How to use argmaxinc/mlx-FLUX.1-schnell-4bit-quantized with DiffusionKit:
# Pipeline for Flux from diffusionkit.mlx import FluxPipeline pipeline = FluxPipeline( shift=1.0, model_version=argmaxinc/mlx-FLUX.1-schnell-4bit-quantized, 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), )
How to use argmaxinc/mlx-FLUX.1-schnell-4bit-quantized with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir mlx-FLUX.1-schnell-4bit-quantized argmaxinc/mlx-FLUX.1-schnell-4bit-quantized
how to use comfyui?
Here is a community-driven port to ComfyUI: https://github.com/thoddnn/ComfyUI-MLX
· Sign up or log in to comment
