QY-H00/attention-interpolation-diffusion

[NeurIPS 2024] Official Implementation of Attention Interpolation of Text-to-Image Diffusion

26
/ 100
Experimental

This project helps artists, designers, and marketers create smooth, consistent visual transitions and compositions using AI. It takes two different images or text descriptions as input and generates a seamless sequence of images that gradually transform from one to the other, offering control over the creative process. It's ideal for anyone needing to generate a series of visually related images or blend concepts smoothly.

108 stars. No commits in the last 6 months.

Use this if you need to generate a series of images that smoothly transition between two distinct concepts, styles, or subjects, or combine elements from multiple prompts into a single image.

Not ideal if you're looking for a simple, one-off image generation from a single prompt without any need for interpolation, morphing, or fine-grained control over transitions.

generative-art digital-design visual-storytelling image-editing content-creation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

108

Forks

6

Language

Jupyter Notebook

License

Last pushed

Nov 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/QY-H00/attention-interpolation-diffusion"

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