Vibe Coding DiscoverFooocus
View on GitHubFocus on prompting and generating
Fooocus is an offline, open-source SDXL image generator with a Gradio UI that removes most manual parameter tuning: you focus on prompt and image. It bundles a GPT-2 prompt engine, own inpaint/image-prompt algorithms, presets, LoRA and upscaling; runs on ~4GB VRAM. Now LTS/bug-fix only.
Use Cases
Local offline text-to-image generationInpainting and outpainting imagesImage upscaling and variationImage-prompt and face swap workflowsApplying LoRA styles to generationsAnime and realistic preset image generationMidjourney-style prompting without parameter tuningBatch image generation with negative prompts and aspect ratios
Built With
- Language
- Python
- Frameworks
- Gradio · PyTorch · Diffusers · Stable Diffusion XL · ControlNet · IP-Adapter · InsightFace · safetensors · LCM
Tags
stable-diffusion-xl · text-to-image · image-generation · gradio · inpainting · outpainting · image-prompt · face-swap · upscaling · lora · offline · diffusion · anime · presets · local-inference · prompt-engineering