IceClear/StableSR
[IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution
Leverages pre-trained Stable Diffusion as a generative prior within a finetuned architecture, using DDIM sampling with optional negative prompts and wavelet color correction for artifact reduction. Supports arbitrary upscaling factors (4x, 8x, beyond 4K) through tile-based processing and integrates with multiple interfaces including Stable Diffusion WebUI, ComfyUI, and cloud platforms (Hugging Face, Replicate, ModelScope). Provides specialized variants like StableSR-768v and face-specific models, compatible with PyTorch/CUDA environments.
2,641 stars. No commits in the last 6 months.
Stars
2,641
Forks
169
Language
Python
License
—
Category
Last pushed
Jul 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/IceClear/StableSR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cswry/SeeSR
[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
JJLibra/SALAD-Pan
🤗 Official implementation for "SALAD-Pan: Sensor-Agnostic Latent Adaptive Diffusion for...
Janspiry/Image-Super-Resolution-via-Iterative-Refinement
Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch
open-mmlab/mmgeneration
MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.
hanjq17/Spectrum
[CVPR 2026] Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration