nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[feat] FastVideo World Model Training (#1179)

Browse Source 
Co-authored-by: mignonjia <mhuo@ucsd.edu>
Co-authored-by: alexzms <3036648523@qq.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Kaiqin Kong
2026-05-11 05:13:12 +00:00
committed by GitHub
co-authored by mignonjia alexzms mergify[bot]
parent 636d3b743e
commit d6dfe95466
29 changed files with 4541 additions and 5143 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.agents/memory/codebase-map/README.md
+2 -1
View File
@@ -30,7 +30,8 @@ FastVideo-WorldModel/
│ │ │ ├── fine_tuning/ # FineTuneMethod, DiffusionForcingSFTMethod
│ │ │ └── distribution_matching/ # DMD2Method, SelfForcingMethod
│ │ ├── models/ # Per-role model wrappers (ModelBase, CausalModelBase)
│ │ │ └── wan/ # WanModel, WanCausalModel
│ │ │ ├── wan/ # WanModel, WanCausalModel
│ │ │ └── matrixgame/ # MatrixGameModel, MatrixGameCausalModel
│ │ ├── callbacks/ # Composable hooks (grad_clip, ema, validation)
│ │ └── utils/ # Config, builder, checkpoint, optimizer, tracking
│ ├── training/ # Legacy training infrastructure (being phased out)