Text-to-Image
Diffusers
Safetensors
MiniMax H3
English
orbitquant
w4a8
4-bit precision
gptq
quantized
image-editing
Instructions to use WaveCut/MiniMax-H3-Image-OrbitQuant-W4A8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/MiniMax-H3-Image-OrbitQuant-W4A8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("WaveCut/MiniMax-H3-Image-OrbitQuant-W4A8", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
Download transformer/modulation.json from WaveCut/MiniMax-H3-Image-OrbitQuant-W4A8: direct link, hf CLI and curl.
- Browser
- Download file 342 Bytes
-
https://huggingface.co/WaveCut/MiniMax-H3-Image-OrbitQuant-W4A8/resolve/main/transformer/modulation.json
- Command line
-
hf download hf://WaveCut/MiniMax-H3-Image-OrbitQuant-W4A8/transformer/modulation.json
-
curl -L -o modulation.json https://huggingface.co/WaveCut/MiniMax-H3-Image-OrbitQuant-W4A8/resolve/main/transformer/modulation.json
342 Bytes
| { | |
| "timesteps": [ | |
| 0.0, | |
| 0.03247630596160889, | |
| 0.11245149374008179, | |
| 0.25, | |
| 0.4672260880470276, | |
| 0.7679911255836487, | |
| 0.9990000128746033 | |
| ], | |
| "note": "AdaLN modulation of every block and of the output norm, precomputed for these timesteps from the BF16 weights; the AdaLN projections and the timestep MLP are not in this checkpoint." | |
| } |