip Strand
4f9af80956
Small README update (#244) 2025-08-03 11:27:30 +02:00
Filip Strand
beee9b9509
Add support for FLUX.1-Krea-dev model (#241) 2025-08-03 00:41:00 +02:00
Aarni Koskela
b8498c59db
Link to 4-bit quantized Kontext model on HF (#240) 2025-07-30 17:25:57 +02:00
filipstrand
7df35522f5 Fix imports after empty mflux init file 2025-07-17 12:00:40 +02:00
Anthony Wu
42bf9e3d4d
Hot Fix: coldstart weight download (version 0.9.3) (#235) 2025-07-08 20:19:34 -07:00
Filip Strand
7388a856e5
Add Flux1.Kontext[dev] support (#219) 2025-06-27 23:37:19 +02:00
Anthony Wu
b26a1d66b3
🖼️↗️ Add scale factor support for image upscaling dimensions (#215) 
Co-authored-by: Anthony Wu <pls-file-gh-issue@users.noreply.github.com>
Co-authored-by: filipstrand <strand.filip@gmail.com>
 2025-06-27 19:51:00 +02:00
Anthony Wu
0125103634
➡️➡️ Tab Tab for zsh: CLI completion generator (#208) 
Co-authored-by: Anthony Wu <pls-file-gh-issue@users.noreply.github.com>
Co-authored-by: filipstrand <strand.filip@gmail.com>
 2025-06-27 15:48:51 +02:00
Anthony Wu
6c3ba1e065
🗂️ Cache Refactor - use platformdirs helper (#201) 
Co-authored-by: Anthony Wu <pls-file-gh-issue@users.noreply.github.com>
 2025-06-27 13:59:43 +02:00
Filip Strand
9a20e83331
Small additions before 0.8.0 (#209) 2025-06-14 10:02:04 +02:00
Filip Strand
847404748f
Generalise in-context functionality (#203) 
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: filipstrand <filipstrand@users.noreply.github.com>
 2025-06-12 09:01:07 +02:00
Anthony Wu
c31326ff33
Support prompt text via stdin. e.g. LLMs can generate prompts that directly feed into mflux. (#204) 
Co-authored-by: Anthony Wu <pls-file-gh-issue@users.noreply.github.com>
 2025-06-11 07:31:46 +02:00
Filip Strand
13bfb24964
Concept Attention (#199) 2025-06-04 19:27:03 +02:00
Anthony Wu
d3e71328b2
LORA_LIBRARY_PATH for Unix-style resource discovery (#198) 
Co-authored-by: Anthony Wu <pls-file-gh-issue@users.noreply.github.com>
Co-authored-by: filipstrand <strand.filip@gmail.com>
 2025-06-04 16:33:31 +02:00
Filip Strand
fa56f33161
Add upscaling support (#184) 2025-05-22 19:40:27 +02:00
Anthony Wu
d20f2833da
🪫 Battery Saver - manage power over long batch operations (#189) 
Co-authored-by: Anthony Wu <pls-file-gh-issue@users.noreply.github.com>
Co-authored-by: filipstrand <strand.filip@gmail.com>
 2025-05-19 17:13:41 +02:00
Anthony Wu
4b56633e6c
Add support for --prompt-file for dynamic prompt updates in large batches (#185) 
Co-authored-by: Anthony Wu <pls-file-gh-issue@users.noreply.github.com>
Co-authored-by: filipstrand <strand.filip@gmail.com>
 2025-05-19 17:10:52 +02:00
Alessandro
3b47c0b7e5
Possibility to balance the Redux function (#190) 
Co-authored-by: Alessandro Rizzo <alessandrorizzo@Alessandros-Mac-Studio.local>
Co-authored-by: filipstrand <strand.filip@gmail.com>
 2025-05-19 15:28:15 +02:00
filipstrand
d376f9c931 FLUX.1 Tools | Redux & Depth 2025-04-24 09:08:21 +02:00
Serkan Sakar
d225d1bbb9 More low-ram improvements 2025-03-22 10:46:21 +01:00
filipstrand
d4d98186e2 FLUX.1 Tools | Fill 2025-03-16 11:12:34 +01:00
filipstrand
cb09eacb69 Update readme with new 4-bit download location 2025-03-15 10:00:47 +01:00
filipstrand
ab3d7abdd2 Update readme to be up-to-date with the newest features 2025-03-05 08:00:01 +01:00
filipstrand
f75593b1dc New: Add In-Context-LoRA feature 2025-03-05 07:55:21 +01:00
filipstrand
5ec7ab5b41 Renaming: Remove 'init' prefix for a more general interface 2025-03-05 07:30:46 +01:00
Serkan Sakar
50752f58f4 Memory usage optimizations 2025-02-28 20:43:01 +01:00
filipstrand
e3b2a65aa6 Allow 3-bit and 6-bit quantization (mlx > v0.21.0) 2025-02-12 22:27:34 +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
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
Anthony Wu
af01fab7d5 support multiple seeds batch generation 2025-01-21 18:14:24 -08:00
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
0eb8f5082e Update README with perf. update, installation issue and version link 2024-12-26 21:03:54 +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