PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
This tool helps graphic designers, digital artists, and marketers create stunningly detailed, high-resolution images from text descriptions or enhance existing low-resolution images. You input a text prompt or an image, and it outputs a crisp, large-format picture ready for professional use. It's designed for anyone needing top-quality visual content without the need for expensive, high-end computing resources.
2,047 stars. No commits in the last 6 months.
Use this if you need to generate or upscale images to very high resolutions (e.g., for print, large displays, or detailed digital art) but have limited access to costly specialized hardware or enterprise-level AI platforms.
Not ideal if your primary need is rapid, real-time image generation for interactive applications, as its progressive upscaling, while yielding excellent quality, involves more processing steps.
Stars
2,047
Forks
216
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/PRIS-CV/DemoFusion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
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...
3DTopia/MaterialAnything
[CVPR 2025 Highlight] Material Anything: Generating Materials for Any 3D Object via Diffusion