EnergyAttention/Energy-Based-CrossAttention

The official repository of "Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models".

28
/ 100
Experimental

This project helps graphic designers and artists refine images generated by AI. By inputting a text description and an image (either newly generated or an existing photo), you can guide the AI to make specific edits or combine different concepts in the final output. It's for anyone using text-to-image diffusion models who needs more precise control over the generated content.

No commits in the last 6 months.

Use this if you are using AI to generate or modify images and find that the output sometimes doesn't quite match your textual description or if you want to combine multiple ideas into one image.

Not ideal if you are looking for a simple, one-click image generation tool without needing fine-grained control over the AI's interpretation of your prompts.

AI-art image-editing generative-design text-to-image digital-creation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

51

Forks

6

Language

Python

License

Last pushed

Apr 01, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/EnergyAttention/Energy-Based-CrossAttention"

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