cswry/SeeSR
[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
Builds on Stable Diffusion 2-Base with learnable LoRA adapters (SeeSR module) and semantic segmentation guidance (DAPE) to inject real-world scene understanding into the diffusion process. Supports variable inference speeds via sd-turbo integration (2-50 steps) and includes tiled VAE processing for memory-efficient upscaling of high-resolution outputs from low-resolution inputs.
618 stars.
Stars
618
Forks
48
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 16, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/cswry/SeeSR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
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.
IceClear/StableSR
[IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution
hanjq17/Spectrum
[CVPR 2026] Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration