Auto-detect available ffmpeg codec (libx264/libopenh264/mpeg4 fallback)

Remove -crf and complex vf filter - use simple -pix_fmt yuv420p

Fix ffmpeg: use shell=True, reorder -crf option

Fix ffmpeg: use subprocess.run with error checking, absolute temp path

Add debug listing to download endpoint

Add custom /api/download endpoint to bypass Gradio file serving 403

Add debug logging for file access

Debug: allowed_paths=['/'] + logging

Add allowed_paths /tmp for file serving

Set GRADIO_TEMP_DIR=/tmp for file serving

Save results to Gradio cache dir for proper file serving

Save results to temp dir for Gradio 5 file serving

Fix allowed_paths with absolute path for results directory

Add allowed_paths for results directory

fix: use direct paste-back instead of get_image (requires face parsing model we don't init)

fix: use proper tensor dtype conversion in inference loop (FloatTensor fails on CUDA half tensors)

Fix gradio_client schema bug + update app

fix: correct get_whisper_chunk parameter order (device was getting librosa_length)

fix: update model loading API

fix: revert to eager model loading — L4 GPU loads models fast, deferred loading caused inference errors

fix: COPY app.py into Docker image (was using GitHub clone, not our custom version)

fix: defer model loading to first inference — unblocks Gradio startup

fix: simplify entrypoint — models pre-downloaded in Docker image

fix: download models at Docker build time to avoid 30-min startup timeout

fix: re-add SyncNet download (required by MuseTalk)

fix: remove debug=True from launch

fix: parallelize model downloads to fit 30-min startup window

fix: add download retry, validate models, use exec for clean process mgmt

fix: resolve NameError, align model paths to models/, remove @spaces.GPU

fix: download diffusion_pytorch_model.safetensors for SD VAE

fix: pin gdown<5.0 to fix missing gdown.cli module

Fix: pin huggingface_hub<1.0 to fix CLI import error

Fix: COPY --chown=user:user so chmod +x succeeds

Fix: chmod +x entrypoint.sh after COPY to fix permission denied

Fix Dockerfile: COPY entrypoint.sh into container for model downloads

Fix entrypoint: download model weights before starting app

Fix: download model weights at startup

Update packages.txt

Update requirements.txt

Update requirements.txt

Update requirements.txt

Update requirements.txt

Update Dockerfile

Upload install_ffmpeg.sh

Update packages.txt

Update packages.txt

Update packages.txt

Update packages.txt

Update packages.txt

Update requirements.txt