Instructions to use Rin247/MiniMax-H3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Rin247/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("Rin247/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
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -34,14 +34,14 @@ The VAE is shared between formats: FP4 reuses the FP8 file, INT4 reuses the INT8
|
|
| 34 |
|
| 35 |
## Recommended settings
|
| 36 |
|
| 37 |
-
|
| 38 |
|
| 39 |
| Parameter | Value |
|
| 40 |
|---|---|
|
| 41 |
| Steps | 25 |
|
| 42 |
-
| CFG / Guidance scale |
|
| 43 |
-
| Resolution |
|
| 44 |
-
| Notes | Audio+video; prompt writing guides linked
|
| 45 |
|
| 46 |
## Example prompts
|
| 47 |
|
|
|
|
| 34 |
|
| 35 |
## Recommended settings
|
| 36 |
|
| 37 |
+
From the source model card (adjust to taste):
|
| 38 |
|
| 39 |
| Parameter | Value |
|
| 40 |
|---|---|
|
| 41 |
| Steps | 25 |
|
| 42 |
+
| CFG / Guidance scale | CFG-distilled (no CFG) |
|
| 43 |
+
| Resolution | 768p default (2K via regenerate) |
|
| 44 |
+
| Notes | Audio+video; prompt writing guides linked |
|
| 45 |
|
| 46 |
## Example prompts
|
| 47 |
|