InternLM/EndoCoT

Official implementation of "EndoCoT". Scaling endogenous Chain-of-Thought (CoT) reasoning in diffusion models for complex structured generation.

31
/ 100
Emerging

This project helps graphic designers, artists, and marketing professionals create complex images that require logical, step-by-step modifications. You provide a base image and a text instruction for modification, and it generates a new image by breaking down the instruction into transparent, intermediate reasoning steps, ensuring more accurate and structured visual output.

Use this if you need to generate images from complex text prompts that involve intricate details or multiple sequential changes, and you want transparency into how the AI arrived at the final image.

Not ideal if you primarily generate simple images from straightforward text prompts or don't require visibility into the AI's reasoning process.

generative-design digital-art image-editing creative-content-creation visual-marketing
No Package No Dependents
Maintenance 13 / 25
Adoption 7 / 25
Maturity 11 / 25
Community 0 / 25

How are scores calculated?

Stars

32

Forks

Language

Python

License

MIT

Last pushed

Mar 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/InternLM/EndoCoT"

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