PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
Employs Progressive Upscaling, Skip Residual, and Dilated Sampling mechanisms to extend Latent Diffusion Models beyond their native resolution without retraining. Integrates with Hugging Face Diffusers and SDXL, supporting text-to-image, image-to-image, and ControlNet pipelines with configurable hyperparameters for balancing quality against GPU memory constraints. Available through ComfyUI nodes, Gradio demos, and low-VRAM variants for accessibility across hardware tiers.
2,047 stars.
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...
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
thu-ml/Causal-Forcing
Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for...