HolmesShuan/Zero-shot-Style-Transfer-via-Attention-Rearrangement

[CVPR2024] Official implementation of the paper "Z∗: Zero-shot Style Transfer via Attention Rearrangement" a.k.a. "Z∗: Zero-shot Style Transfer via Attention Reweighting"

31
/ 100
Emerging

This project helps graphic designers and artists transform the visual style of an image without needing to train a special model first. You provide a content image (what you want to stylize) and a style image (the look you want to apply), and it generates a new image with the content of the first and the style of the second. It's ideal for anyone creating visual content who wants to quickly experiment with different artistic styles.

No commits in the last 6 months.

Use this if you need to apply a new artistic style to an image instantly, without any setup or training for each new style.

Not ideal if you need fine-grained control over specific stylistic elements beyond what a general diffusion model can provide, or if you don't have access to the necessary computational resources for running image generation models.

graphic-design digital-art image-editing visual-content-creation creative-workflows
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

97

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Sep 29, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/HolmesShuan/Zero-shot-Style-Transfer-via-Attention-Rearrangement"

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