On the recordRead 12 Oct 202627 facts
SUPIR
SUPIR · founded 2024
On the record
- Batch processing
- Yesgithub.com · read 22 Sep 2026
- Commercial use
- The repository declares SUPIR software available strictly for non-commercial purposes unless prior written permission is obtained from Dr. Jinjin Gu.github.com · read 12 Oct 2026
- 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.github.com · read 12 Oct 2026
- Compute requirements
- The repository notes a lower-VRAM configuration that uses 12G for diffusion and 16G for LLaVA, with slower performance.github.com · read 12 Oct 2026
- Dependent models
- The documented dependencies include SDXL CLIP encoders, SDXL base, LLaVA CLIP, and LLaVA v1.5 13B.github.com · read 12 Oct 2026
- Hardware requirements
- The repository describes a lower-VRAM demo mode as using 12 GB for diffusion and 16 GB for LLaVA, with slower processing.github.com · read 12 Oct 2026
- Image controls
- Inference options include an upsampling ratio, model selection, random seed, minimum output size, sampling steps, prompts, and color-fixing choices.github.com · read 12 Oct 2026
- Image enhancement
- The project presents SUPIR for image processing and upscaling, including compressed, noisy, or blurry images.xpixel.group · read 12 Oct 2026
- Installation
- The repository instructions create a Python 3.8 Conda environment and install dependencies from requirements.txt.github.com · read 12 Oct 2026
- Local installation
- The repository instructions use Python 3.8, Conda, pip, and the project's requirements file to install SUPIR.github.com · read 12 Oct 2026
- Maximum scale
- customgithub.com · read 22 Sep 2026
- Model
- SUPIR is described as a high-fidelity general image restoration model based on a large-scale diffusion generative prior.supir.xpixel.group · read 12 Oct 2026
- Model choices
- The repository provides SUPIR-v0Q with default training settings and SUPIR-v0F trained with light degradation settings.github.com · read 12 Oct 2026
- Model dependencies
- The installation instructions list SDXL CLIP encoders, an SDXL base checkpoint, and LLaVA CLIP and v1.5 13B among dependent models.github.com · read 12 Oct 2026
- Model variants
- The repository provides SUPIR-v0Q with default training settings and SUPIR-v0F trained with light degradation settings.github.com · read 12 Oct 2026
- 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.github.com · read 12 Oct 2026
- Online demo
- The repository links to SupPixel AI, an online image processing and upscaling tool built on SUPIR.github.com · read 12 Oct 2026
- Purpose
- SUPIR aims to develop practical algorithms for photo-realistic image restoration in the wild.github.com · read 12 Oct 2026
