Spaces:
Running on Zero
Running on Zero
| # `diffusers` is installed from the canonical MiniMax-H3 pull request, | |
| # https://github.com/huggingface/diffusers/pull/14371 ("Minimax h3 follow up (review & refactor)"), pinned to a | |
| # **commit** rather than to its `minimax-h3-refactor` branch: the PR is a WIP and its head moves, and this Space's | |
| # blocks subclass its block classes. Re-pin — and re-check `h3_split_blocks.py` against the block names of the new | |
| # head — whenever the PR updates. | |
| # | |
| # 665f578278365ea4a3318cb8c9b66ce6c01204b9 = refs/pull/14371/head at the time of this deploy | |
| --extra-index-url https://download.pytorch.org/whl/cu130 | |
| diffusers @ git+https://github.com/huggingface/diffusers.git@665f578278365ea4a3318cb8c9b66ce6c01204b9 | |
| torch==2.11.0 | |
| torchvision==0.26.0 | |
| # A reference soundtrack that is not already at the audio VAE's 32 kHz is resampled with `torchaudio`; a 32 kHz one | |
| # skips the resample entirely, so this is easy to miss. | |
| torchaudio==2.11.0 | |
| # The Qwen3-VL processor decides the vision patch count, so a different minor changes the conditioning. | |
| transformers==5.8.0 | |
| accelerate==1.14.0 | |
| # diffusers pins <2. | |
| huggingface-hub==1.24.0 | |
| gradio==6.20.0 | |
| spaces==0.51.1 | |
| # No `kernels` pin on purpose: the Hub attention backends want `kernels>=0.12.3`, and that version breaks | |
| # transformers 5.8.0 at import. | |
| # PyAV decodes the reference media (`MiniMaxH3VideoReference.from_file`). | |
| av | |
| pillow | |
| peft | |
| numpy | |
| requests | |
| safetensors>=0.8.0 | |