Fooocus
Minimalist SD image tool — "Midjourney-style" out-of-the-box, zero learning curve
A minimalist Stable Diffusion image tool with "Midjourney-style" out-of-the-box usability and zero learning curve.
Open image generation models — from quick drafts to production art.
Key features
- Offline image generator needing no prompt tuning
- GPT-2 based prompt processing with automatic quality sampling
- Inpaint and outpaint, upscale and variation, image prompts
- First image in under 3 clicks; 4GB Nvidia VRAM minimum
Good for
- Beginners wanting Midjourney-like quality offline for free
- Users focused on prompts and images, not parameters
Stack & tags
Gradioimage-generationstable-diffusion-xlbeginner-friendlyofflinegradioopen-sourcetxt2img
Screenshots
Screenshots from the project’s GitHub README.
Similar open-source projects
stable-diffusion-webui
★ 165,985A1111 — once the most popular SD WebUI with the richest plugin ecosystem
ComfyUI
★ 135,608Node-based diffusion workflow UI — the de-facto standard for open-source AI art