KemingWu/HybridLayout
[ICCV 2025] Hybrid Layout Control for Diffusion Transformer: Fewer Annotations, Superior Aesthetics.
This project helps designers, artists, and marketers generate high-quality images with precise control over the placement and composition of elements. You provide text prompts and layout specifications, and it produces visually appealing images where objects are positioned exactly as desired, even with minimal initial input. It's ideal for anyone who needs to create consistent and aesthetically pleasing visual content efficiently.
Use this if you need to create visually appealing images with specific object placements and layouts, without needing extensive manual adjustments or detailed annotations.
Not ideal if you primarily need to generate free-form images without any particular layout constraints or if you prefer a system that requires exhaustive annotation for every detail.
Stars
18
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/KemingWu/HybridLayout"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...