mlx stable diffusion 3 medium
by argmaxinc
Open source · 12k downloads · 6 likes
1.1
(6 reviews)ImageAPI & LocalAbout
The *mlx stable diffusion 3 medium* model is an optimized version for Apple devices equipped with M1 chips or later, enabling high-quality image generation from text descriptions. It is based on the Stable Diffusion 3 architecture, delivering detailed renders, improved prompt comprehension, and enhanced visual consistency. Its primary use cases include artistic creation, visual prototyping, illustration, and generating images for creative or professional projects. This model stands out for its efficiency on Apple hardware, reducing resource requirements while maintaining performance comparable to the original versions. Its integration with DiffusionKit simplifies local deployment, ensuring a smooth and privacy-respecting experience.
Documentation
Stable Diffusion 3 Medium on DiffusionKit MLX!
Check out the original model!
Check out the DiffusionKit github repository!
Usage
-
Create conda environment
Shell
conda create -n diffusionkit python=3.11 -y
conda activate diffusionkit
pip install diffusionkit
-
Run the cli command
Shell
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 'SD3 on \
DiffusionKit' glowing softly. High detail hard surface render" \
--model-version argmaxinc/mlx-stable-diffusion-3-medium \
--height 768 \
--width 1360 \
--seed 1001 \
--step 50 \
--cfg 7 \
--output ~/Desktop/sd3_on_mac.png
Capabilities & Tags
diffusionkittext-to-imageimage-generationmlxen
Links & Resources