# `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
#
# Nothing is quantized in this deployment, so there is no `torchao`.
--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`, which is the
# only thing in the `ref2va` path that needs it — and it is easy to miss, because a 32 kHz reference skips the
# resample entirely. Both halves need it: the conditioner's `setup` step normalizes the same waveforms this one does.
torchaudio==2.11.0
# Pinned to the version the MiniMax-H3 parity work was verified against: 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; 1.24.0 is the version the parity work ran on.
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: decoding the reference media, i.e. `MiniMaxH3VideoReference.from_file` / `MiniMaxH3AudioReference.from_file`.
av
pillow
numpy
requests
safetensors>=0.8.0