shaoxiongduan
ac919b1c87
[feat] WanTrack: OpenVid preprocess + Wan2.2 synthetic-gen pipeline, training configs, first-frame saturation fix
...
- data_pipeline: SAM+CoTracker preprocessing, sharded Slurm launchers, OpenVid download/filter,
and a data-parallel Wan2.2-T2V-A14B synthetic video generator with the first-frame
over-brightness fix (over-generate 129 -> drop first 8 -> keep 121).
- examples/train: OpenVid bidir/stage2/stage3 launchers + finetune YAMLs (sparse, merged,
merged_bias, stage2v2 hi-lr, stage3A/B/C).
- research_log: first-frame saturation root-cause writeup (DiT position-0 latent, not VAE decode).
- fastvideo: trackwan model / track-encoder / preprocessing updates, dcp_to_diffusers export, FA4.
2026-07-14 08:58:22 +00:00
shaoxiongduan
7349e07cec
[feat] WanTrack: Fun-Control init to break the track-encoder deadlock
...
Initialize the 52ch TrackWan from Wan2.1-Fun-1.3B-Control so the track-slot
patch-embed channels start from Fun-Control's PRETRAINED control channels
(non-zero). Combined with the zero-init track head this gives step-0 == teacher
while still letting gradient reach the track encoder -- avoiding the double
zero-init deadlock of the from-scratch Fun-InP path (where both the track
patch-embed channels and the track-head proj are zero, so the track pathway
never trains). Adds the converter, the matching track_config channel handling,
and the InP init updates.
2026-07-01 06:36:42 +00:00
d922ab2cbc
[model] Flux2 Klein Port ( #1349 )
...
Co-authored-by: Gnav3852 <63612880+Gnav3852@users.noreply.github.com >
Co-authored-by: Mac Lee <macthecadillac@gmail.com >
2026-06-09 14:55:55 -07:00
William Lin
3fb2fbe1a2
[infra]: MagiHuman checkpoint conversion + push scripts (7/8) ( #1301 )
2026-05-12 15:45:15 -07:00
William Lin
140bd1a6cf
[misc]: standardize install instructions on uv pip install ( #1279 )
2026-05-02 12:45:50 -07:00
William Lin
c85f6a477f
[docs] add hierarchical AGENTS.md per-directory guidance ( #1278 )
2026-05-02 03:28:18 -07:00
William Lin
c77a76c6af
[feat] Stable Audio Open 1.0: T2A + A2A + RePaint inpainting (native) ( #1260 )
2026-05-01 00:07:11 -07:00
vishruthb
5789955bbe
[feat] add gen3c (cosmos-7b) model and pipeline support ( #1059 )
2026-04-01 11:42:02 +00:00
Mihir Jagtap
7a83e0e6fc
[feature] Add Hunyuan-GameCraft model support ( #1071 )
2026-02-14 08:07:44 +08:00
ad58f802f3
[Feat] Port LTX2 trainer ( #1074 )
...
Co-authored-by: Davids048 <jundasu@ucsd.edu >
Co-authored-by: Matthew Noto <99706358+RandNMR73@users.noreply.github.com >
2026-02-09 17:32:57 -08:00
Shao Duan and Will Lin
029216029f
Added LTX-2 Distilled T2V Generation ( #1016 )
...
Co-authored-by: Will Lin <wlsaidhi@gmail.com >
2026-01-21 14:11:39 -08:00
KyleShao
dbddfab6d2
[feat] Introduce Cosmos 2.5 Text2World pipeline ( #974 )
2026-01-15 15:09:05 -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
Loay Rashid
e7748d9952
[feat] add Turbodiffusion I2V pipeline ( #984 )
2026-01-05 15:41:23 -06:00
Loay Rashid
dea69cf651
[New Model] Turbodiffusion ( #971 )
2026-01-02 17:55:56 -06:00
William Lin
704bc9aaf9
[misc] Add util script to create diffuser HF repo from custom component weights ( #970 )
2025-12-29 19:38:30 -06:00
alexzms and Shao Duan
8f1e6c3336
Add LongCat T2V (Base, Distillation and Refinement) Support to FastVideo ( #883 )
...
Co-authored-by: Shao Duan <shaoxiongduan@gmail.com >
2025-12-23 01:11:18 -06:00
Wei Zhou and SolitaryThinker
ce67cd3729
[Feat] Support Self-Forcing's Causal Inference for Wan2.1 T2V 1.3B ( #766 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2025-08-28 16:47:49 -07:00
shaoxiongduan