Instructions to use argmaxinc/mlx-FLUX.1-schnell with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- DiffusionKit
How to use argmaxinc/mlx-FLUX.1-schnell with DiffusionKit:
# Pipeline for Flux from diffusionkit.mlx import FluxPipeline pipeline = FluxPipeline( shift=1.0, model_version=argmaxinc/mlx-FLUX.1-schnell, low_memory_mode=True, a16=True, w16=True, )
# Image Generation HEIGHT = 512 WIDTH = 512 NUM_STEPS = 4 CFG_WEIGHT = 0 image, _ = pipeline.generate_image( "a photo of a cat", cfg_weight=CFG_WEIGHT, num_steps=NUM_STEPS, latent_size=(HEIGHT // 8, WIDTH // 8), )
- MLX
How to use argmaxinc/mlx-FLUX.1-schnell with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir mlx-FLUX.1-schnell argmaxinc/mlx-FLUX.1-schnell
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Tag repo as `diffusionkit`
#2
by Wauplin HF Staff - opened
Related to PR https://github.com/huggingface/huggingface.js/pull/869. It will ensure the repo is recognized as a diffusionkit library in addition to mlx once #869 will be merged and deployed.
Would be good to update model cards in the same way for all models from the DiffusionKit collection.
LGTM!
ZachNagengast changed pull request status to merged