Views
No views yet
ok; provide a τ update (e.g. mud: -0.7; gravel: 0.6, or just ok) and
press Resumeimageio-ffmpeg, no system ffmpeg required)pip + a virtualenv1git clone https://huggingface.co/sattwik21/anytraverse-studio
2cd anytraverse-studiouv (recommended):uv syncpip:1python3 -m venv .venv
2source .venv/bin/activate # Windows: .venv\Scripts\activate
3pip install -r requirements.txtTorch pulls the wrong build, install the CUDA build explicitly, e.g.:1pip install torch --index-url https://download.pytorch.org/whl/cu128
2pip install torchvision --index-url https://download.pytorch.org/whl/cu128python app.pyshare=True is enabled
outside Hugging Face Spaces, Gradio will also print a temporary public share
link at startup — you can ignore it for local use..mp4, .mov, .avi).{} for default preferences, or enter e.g.
{"road": 1.0, "grass": 0.0, "bush": -0.8}.unknown_scene / unknown_object), type an operator
update in the box and press ✅ Apply & Resume.data/weights/ and the generated *.mp4 files are runtime artifacts; the
dashboard writes raw_opencv_temp.mp4 and anytraverse_h264_output.mp4 in
the working directory.