# `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 # No `gradio` or `spaces` pin here on purpose. Hugging Face appends its own # `gradio[oauth,mcp]==` and `spaces==` to the install command, and a # second pin for either one is a different version specifier for the same package, which # pip refuses to resolve: "Cannot install spaces==0.51.1 and spaces==0.51.3". The gradio # version comes from `sdk_version` in README.md instead. # 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 # CPU identity correction and atomic per-file LoRA preparation. opencv-python-headless>=4.10,<5 filelock # INT8 support; installed here because the Spaces dependency stage mounts only this file. # Quantization stays opt-in through H3_QUANTIZATION=int8. torchao==0.17.0