jiuntian/interactdiffusion
[CVPR 2024] Official repo for "InteractDiffusion: Interaction-Control for Text-to-Image Diffusion Model".
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.
Stars
125
Forks
9
Language
Python
License
—
Category
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.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...