Image-Text-to-Video
MiniMax H3
Diffusers
Safetensors
text-to-video
image-to-video
video-to-video
text-to-audio-video
image-to-audio-video
image-text-to-audio-video
video-to-audio-video
audio-to-audio-video
audio-video-generation
multimodal
synchronized-audio-video
reference-to-audio-video
Instructions to use MiniMaxAI/MiniMax-H3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use MiniMaxAI/MiniMax-H3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MiniMaxAI/MiniMax-H3", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
Free one-click Mac app for MiniMax H3 (h3.c, Apple Silicon, no ComfyUI)
#118
by UnifiedForge - opened
For Mac users who’d rather not set up ComfyUI: we made a small open-source app around antirez’s h3.c that handles the first run — builds the engine, walks you through accepting this license and creating a HF token, downloads the weights (~210 GB for FL2VA + Ref2VA), then opens a simple local UI (presets, first/last frame, reference images, history). For smaller Macs it has a low-memory mode via h3’s --ssd-streaming (≈11 GB vs ≈20 GB peak at 576×1024, 5 s).
https://github.com/UnifiedForge/minimax-h3-lite
You still download the weights yourself and accept MiniMax’s license — please check it allows use in your region.
