Image-Text-to-Video
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] - Notebooks
- Google Colab
- Kaggle
Commit ·
73372e6
1
Parent(s): ec19cc6
Scope the download command to the original checkpoint folders (#16)
Browse files- Scope the download command to the original checkpoint folders (9b40f3e632cfde4564aa4859d499b5862a679731)
- Link the diffusers documentation (83194394ab66c4e617251b5281d727a1ba47fb0e)
- Shorten the docs link text (71d6e6db54dcbd8c66c4679c90a0df33badfad2e)
- ComfyUI uses its own weights (2bc8c473e5c4c0fcf2e2a7a37bcdce7b072a48cc)
Co-authored-by: Apolinário from multimodal AI art <multimodalart@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -192,12 +192,18 @@ Each checkpoint is distributed as a self\-contained Hugging Face\-style reposito
|
|
| 192 |
└── audio_vae/
|
| 193 |
```
|
| 194 |
|
| 195 |
-
Download the model:
|
| 196 |
|
| 197 |
```bash
|
| 198 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 199 |
```
|
| 200 |
|
|
|
|
|
|
|
| 201 |
We recommend the following inference frameworks to serve the model:
|
| 202 |
|
| 203 |
- [SGLang](https://docs.sglang.io/) \- see [cookbook](https://docs.sglang.io/cookbook/diffusion/MiniMax/MiniMax-H3)
|
|
|
|
| 192 |
└── audio_vae/
|
| 193 |
```
|
| 194 |
|
| 195 |
+
Download the model. The repository hosts the original checkpoint (`FL2VA/`, `Ref2VA/`) and the diffusers format side by side, so scope the download to what your framework needs:
|
| 196 |
|
| 197 |
```bash
|
| 198 |
+
# Original checkpoint, both task families (SGLang, vLLM):
|
| 199 |
+
hf download MiniMaxAI/MiniMax-H3 --include "FL2VA/*" "Ref2VA/*" --local-dir MiniMax-H3
|
| 200 |
+
|
| 201 |
+
# Or a single task family:
|
| 202 |
+
hf download MiniMaxAI/MiniMax-H3 --include "FL2VA/*" --local-dir MiniMax-H3
|
| 203 |
```
|
| 204 |
|
| 205 |
+
diffusers users do not need a manual download: `ModularPipeline.from_pretrained("MiniMaxAI/MiniMax-H3")` fetches exactly the components it needs. See the [diffusers documentation](https://github.com/huggingface/diffusers/blob/minimax-h3/docs/source/en/api/pipelines/minimax_h3.md) for loading recipes.
|
| 206 |
+
|
| 207 |
We recommend the following inference frameworks to serve the model:
|
| 208 |
|
| 209 |
- [SGLang](https://docs.sglang.io/) \- see [cookbook](https://docs.sglang.io/cookbook/diffusion/MiniMax/MiniMax-H3)
|