Spaces:

C4G-HKUST
/

AnyTalker

Running on Zero

App Files Files Community

83.5 MB

2 contributors

History: 21 commits

C4G-HKUST's picture

Fix VAE scale tensor device mismatch: recreate scale list on GPU and move T5 encoder

c2db27b 17 days ago

assets
Initial commit with LFS 17 days ago
checkpoints
Use preload_from_hub for models, only upload vocal_separator 17 days ago
input_example
Initial commit with LFS 17 days ago
utils
Fix GPU detection and CPU fallback: remove ssr_mode, add runtime GPU check, support CPU mode for FaceInference 17 days ago
wan
Fix Stateless GPU environment: avoid CUDA init in main process, initialize GPU in worker process 17 days ago
.gitattributes

1.77 kB

Initial commit with LFS 17 days ago
.gitignore

705 Bytes

Use preload_from_hub for models, only upload vocal_separator 17 days ago
LICENSE.txt

11.3 kB

Initial commit with LFS 17 days ago
README.md

10.7 kB

Update: increase GPU duration to 360s, add gradio==5.42.0, update README 17 days ago
app.py

35.6 kB

Fix VAE scale tensor device mismatch: recreate scale list on GPU and move T5 encoder 17 days ago
requirements.txt

847 Bytes

Fix Gradio version and launch config: downgrade to 5.0.x, remove show_api parameter 17 days ago