kongzhecn/OMG
[ECCV 2024] OMG: Occlusion-friendly Personalized Multi-concept Generation In Diffusion Models
This tool helps artists, designers, and marketers generate high-quality images with multiple consistent characters and specific artistic styles. You provide text prompts, optional reference images for characters, and style preferences. It then produces custom images where characters maintain their identity, even when occluded or in complex scenes. This is ideal for anyone needing to create detailed visual content quickly.
701 stars. No commits in the last 6 months.
Use this if you need to generate images featuring specific characters interacting in various scenes or adopting different artistic styles, ensuring their appearance remains consistent throughout.
Not ideal if you only need to generate single-character images or if you prefer to hand-draw or digitally paint every visual element from scratch.
Stars
701
Forks
46
Language
Python
License
—
Category
Last pushed
Jul 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/kongzhecn/OMG"
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...