baojudezeze/RMP-Adapter
The implementation of RMP-Adapter: A region-based Multiple Prompt Adapter for multi-concept customization in text-to-image diffusion model
This tool helps creative professionals and digital artists combine distinct visual elements from multiple reference images into a single, new image generated from text. You provide a general text description, individual reference images for each concept you want to include, and keywords for each concept. The output is a new image where the concepts from your reference images appear precisely where you describe them in the text, allowing for complex scene creation.
Use this if you need to generate images that accurately blend multiple specific visual concepts or identities from reference images into a new scene, such as creating virtual try-ons or consistent characters across different story panels.
Not ideal if you're looking for a simple text-to-image generator without needing to incorporate detailed visual styles or specific objects/people from reference photos.
Stars
20
Forks
3
Language
Python
License
—
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/baojudezeze/RMP-Adapter"
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...