bloc97/CrossAttentionControl

Unofficial implementation of "Prompt-to-Prompt Image Editing with Cross Attention Control" with Stable Diffusion

42
/ 100
Emerging

This tool helps artists and designers precisely edit images generated by Stable Diffusion. By modifying the text prompts, you can change specific elements like objects, styles, or even seasons within an image, without needing to manually mask areas. It takes an initial text prompt and a desired modification, producing a new, subtly altered image that retains the original composition.

1,344 stars. No commits in the last 6 months.

Use this if you need fine-grained control over AI-generated images, allowing you to iterate on concepts by making targeted changes to prompts while preserving the overall structure.

Not ideal if you're looking to generate entirely new images from scratch or perform broad, uncontrolled style transfers that don't prioritize maintaining the original image's elements.

AI art image generation digital design creative editing prompt engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

1,344

Forks

87

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 18, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/bloc97/CrossAttentionControl"

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