Correr-Zhou/MagicTailor

[IJCAI 2025 (Oral)] Offical implementation of the paper "MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models".

41
/ 100
Emerging

This tool helps designers, artists, and marketers create highly specific images from text descriptions by letting them personalize individual parts of a subject. You provide example images of a subject (like a person) and a specific component (like a hairstyle), and the tool generates new images that incorporate both elements with fine-grained control over the component. This is ideal for anyone needing to generate unique visual content that combines established concepts with custom details.

100 stars.

Use this if you need to generate images where you can precisely control specific visual components within a larger concept, such as putting a custom hairstyle on a character.

Not ideal if you just need to generate images from general text prompts without needing to inject or control specific visual components from reference images.

digital art content creation image generation visual design marketing visuals
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

100

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Jan 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Correr-Zhou/MagicTailor"

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