Will Lin
3572c6821e
move tests
2026-01-21 14:09:58 -08:00
Will Lin
deb901f6fc
cleanup
2026-01-21 14:09:40 -08:00
Will Lin
beae2943cf
cleanup
2026-01-21 13:28:43 -08:00
Will Lin
fadb71bb64
fix
2026-01-20 18:45:26 -08:00
Shao Duan
65c6fbaa46
Use PyAV for audio muxing instead of ffmpeg CLI
...
Replace ffmpeg subprocess call with PyAV library for muxing audio
into video files. PyAV bundles FFmpeg libraries, so users no longer
need ffmpeg CLI installed separately.
2026-01-20 21:32:47 +00:00
Shao Duan
e32a8a9504
added tiling to ltx vae, simplified example for ltx2
2026-01-20 08:32:06 +00:00
Shao Duan
6907d87871
cleanup
2026-01-20 08:32:06 +00:00
Shao Duan
9775fed31a
Implement native LTX2 Video and Audio VAEs
2026-01-20 08:32:06 +00:00
Shao Duan
5c6f635d73
Use LTX2 config defaults and HF model ID
2026-01-20 08:32:06 +00:00
Shao Duan
c19708fd58
Fix test_ltx2_audio imports and use consistent attention backend
2026-01-20 08:32:06 +00:00
Shao Duan
b2e4fb0743
Use HuggingFace model path for LTX2 examples and CI tests
2026-01-20 08:32:06 +00:00
Shao Duan
a3ad4852b0
Fix yapf formatting
2026-01-20 08:32:06 +00:00
Shao Duan
add2be21b5
Fix missing LTX2 exports and add layerwise offload compatibility
...
- Restore LTX2VideoConfig and add to dits __init__
- Add LTX2VAEConfig export to vaes __init__
- Add LTX2Transformer3DModel and CausalVideoAutoencoder to model registry
- Add compatibility check for layerwise offload (skip for models without nn.ModuleList)
2026-01-20 08:32:06 +00:00
Shao Duan
41203d92b8
Fix pre-commit issues and code cleanup
...
- Fix ruff SIM102 errors in ltx2_denoising.py (combine nested if statements)
- Remove exit() call from create_hf_repo.py
- Remove global torch.backends.cuda settings from gemma.py property
- Apply yapf formatting fixes
2026-01-20 08:32:06 +00:00
Shao Duan
5fa8415c0b
Remove development markdown files
2026-01-20 08:32:06 +00:00
Shao Duan
3a182925f3
Fix LTX2 distilled to skip CFG with guidance_scale=1.0
2026-01-20 08:32:06 +00:00
Shao Duan
c1e4787775
Added audio to ltx2 and fixed issue with sigma values and encoder alignment ( #1004 )
2026-01-20 08:32:06 +00:00
Will Lin
2c6bf47b9f
update
2026-01-20 08:32:06 +00:00
Will Lin
548cc08817
working
2026-01-20 08:32:06 +00:00
Will Lin
7521b06693
update
2026-01-20 08:32:06 +00:00
Will Lin
fb9ad77086
encoder
2026-01-20 08:32:06 +00:00
alexzms and William Lin
31f44110b5
[kernel] [bugfix] [ci] bump v0.2.4. Fix STA output handling, TurboDiffusion CUDA norm dtypes for fastvideo-kernel unit tests. ( #1020 )
...
Co-authored-by: William Lin <SolitaryThinker@users.noreply.github.com >
2026-01-19 17:42:42 -08:00
William Lin
21f3ce6577
[kernel] Fix fastvideo-kernel release workflow ( #1019 )
2026-01-17 15:57:46 -08:00
XOR-op
785d123e36
[feat] Hooks API and layerwise offloading for all DiTs ( #1006 )
2026-01-17 11:22:02 -08:00
William Lin
d58c551c11
[chore] release fastvideo-kernel 0.2.3 ( #1018 )
2026-01-17 02:24:23 -08:00
alexzms
560628709c
[Bug Fix] Add autograd wrapper for block-sparse attention in fastvideo-kernel + fix CMake extension linking ( #1015 )
2026-01-16 21:16:43 -08:00
William Lin
0f53b51e6c
[CI] Fix OOM issues in ssim tests ( #1011 )
2026-01-16 21:15:20 -08:00
alexzms and Will Lin
06093a9c4e
[CI] SSIM tests optimization: load all model weights from Modal persistent Volume ( #958 )
...
Co-authored-by: Will Lin <wlsaidhi@gmail.com >
2026-01-16 11:50:43 -08:00
KyleShao
dbddfab6d2
[feat] Introduce Cosmos 2.5 Text2World pipeline ( #974 )
2026-01-15 15:09:05 -08:00
William Lin
7188170277
[misc] [bugfix] unpin 'av' in pyproject ( #1009 )
2026-01-13 15:40:46 -08:00
XOR-op
b7f69c2c1d
[feat!] Disable FSDP inference by default ( #1001 )
2026-01-13 14:20:05 -08:00
Loay Rashid
23a4531491
[CI] Fixed Turbodiffusion I2V CI ( #1002 )
2026-01-13 01:08:58 -08:00
William Lin and gemini-code-assist[bot]
7d52ad0118
[ci] temporarily disable turbodiffusion ssim test ( #1000 )
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-08 15:43:50 -08:00
Will Lin
4d7bf35fa3
Revert "dit"
...
This reverts commit a6a9c9ca07
2026-01-07 03:22:48 -08:00
Will Lin
a6a9c9ca07
dit
2026-01-07 03:18:48 -08:00
f4704847c2
[bugfix] Add configs for TurboDiffusion T2V/I2V models ( #993 )
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Will Lin <wlsaidhi@gmail.com >
2026-01-06 16:36:45 -06:00
Shreejith SG and Will Lin
d9c996310b
[docs]: add LoRA extraction utilities documentation ( #992 )
...
Co-authored-by: Will Lin <wlsaidhi@gmail.com >
2026-01-06 16:36:26 -06:00
Shao Duan
d6651afd2e
[examples] Added longcat-video python api examples ( #994 )
2026-01-06 15:03:42 -06:00
William Lin
cf67618cad
[chore] release 0.1.7 (real) ( #980 )
2026-01-05 15:47:05 -06:00
William Lin
2f0a2b3c57
[misc] add pin_cpu_memory false for RTX 4090 ( #990 )
2026-01-05 15:45:35 -06:00
Loay Rashid
e7748d9952
[feat] add Turbodiffusion I2V pipeline ( #984 )
2026-01-05 15:41:23 -06:00
William Lin
8eb3140b2f
[misc] pin fastvideo-kernel in .toml file ( #989 )
2026-01-05 13:42:32 -06:00
Shao Duan
d6ddcea682
Add LongCat-Video I2V and Video Continuation (Base, Distillation and Refinement) Support to FastVideo ( #953 )
2026-01-04 22:20:09 -06:00
William Lin
3559ba2377
[chore] update wechat QR code ( #988 )
2026-01-04 21:59:38 -06:00
William Lin
61e63ea0d7
[chore] release fastvideo-kernel 0.2.2 ( #986 )
2026-01-04 21:21:06 -06:00
William Lin
4ce4ac4734
[ci] increase ssim and lora inference test timeout ( #985 )
2026-01-04 15:08:20 -06:00
William Lin
e7f6db9bd1
[docs] Update docs and README ( #975 )
2026-01-04 14:59:19 -06:00
Ohm-Rishabh
d83f45a6a0
Layer offloading ( #966 )
2026-01-03 21:46:00 -08:00
XOR-op
dd91542cd1
[feat] Support text encoder weight override and quantization ( #983 )
2026-01-03 15:33:33 -06:00
Kaiqin Kong
581e8115fe
[feat] support Matrix-Game 2.0 streaming generation ( #957 )
2026-01-02 19:14:38 -06:00
Will Lin