j-min/IterInpaint

Code for IterInpaint model, presented in Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation (CVPR 2024 workshop)

15
/ 100
Experimental

This tool helps creative professionals or researchers generate images from scratch by precisely defining the placement and types of objects they want to see. You provide a 'layout' (like bounding boxes indicating where objects should go and what they are), and the system fills in those areas with detailed, coherent imagery. It's for anyone who needs to quickly prototype visual scenes or create specific image compositions without extensive manual editing.

No commits in the last 6 months.

Use this if you need to create images where you have a clear idea of object positions and categories, and want to generate visual content that adheres to that spatial blueprint.

Not ideal if you're looking for a simple text-to-image generator without specific spatial controls, or if you primarily want to edit existing images rather than generate new ones based on a layout.

generative-art visual-prototyping image-synthesis creative-design scene-composition
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

25

Forks

Language

Jupyter Notebook

License

Last pushed

Jul 21, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/j-min/IterInpaint"

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