bubbliiiing
e52c17b96e
Update minimax h3
2026-10-23 14:15:44 +08:00
bubbliiiing
03ef7ec62b
Update self forcing code
2026-10-23 13:20:38 +08:00
bubbliiiing
e7afc604e1
Update self forcing gan and causal forcing precision
2026-10-23 13:10:15 +08:00
bubbliiiing
42b33f4998
Update sparkwan md
2026-10-20 15:13:35 +08:00
bubbliiiing
e94e7e0c78
Update sparkwan
2026-10-20 13:23:31 +08:00
bubbliiiing
467150f68f
Update sparkwan
2026-10-19 20:23:02 +08:00
bubbliiiing
ae07a9435d
Update sparkwan
2026-10-19 15:44:25 +08:00
bubbliiiing
32f8c790f2
Update sparkwan
2026-10-19 14:59:49 +08:00
bubbliiiing
ef6c201d9d
Update sparkwan
2026-10-13 10:03:02 +08:00
bubbliiiing
4f76b103d2
Update sparkwan
2026-10-13 10:00:14 +08:00
bubbliiiing
0ff4723eb2
Update sparkwan
2026-10-12 22:44:18 +08:00
bubbliiiing
cd6fbc070c
Update sparkwan and reward model training
2026-10-12 22:25:49 +08:00
Bubbliiiing
4b7b6402a1
Upgrade GPU Memory Mode architecture ( #521 )
2026-09-29 19:18:17 +08:00
dellenovo
f3d5491459
Fix a typo in xFuserLongContextAttention ( #520 )
2026-09-27 09:13:59 +08:00
Bubbliiiing
67e3b4b818
Update Qwen Image 2.1 Control and Flex Forcing ( #519 )
2026-09-24 15:52:16 +08:00
Bubbliiiing
bce42b301f
Update Readme ( #517 )
2026-09-22 21:06:38 +08:00
Bubbliiiing
2beb171099
Support Qwen-Image2.1 && Support new Control for Minimax-H3 && Support Wan2.2 with 2.2VAE && Update new tqdm for All Training Code ( #511 )
2026-09-22 20:41:39 +08:00
hkz
968f0e2192
Add PDD for MiniMax-H3 ( #515 )
2026-09-04 17:02:21 +08:00
谢翊凡 and 谢翊凡
43739895a1
fix: use dtype instead of deprecated torch_dtype ( #514 )
...
* fix: use dtype instead of deprecated torch_dtype for transformers >= 4.56
config.torch_dtype and the torch_dtype keyword argument were deprecated in transformers 4.56 (PR #39782 ). Use dtype when accepted and fall back to torch_dtype via try/except TypeError for older versions.
* fix: use dtype instead of deprecated torch_dtype for transformers >= 4.56
config.torch_dtype and the torch_dtype keyword argument were deprecated in transformers 4.56 (PR #39782 ). Pass dtype based on the installed transformers version (packaging.version), falling back to torch_dtype on older versions.
---------
Co-authored-by: 谢翊凡 <xyf5432@users.noreply.github.com >
2026-09-02 16:47:39 +08:00
Bubbliiiing
6f3fb60dad
Update scale fp8 with fsdp ( #508 )
2026-08-25 12:35:36 +08:00
Bubbliiiing
b0acf916c2
Update Lingbot Worl, Lingbot Video, Minimax-H3 and Minimax-H3 Control ( #506 )
2026-08-24 16:47:38 +08:00
hkz
6787dc8ed4
Add DFD for Wan2.1 and Wan2.2 ( #505 )
2026-08-13 16:56:53 +08:00
hkz
248ab0ac0e
Add Causal-Focing for Wan2.1 ( #500 )
2026-07-22 17:37:05 +08:00
Bubbliiiing
403f1f7b78
Fix Bug in Self Forcing in Multi-Gpus Infernece && Update Training Code and Docs && Update Reward Models ( #498 )
2026-07-14 10:30:54 +08:00
Bubbliiiing
1fd9ed9208
Ode training && Update Lens model && Update LTX2 upsampler ( #497 )
2026-06-09 15:20:04 +08:00
Bubbliiiing
2b5596b8e6
Update Self-Forcing and Ernie Image ( #490 )
2026-05-25 17:39:17 +08:00
Bubbliiiing
804a4258e2
Update Flash Head && Update Readmes ( #491 )
2026-05-12 16:48:47 +08:00
Tyler Luan
8fb0bb165c
Align with the official FlashHead implementation ( #488 )
...
- Update predict_s2v.py with improved inference configuration
- Align pipeline_flashhead.py with official streaming, scheduling, conditioning, and motion-cache behavior
2026-05-08 14:04:09 +08:00
Bubbliiiing
0266bab98b
Update Model Group Offload and Readmes ( #487 )
2026-05-06 10:48:08 +08:00
Bubbliiiing
199a43b544
Update READMEs, add LongCatVideo multi-GPU inference, and fix import bugs ( #485 )
2026-04-24 15:54:22 +08:00
Bubbliiiing
34036517a8
Added LTX-2.3 support, optimized memory usage by casting e and e0 types in Wan-based models, and updated READMEs for image training and digital human models. ( #483 )
2026-04-16 20:45:16 +08:00
Bubbliiiing
54bf97ab66
Fix bug in FA3 and LTX2 && Update FA4 support && Update Infinitalk && Update MOVA && Update FlashHead ( #479 )
2026-04-07 14:08:39 +08:00
Bubbliiiing
4a86483cc2
Reformat S2V models && Update LTX-2 ( #476 )
2026-03-20 10:45:57 +08:00
Bubbliiiing
ad72867c0f
Fix Bug in Group Offload when diffusers version is low. ( #474 )
2026-03-10 15:02:16 +08:00
Bubbliiiing
5202421e7c
Update Z Image Turbo Control 2602 ( #460 )
2026-03-04 16:17:04 +08:00
Sense_wang and haosenwang1018
745acc1f47
Fix: Replace 74 bare excepts with except Exception ( #458 )
...
Co-authored-by: haosenwang1018 <haosenwang1018@users.noreply.github.com >
2026-02-26 16:24:51 +08:00
Bubbliiiing
a4b60f40bf
Update Z Image Control Tile ( #457 )
2026-02-25 11:12:57 +08:00
Bubbliiiing
7a085c9535
Update Longcat Avatar ( #453 )
2026-02-13 10:14:14 +08:00
Bubbliiiing
1ca4162447
Support validations in all models && Update Saving Code && Preparing Code ( #452 )
2026-02-10 17:23:23 +08:00
Bubbliiiing
ee44fbc950
Lora Loading Log and Z Image Distill ( #450 )
2026-02-04 16:55:24 +08:00
Bubbliiiing
a6b026526f
Update Qwen Image Layered, Turbowan Training Code and Z Image predict Code ( #448 )
2026-02-03 18:23:45 +08:00
Bubbliiiing
0f0e2bd5ab
Update Flux2 Control Cfg Distill && Fix Bug in Lora Training Register Hook ( #445 )
2026-02-03 10:23:10 +08:00
Bubbliiiing
0af07603da
Flux2 Comfyui Nodes ( #441 )
2026-01-26 20:00:36 +08:00
Bubbliiiing
7671af8b16
Update pyproject.toml ( #438 )
2026-01-20 22:32:05 +08:00
Bubbliiiing
95737c8f1d
Update Qwen Image Comfyui and pyproject.toml ( #437 )
2026-01-20 21:03:57 +08:00
Bubbliiiing
ac114cc142
Update Flux2 Training Code ( #436 )
2026-01-16 17:21:25 +08:00
Bubbliiiing
b534ebfef1
Update Z Image Control Distill Training Code and Update LogValidation in QwenImage and ZImage ( #435 )
2026-01-16 15:05:49 +08:00
Bubbliiiing
e9d5b09c92
Update Flux2 Fun Control Training ( #434 )
2026-01-15 14:04:59 +08:00
Bubbliiiing
a4783c4364
Qwen Image Fun Control Training and Qwen Image InstantX Controlnet Training and Inference ( #431 )
2026-01-14 15:07:54 +08:00
Bubbliiiing
5eb0c6862f
Update Z Image Control 2.1 Lite models ( #429 )
2026-01-12 21:04:35 +08:00