jiuntian/interactdiffusion

[CVPR 2024] Official repo for "InteractDiffusion: Interaction-Control for Text-to-Image Diffusion Model".

31
/ 100
Emerging

This tool helps digital artists, designers, and content creators generate images where objects interact precisely as intended. You provide a text prompt describing your scene and specify the subjects, objects, their actions, and exact locations using bounding boxes. The output is a highly controlled image reflecting these specific interactions, eliminating the randomness often found in standard text-to-image models.

125 stars. No commits in the last 6 months.

Use this if you need fine-grained control over how different elements in your AI-generated images interact with each other, such as 'a person feeding a cat' where you define the specific areas for the person and the cat.

Not ideal if you prefer broad creative exploration without precise control over object placement or interaction, or if you're looking for a simple, single-prompt image generation tool.

AI art generation digital design creative content image manipulation visual storytelling
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

125

Forks

9

Language

Python

License

Last pushed

Jun 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/jiuntian/interactdiffusion"

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