Image-Text-to-Video
MiniMax H3
Diffusers
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 drawthingsai/MiniMax-H3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use drawthingsai/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("drawthingsai/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] - Notebooks
- Google Colab
- Kaggle
Download .gitattributes from drawthingsai/MiniMax-H3: direct link, hf CLI and curl.
- Browser
- Download file 622 Bytes
-
https://huggingface.co/drawthingsai/MiniMax-H3/resolve/main/.gitattributes
- Command line
-
hf download hf://drawthingsai/MiniMax-H3/.gitattributes
-
curl -L -o .gitattributes https://huggingface.co/drawthingsai/MiniMax-H3/resolve/main/.gitattributes
622 Bytes
| minimax_h3_vae_f16.ckpt filter=lfs diff=lfs merge=lfs -text | |
| qwen_3_vl_32b_50_i8x.ckpt filter=lfs diff=lfs merge=lfs -text | |
| minimax_h3_fl2va_i6x.ckpt filter=lfs diff=lfs merge=lfs -text | |
| minimax_h3_fl2va_i8x.ckpt filter=lfs diff=lfs merge=lfs -text | |
| minimax_h3_fl2va_q6p.ckpt filter=lfs diff=lfs merge=lfs -text | |
| minimax_h3_ref2va_i6x.ckpt filter=lfs diff=lfs merge=lfs -text | |
| minimax_h3_ref2va_i8x.ckpt filter=lfs diff=lfs merge=lfs -text | |
| minimax_h3_ref2va_q6p.ckpt filter=lfs diff=lfs merge=lfs -text | |
| minimax_h3_ref2va_q8p.ckpt filter=lfs diff=lfs merge=lfs -text | |
| minimax_h3_fl2va_q8p.ckpt filter=lfs diff=lfs merge=lfs -text | |