Image Generation
Collection
Models, datasets and evaluations results for DiffusionKit: https://github.com/argmaxinc/DiffusionKit • 8 items • Updated • 7
# 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),
)FLUX.1-schnell on DiffusionKit MLX!
Check out the original model!
Check out the DiffusionKit github repository!
![FLUX.1 [schnell] Grid](/argmaxinc/mlx-FLUX.1-schnell-4bit-quantized/blob/main/flux_on_mac.png)
Note: This checkpoint features 4-bit quantization of the mmdit module using MLX's nn.quantize function with default settings (group_size=64).
Usage
conda create -n diffusionkit python=3.11 -y
conda activate diffusionkit
pip install diffusionkit
diffusionkit-cli --prompt "detailed cinematic dof render of a \
detailed MacBook Pro on a wooden desk in a dim room with items \
around, messy dirty room. On the screen are the letters 'FLUX on \
DiffusionKit' glowing softly. High detail hard surface render" \
--model-version argmaxinc/mlx-FLUX.1-schnell-4bit-quantized \
--height 768 \
--width 1360 \
--seed 1001 \
--step 4 \
--output ~/Desktop/flux_on_mac.png
- Downloads last month
- 10,646
Hardware compatibility
Log In to add your hardware
Quantized
# 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, )