giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
This project helps graphic designers, 3D artists, and game developers create realistic material textures for digital assets. You provide input like color palettes, sketches, text descriptions, or reference images, and it generates high-quality material maps (diffuse, normal, roughness, specular). This allows for fine-grained control over how materials look and react to light, and you can even refine synthesized materials after generation.
Use this if you need to quickly generate or refine detailed and controllable SVBRDF material maps for computer graphics applications, reducing the time and expertise traditionally required.
Not ideal if you are looking for a simple image editor or a tool for general-purpose image generation unrelated to specific material properties.
Stars
58
Forks
7
Language
Python
License
MIT
Category
Last pushed
Feb 19, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/giuvecchio/matfuse"
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...
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...
3DTopia/MaterialAnything
[CVPR 2025 Highlight] Material Anything: Generating Materials for Any 3D Object via Diffusion