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
Omni-Rewriter Replay: observe a clip into validated H3 PE (open harness)
#79
by Wayne-King - opened
We shipped an open prompt-expansion path on top of public MiniMax-H3.
omni-rewriter reconstruct watches a local clip, writes a validated H3 t2va prompt, then you can generate if you want. Public generate window is still integer 4β15s. This is not MiniMax software, and it is not a claim to reproduce private Context-IR.
Recommended Writer for the observe step: Qwen/Qwen3.6-35B-A3B.
- Gallery (Source vs Replay): https://huggingface.co/spaces/Wayne-King/omni-rewriter-replay
- PE JSON: https://huggingface.co/datasets/Wayne-King/omni-rewriter-pe-examples
- Code: https://github.com/WayneJin0918/Omni-Rewriter
- Collection: https://huggingface.co/collections/Wayne-King/omni-rewriter-replay-6a7e345df49af4cc12038cd0
If this is the wrong place for community tooling, happy to close it.