CVL-UESTC/Internal-Guidance

CVPR 2026-Guiding a Diffusion Transformer with the Internal Dynamics of Itself (IG)

36
/ 100
Emerging

This project helps researchers and practitioners in generative AI create highly realistic images from scratch, particularly for large datasets like ImageNet. By providing a guidance mechanism for Diffusion Transformers, it enables faster training and improved image quality. The primary user would be an AI/ML researcher or practitioner focused on advancing state-of-the-art image generation models.

Use this if you are developing or training diffusion models and need to achieve state-of-the-art image generation quality with improved training efficiency.

Not ideal if you are looking for an off-the-shelf image generation tool for end-user applications rather than a research framework.

generative-AI image-synthesis deep-learning-research computer-vision diffusion-models
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 13 / 25
Community 5 / 25

How are scores calculated?

Stars

60

Forks

2

Language

Python

License

MIT

Last pushed

Feb 26, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/CVL-UESTC/Internal-Guidance"

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