omerbt/MultiDiffusion

Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)

34
/ 100
Emerging

MultiDiffusion helps creative professionals like graphic designers, marketers, and artists generate high-quality images with precise control, without needing to retrain complex AI models. You provide text descriptions and optional spatial guides like segmentation masks or bounding boxes, and it outputs tailored, diverse images that adhere to your creative vision. This is perfect for anyone needing specific visual outcomes from text-to-image AI.

1,057 stars. No commits in the last 6 months.

Use this if you need to create custom images with fine-grained control over elements like aspect ratio (e.g., panoramas) or the placement of objects, using existing text-to-image models.

Not ideal if you're looking for simple, unconstrained image generation where specific spatial or structural control isn't a priority.

graphic-design digital-art marketing-content-creation visual-storytelling image-editing
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

1,057

Forks

64

Language

Jupyter Notebook

License

Last pushed

Sep 21, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/omerbt/MultiDiffusion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.