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
Commit History
Yesterday
-
README: fix hf download command dropping model_index.json
Verified signatureWith huggingface_hub >= 1.0, `--include` takes one pattern per flag. In `hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "FL2VA/*" "Ref2VA/*"`, only `model_index.json` goes to `--include`; the other two become positional file names, and the CLI warns "Ignoring `--include` since filenames have being explicitly set". The download then lacks the root `model_index.json`. Passing all patterns as positional arguments works on both 0.x and 1.x, since several positional names are used as allow patterns. Checked on huggingface_hub 1.17.0 with `--dry-run` (both families: 163 files including `model_index.json`; FL2VA only: 82 files) and on 0.35.3 with a small real download. Repeating `--include` per pattern would fix 1.x but keep only the last pattern on 0.x.9ad4876
3 days ago
-
Update README.md (#126)
- Update README.md (3562e14f5ae784735a528a79092b9839703d4499) Co-authored-by: Robbin <Peopleing@users.noreply.huggingface.co>0919fb6
-
Update README.md (#75)
- Update README.md (1fb42d0ef9f260ecc6ddb5a4520f6a137d185b41) Co-authored-by: Pierric Cistac <pierric@users.noreply.huggingface.co>42ed227
-
Update README.md
Verified signature939557d
-
Update README.md (#68)
- Update README.md (9fdb38451f4baf17604c69463aeff6b1c09b2e46) Co-authored-by: Val Alexander <BunsDev@users.noreply.huggingface.co>9ac0dd7
-
Update README.md
Verified signature6818f6c -
Update README.md
Verified signatured39e58c
-
Update README.md
Verified signaturebfc8ed0 -
use actual documentation links for diffusers (#52)
- use actual documentation links for diffusers (327170274665392b81db66e287ce20e192295e1e) Co-authored-by: Sayak Paul <sayakpaul@users.noreply.huggingface.co>a9e1d84 -
Update README.md
Verified signature3cee197 -
Update README.md
Verified signature6f65546 -
Update README.md
Verified signature31121b9 -
Update README.md
Verified signature40ce944 -
Update README.md
Verified signature66c0d01 -
Update docs/QA-about-License.md
Verified signaturece18b0e
-
Update README.md
Verified signatureb3c7290 -
Update README.md
Verified signature101ecd0 -
Make model_index the public entry
yuanhe83db0c0
-
Update README.md
Verified signaturefa9c8ab -
Remove unused assets
yuanheb8b09e3 -
Add repository model index for HF downloads
yuanhe48d93ed
-
Init MiniMaxAI/MiniMax-H3
Co-authored-by: multimodalart <multimodalart@users.noreply.huggingface.co> Co-authored-by: yuanhe <yuanhe@users.noreply.huggingface.co> Co-authored-by: RuggingHace <RuggingHace@users.noreply.huggingface.co> Co-authored-by: MiniMax-AI <MiniMax-AI@users.noreply.huggingface.co>5d9b308