Fooocus

Converts text prompts into images offline using Stable Diffusion XL, requiring minimal manual parameter configuration to produce results

It takes care to curate a safe software space. Help us do more.

&

+
Offline Generation
free
Runs entirely on local hardware once models are downloaded, without needing an internet connection to generate images.
+
Prompt Expansion
free
Uses an offline GPT-2-based engine to automatically add detail to short or long prompts before generation.
+
Inpaint and Outpaint
free
Edits or extends parts of an existing image using the project’s own inpaint algorithm and models.
+
Image Prompt
free
Guides generation using a reference image through a proprietary image-prompt algorithm rather than standard IP-Adapter methods.
+
Face Swap
free
Replaces faces in generated or input images using InsightFace-based detection.
+
Preset Editions
free
Switches between General, Anime, and Realistic model presets from separate launchers or an in-browser selector.
+
Wildcards
free
Substitutes a random line from a text file into a prompt at generation time, based on the seed.
+
Array Processing
free
Generates one image per value listed in bracketed prompt syntax, producing several variants from a single prompt.
+
Inline LoRA
free
Applies a LoRA model directly from prompt text without a separate configuration step.
...5 more features/limitations. Contact us to get a complete list of features and system requirements.

Platform

Desktop
Software

Social

System Requirements

#Minimum
1
Windows
2
  • 8GB
  • 32GB CPU-only mode (~17x slower)
3
40GB free space
4
  • Nvidia GTX 9XX/10XX, 8GB VRAM
  • Nvidia RTX 2XXX/3XXX/4XXX, 4GB VRAM
  • AMD GPU, 8GB VRAM, Slow compared to Nvidia
5
Requires System Swap enabled.
#Minimum
1
Linux
2
  • 8GB
  • 32GB CPU-only mode (~17x slower)
3
40GB free space
4
  • Nvidia GTX 9XX/10XX, 8GB VRAM
  • Nvidia RTX 2XXX/3XXX/4XXX, 4GB VRAM
  • AMD GPU, 8GB VRAM, Slow compared to Nvidia
5
Requires System Swap enabled.
#Minimum
1
macOS Catalina or newer
2
Apple Silicon (M1/M2)
3
Apple M1/M2 via PyTorch MPS, shared system memory
4
~9x slower than Nvidia

Ratings

Not available, but we appreciate help! You can help us improve this page by contacting us.

Developer

Written in

Python, JavaScript

Initial Release

2023-08-11

Repository

License

Categories


Notes

  • The developers warn of numerous fake websites impersonating the project (including fooocus[dot]com, fooocus[dot]net, fooocus[dot]co, fooocus[dot]ai, fooocus[dot]org, fooocus[dot]pro, and fooocus[dot]one); the only official source is the GitHub repository linked above.
  • The project is in a state of Limited Long-Term Support (LTS): the developers state there are no current plans to adopt newer model architectures, and updates are now limited to bug fixes.