Hugging Face's logo

Spaces:
prashantgod
/
MultiPerson
Running on Zero

App Files Community
MultiPerson

Commit History

Remove generation_time_display component from examples
7b1f748

C4G-HKUST commited on

Ensure generation_time_display always has valid value to prevent JSON decode errors
b197409

C4G-HKUST commited on

Disable cache for gr.Examples to fix JSON decode error on repeated example clicks
62aa7d4

C4G-HKUST commited on

fix: debug
ae6ee70

C4G-HKUST commited on

Update GPU duration to 720s and 2p-2 generation time to ~11 minutes
a3f3eee

C4G-HKUST commited on

Add note about 40 denoising steps in generation time display
5440852

C4G-HKUST commited on

Fix JSON decode error: add generation_time_display to outputs to match inputs for cache compatibility
3049f55

C4G-HKUST commited on

Update GPU duration to 600 seconds (10 minutes)
60f55fe

C4G-HKUST commited on

Update GPU duration to 1800 seconds (30 minutes)
98ffd05

C4G-HKUST commited on

Update generation time estimates and GPU duration
26fd4c9

C4G-HKUST commited on

Fix examples: move generation time to second column and fix list index out of range error
e9633ab

C4G-HKUST commited on

fix: hf demo
b505615

C4G-HKUST commited on

Fix wav2vec model path to use Hugging Face model ID: facebook/wav2vec2-base-960h
b2737a3

C4G-HKUST commited on

Fix VAE scale tensor device mismatch: recreate scale list on GPU and move T5 encoder
c2db27b

C4G-HKUST commited on

Move models from CPU to GPU in worker process (like LivePortrait)
f2436d3

C4G-HKUST commited on

Simplify GPU handling following LivePortrait pattern: CPU in main process, GPU in worker via @spaces.GPU
7b63b72

C4G-HKUST commited on

Fix Stateless GPU environment: avoid CUDA init in main process, initialize GPU in worker process
f0617b0

C4G-HKUST commited on

Track GPU device during initialization and use same GPU in worker process and inference
3c322ce

C4G-HKUST commited on

Add GPU availability check in worker process for @spaces.GPU decorator
694fec8

C4G-HKUST commited on

Fix Gradio version and launch config: downgrade to 5.0.x, remove show_api parameter
5cb609b

C4G-HKUST commited on

Update: increase GPU duration to 360s, add gradio==5.42.0, update README
7569450

C4G-HKUST commited on

Use @spaces.GPU decorator for GPU management (reference LivePortrait)
f1ae228

C4G-HKUST commited on

Fix GPU detection and CPU fallback: remove ssr_mode, add runtime GPU check, support CPU mode for FaceInference
b7867cd

C4G-HKUST commited on

Fix CUDA device fallback in WanVAE and WanAF2V
7c629b9

C4G-HKUST commited on

Fix CUDA device access in T5EncoderModel and add GPU check
831eccf

C4G-HKUST commited on

Fix Gradio launch config for HF Spaces (remove no_proxy, use queue)
ef30698

C4G-HKUST commited on

Use flash_attn 2.7.4.post1 precompiled wheel (torch 2.6 compatible)
28f2de3

zzz66 commited on

Remove flash_attn (no precompiled wheel for torch 2.6)
bd2c73d

zzz66 commited on

Fix flash_attn wheel URL (cu122)
e7afc0e

zzz66 commited on

Use precompiled flash_attn wheel
96465d6

zzz66 commited on

Use preload_from_hub for models, only upload vocal_separator
63a1b7e

zzz66 commited on

Add YAML frontmatter for HF Space config
da470b8

zzz66 commited on

Initial commit with LFS
400a879

zzz66 commited on

initial commit
d5bbcc5
verified

zzz66 commited on