Instructions to use AX1Y2JP/MiniMax-H3-W4A8-ConvRot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AX1Y2JP/MiniMax-H3-W4A8-ConvRot with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AX1Y2JP/MiniMax-H3-W4A8-ConvRot", 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
Original model repository: https://huggingface.co/MiniMaxAI/MiniMax-H3
Example result on a 4070Ti:
Prerequisites & Installation
⚠️By applying this PR (Support asym w4a8_int #15308), the ComfyUI-W4A8 custom node becomes unnecessary.
This model requires a properly built Comfy-Kitchen branch (PR #90) and custom nodes from the ComfyUI-W4A8 folder.
Don't forget to initialize the submodule.
- Downloads last month
- -