Skip to content
SPECIFICTION
Get listed

SUPIR

github.com

WebWindowsmacOSLinuxSelf-hosted
Visit github.com
Spec score 7.9 #53 of 99 in Image Upscaling Software

Spec sheet

Purpose
SUPIR aims to develop practical algorithms for photo-realistic image restoration in the wild.Read 12 Oct 2026 · github.com
Support
The repository directs questions to [email protected] or [email protected].Read 12 Oct 2026 · github.com
Founded
2024Read 28 Sep 2026 · github.com
Batch processing
YesRead 22 Sep 2026 · github.com
Commercial use
The repository declares SUPIR software available strictly for non-commercial purposes unless prior written permission is obtained from Dr. Jinjin Gu.Read 12 Oct 2026 · github.com
Commercial-use restriction
The repository declares SUPIR software use, reproduction, and distribution strictly non-commercial unless prior written permission is obtained from Dr. Jinjin Gu.Read 12 Oct 2026 · github.com
Compute requirements
The repository notes a lower-VRAM configuration that uses 12G for diffusion and 16G for LLaVA, with slower performance.Read 12 Oct 2026 · github.com
Dependent models
The documented dependencies include SDXL CLIP encoders, SDXL base, LLaVA CLIP, and LLaVA v1.5 13B.Read 12 Oct 2026 · github.com
Hardware requirements
The repository describes a lower-VRAM demo mode as using 12 GB for diffusion and 16 GB for LLaVA, with slower processing.Read 12 Oct 2026 · github.com
Image controls
Inference options include an upsampling ratio, model selection, random seed, minimum output size, sampling steps, prompts, and color-fixing choices.Read 12 Oct 2026 · github.com
Image enhancement
The project presents SUPIR for image processing and upscaling, including compressed, noisy, or blurry images.Read 12 Oct 2026 · xpixel.group
Installation
The repository instructions create a Python 3.8 Conda environment and install dependencies from requirements.txt.Read 12 Oct 2026 · github.com
Local installation
The repository instructions use Python 3.8, Conda, pip, and the project's requirements file to install SUPIR.Read 12 Oct 2026 · github.com
Maximum scale
customRead 22 Sep 2026 · github.com
Model
SUPIR is described as a high-fidelity general image restoration model based on a large-scale diffusion generative prior.Read 12 Oct 2026 · supir.xpixel.group
Model choices
The repository provides SUPIR-v0Q with default training settings and SUPIR-v0F trained with light degradation settings.Read 12 Oct 2026 · github.com
Model dependencies
The installation instructions list SDXL CLIP encoders, an SDXL base checkpoint, and LLaVA CLIP and v1.5 13B among dependent models.Read 12 Oct 2026 · github.com
Model variants
The repository provides SUPIR-v0Q with default training settings and SUPIR-v0F trained with light degradation settings.Read 12 Oct 2026 · github.com
Online app
The repository links to an online app and describes SupPixel AI as an easy-to-use image processing and upscaling tool built on SUPIR.Read 12 Oct 2026 · github.com
Online demo
The repository links to SupPixel AI, an online image processing and upscaling tool built on SUPIR.Read 12 Oct 2026 · github.com
Quality and fidelity
The repository says its empirical hyperparameters affect image quality and appearance, and describes a tradeoff between visual quality and fidelity.Read 12 Oct 2026 · github.com
Restoration approach
The project describes SUPIR as a high-fidelity general image restoration model based on a large-scale diffusion generative prior.Read 12 Oct 2026 · supir.xpixel.group
Run options
The repository supports command-line inference with input and output folders, an upsampling ratio, model selection, and configurable sampling and prompt parameters.Read 12 Oct 2026 · github.com
Security and compliance
The project pages opened do not state security certifications or compliance claims.Read 12 Oct 2026 · github.com
Text-driven restoration
The project describes restoration as text-driven and intelligent, blending AI technology with creativity.Read 12 Oct 2026 · supir.xpixel.group
Upscaling method
aiRead 22 Sep 2026 · github.com
Use cases
The project showcases restoration for landscape, face, animal, gaming, cinematic, and vintage photos.Read 12 Oct 2026 · supir.xpixel.group

Where Specifiction places it

Alternatives to SUPIRAll alternatives →