Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official Implementation)
This tool helps graphic designers, marketers, and digital artists seamlessly combine different visual elements into a single image. You provide a background image, a foreground object image, and masks to define the object and where it should go, and the tool produces a high-quality composite image where the object blends naturally into the new scene. It's for anyone needing to create realistic or stylized visual compositions without extensive manual editing.
821 stars. No commits in the last 6 months.
Use this if you need to integrate an object from one image (e.g., a product photo) into a completely different visual style or background (e.g., a painting or cartoon scene) quickly and without manual training.
Not ideal if you need to perform basic image cropping, resizing, or simple overlay tasks that don't require advanced visual blending across different artistic styles.
Stars
821
Forks
101
Language
Python
License
MIT
Category
Last pushed
Mar 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Shilin-LU/TF-ICON"
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)
3DTopia/MaterialAnything
[CVPR 2025 Highlight] Material Anything: Generating Materials for Any 3D Object via Diffusion