requirements.txt

# `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==0.40.0
torch==2.11.0
torchvision==0.26.0
# The Qwen3-VL processor decides the vision patch count, so a different minor changes the conditioning.
transformers==5.8.0
accelerate==1.14.0
# PEFT backs `load_lora_adapter` / `set_adapters` on the transformer (multi-LoRA blending).
peft>=0.15.0
# diffusers pins <2.
huggingface-hub==1.24.0
gradio==6.20.0
spaces>=0.51.1
scipy>=1.11.0
torchsde>=0.2.6
# 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 muxes the generated soundtrack onto the frames (`encode_video`).
opencv-python-headless
av
pillow
numpy
requests
safetensors>=0.8.0