PRIS-CV/DemoFusion

Let us democratise high-resolution generation! (CVPR 2024)

52
/ 100
Established

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.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

2,047

Forks

216

Language

Jupyter Notebook

License

MIT

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.