YangLing0818/RealCompo
[NeurIPS 2024] RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
This project helps graphic designers, artists, and marketers create complex images from text descriptions with greater control over object placement and realism. You provide a text prompt describing your desired image and optional details like object bounding boxes, and it generates high-quality images that accurately reflect both your description and spatial arrangements. This is ideal for anyone needing to generate specific, multi-object scenes or stylized images from text.
121 stars. No commits in the last 6 months.
Use this if you need to generate images where specific objects are precisely placed, or if you want to apply a particular artistic style to your generated scenes.
Not ideal if you're looking for a simple text-to-image tool without needing fine-grained control over object layout or combining different generation models.
Stars
121
Forks
3
Language
Python
License
—
Category
Last pushed
Nov 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/YangLing0818/RealCompo"
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...