bytedance-fanqie-ai/MOSAIC
[ICLR 2026]🔥🔥🔥MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement
MOSAIC helps digital artists, designers, and marketers create highly consistent images featuring multiple distinct subjects. You provide reference images of different subjects, and MOSAIC generates a new, personalized image where these subjects are accurately placed and retain their unique characteristics. This is ideal for anyone needing to generate customized visual content with specific, recognizable elements.
396 stars.
Use this if you need to generate new images that faithfully combine multiple specific people, objects, or characters from different reference images into a coherent scene.
Not ideal if you're looking for a tool to generate single-subject images or highly abstract art without specific subject consistency.
Stars
396
Forks
3
Language
Python
License
—
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/bytedance-fanqie-ai/MOSAIC"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks,...
keivalya/mini-vla
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to...
adobe-research/custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation...