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
|
@@ -27,3 +27,14 @@ Each one holds the Denoiser, Text Encoder, and VAE components packaged together
|
|
| 27 |
| INT8 | INT8 | INT8 | INT8 |
|
| 28 |
|
| 29 |
The VAE is shared between formats: FP4 reuses the FP8 file, INT4 reuses the INT8 file (FP4/INT4 packages in progress).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
| INT8 | INT8 | INT8 | INT8 |
|
| 28 |
|
| 29 |
The VAE is shared between formats: FP4 reuses the FP8 file, INT4 reuses the INT8 file (FP4/INT4 packages in progress).
|
| 30 |
+
|
| 31 |
+
## Recommended settings
|
| 32 |
+
|
| 33 |
+
Starting points (adjust to taste; see the source model card for authoritative values):
|
| 34 |
+
|
| 35 |
+
| Parameter | Value |
|
| 36 |
+
|---|---|
|
| 37 |
+
| Steps | 25 |
|
| 38 |
+
| CFG / Guidance scale | 7.0 |
|
| 39 |
+
| Resolution | 1024x1024 |
|
| 40 |
+
| Notes | Audio+video |
|