madaror/tiled-diffusion
Official implementation of "Tiled Diffusion" [CVPR 2025]
This project helps artists, game developers, and designers automatically create images that perfectly connect on their edges. You provide a text description or an existing image, and the system generates new images or transforms the input so that it can be seamlessly tiled. The output is a high-quality image ready for use as a repeating pattern, texture, or part of a larger composite.
No commits in the last 6 months.
Use this if you need to generate repeating textures, background patterns, or visual assets for games, digital art, or 360° environments that must connect without visible seams.
Not ideal if you need to create standalone, non-repeating images or if you require precise control over every minute detail of the image content rather than its tiling properties.
Stars
79
Forks
5
Language
Python
License
—
Category
Last pushed
Mar 16, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/madaror/tiled-diffusion"
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...