Correr-Zhou/MagicTailor
[IJCAI 2025 (Oral)] Offical implementation of the paper "MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models".
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.
Stars
100
Forks
3
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
bghira/SimpleTuner
A general fine-tuning kit geared toward image/video/audio diffusion models.
mcmonkeyprojects/SwarmUI
SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an...
nateraw/stable-diffusion-videos
Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
TheDesignFounder/DreamLayer
Benchmark diffusion models faster. Automate evals, seeds, and metrics for reproducible results.