Patreon
Home / Videos / Restore and Upscale Old, Blurry Photos With AI: SUPIR Full T

Restore and Upscale Old, Blurry Photos With AI: SUPIR Full Tutorial With 10 Real Tests (2024)

SUPIR upscales and restores images better than Magnific, for example a 3x upscale from 1024 to 3072 px with face restore, and now supports up to 4 LoRAs.

Published Feb 27, 2024 · 21,281 views · Watch on YouTube

Get the app and files

SUPIR 1-Click Installer for Windows, Linux, Cloud & Free Kaggle

SUPIR 1-Click Installer for Windows, Linux, Cloud & Free Kaggle

SUPIR upscales and restores images better than Magnific, for example a 3x upscale from 1024 to 3072 px with face restore, and now supports up to 4 LoRAs.

SUPIR Image Upscaler Update: RTX 1000 to RTX 5000 & Cloud GPU Support

SUPIR Image Upscaler Update: RTX 1000 to RTX 5000 & Cloud GPU Support

SUPIR is still the unchallenged image upscaler; the V91 update brings Torch 2.8, CUDA 12.9, a resumable hash-checked model downloader and faster installs.

SUPIR Upscaler 1-Click Installer & Free Kaggle Notebook (Legacy)

SUPIR Upscaler 1-Click Installer & Free Kaggle Notebook (Legacy)

SUPIR upscaler 1-click installers for Windows, RunPod, Massed Compute and Linux plus a free Kaggle notebook; this older copy points to the maintained post.

SUPIR Full Tutorial: 1-Click Install, Batch Upscale & Magnific Test

SUPIR Full Tutorial: 1-Click Install, Batch Upscale & Magnific Test

SUPIR image upscaler full 33-minute tutorial: install with 1 click on Windows or RunPod and Linux, run on 12 GB VRAM GPUs and batch upscale your images.

Chapters

  1. 0:00 Introduction to SUPIR (Scaling-UP Image Restoration) full tutorial
  2. 2:10 How to download and install SUPIR on Windows or RunPod (thus Linux)
  3. 3:19 How to setup a community Pod on RunPod's newest interface
  4. 4:33 How to install and start SUPIR on RunPod
  5. 7:10 How to use Proxy connect of RunPod
  6. 8:13 How to install and start our own quantization supporting LLaVA
  7. 9:22 Getting image description from our own LLaVA model
  8. 9:42 How to use SUPIR interface and testing camel image (test image 1) on SUPIR in details
  9. 12:07 Testing a very old family photo enhancement and upscaling with SUPIR (test image 2)
  10. 14:34 Where the generated images are saved
  11. 14:53 Testing the image of Arnold Schwarzenegger as a warrior (test image 3) on SUPIR in details
  12. 16:22 The effect of simple prompt vs detailed prompt
  13. 17:30 Testing a dragon statue enhancement and upscaling with SUPIR (test image 4)
  14. 17:42 How I used ChatGPT Plus / GPT-4 for image captioning
  15. 18:29 The model works with literally every resolution and example very big upscale
  16. 19:00 Testing image of a dinosaur in jurassic park image enhancement and upscaling with SUPIR (test image 5)
  17. 19:41 From 500px to 3000px upscale results and how to do very big upscale properly
  18. 22:39 GPU utilization of the SUPIR scripts
  19. 23:15 If you get out of VRAM error what can you do and how you can solve
  20. 25:22 Testing a MonsterMMORPG Game character (anime like drawing) upscaling and image enhancing (test image 6)
  21. 25:39 What to do if your image has transparent pixels to be able to upscale
  22. 27:35 Testing a black and white colored movie screenshot of a man image enhancement and upscaling with SUPIR (test image 7)
  23. 28:29 Testing a screenshot from the movie Predator enhancement and upscaling with SUPIR (test image 8)
  24. 29:12 The queue ability of the Gradio app of SUPIR
  25. 29:49 Testing an old photo of Muhammad Ali in a boxing stance image enhancement and upscaling with SUPIR (test image 9)
  26. 30:45 Testing a black and white colored movie screenshot of Charlie Chaplin image enhancement and upscaling with SUPIR (test image 10)

About this video

With V8, NOW WORKS on 12 GB GPUs as well with Juggernaut-XL-v9 base model. In this tutorial video, I introduce SUPIR (Scaling-UP Image Restoration), a state-of-the-art image enhancing and upscaling model presented in the paper "Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild." SUPIR surpasses the performance of expensive alternatives like Magnific AI or Topaz AI and is open-source, with the models readily available. Additionally, I provide a one-click installer for easy installation and use on various platforms, including Windows, RunPod, and Linux. SUPIR also incorporates the Stable Diffusion XL (SDXL) pipeline for superior photo upscaling and enhancement.

The Patreon Post Link Used In The Video To Download Installers ⤵️

https://www.patreon.com/posts/99176057

Official GitHub Link ⤵️

https://github.com/Fanghua-Yu/SUPIR

Our Discord Channel ⤵️

https://discord.com/servers/software-engineering-courses-secourses-772774097734074388

Our Patreon With Amazing AI Scripts & Tutorials ⤵️

https://www.patreon.com/SECourses

0:00 Introduction to SUPIR (Scaling-UP Image Restoration) full tutorial

2:10 How to download and install SUPIR on Windows or RunPod (thus Linux)

3:19 How to setup a community Pod on RunPod's newest interface

4:33 How to install and start SUPIR on RunPod

7:10 How to use Proxy connect of RunPod

8:13 How to install and start our own quantization supporting LLaVA

9:22 Getting image description from our own LLaVA model

9:42 How to use SUPIR interface and testing camel image (test image 1) on SUPIR in details

12:07 Testing a very old family photo enhancement and upscaling with SUPIR (test image 2)

14:34 Where the generated images are saved

14:53 Testing the image of Arnold Schwarzenegger as a warrior (test image 3) on SUPIR in details

16:22 The effect of simple prompt vs detailed prompt

17:30 Testing a dragon statue enhancement and upscaling with SUPIR (test image 4)

17:42 How I used ChatGPT Plus / GPT-4 for image captioning

18:29 The model works with literally every resolution and example very big upscale

19:00 Testing image of a dinosaur in jurassic park image enhancement and upscaling with SUPIR (test image 5)

19:41 From 500px to 3000px upscale results and how to do very big upscale properly

22:39 GPU utilization of the SUPIR scripts

23:15 If you get out of VRAM error what can you do and how you can solve

25:22 Testing a MonsterMMORPG Game character (anime like drawing) upscaling and image enhancing (test image 6)

25:39 What to do if your image has transparent pixels to be able to upscale

27:35 Testing a black and white colored movie screenshot of a man image enhancement and upscaling with SUPIR (test image 7)

28:29 Testing a screenshot from the movie Predator enhancement and upscaling with SUPIR (test image 8)

29:12 The queue ability of the Gradio app of SUPIR

29:49 Testing an old photo of Muhammad Ali in a boxing stance image enhancement and upscaling with SUPIR (test image 9)

30:45 Testing a black and white colored movie screenshot of Charlie Chaplin image enhancement and upscaling with SUPIR (test image 10)

Info From The Paper

Sure, here's a summary of the paper "Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild" (SUPIR), with the goal of at least 3,000 characters.

The paper introduces SUPIR, a groundbreaking image restoration (IR) approach that combines a powerful generative prior with the benefits of model scaling. SUPIR leverages multi-modal techniques and a large-scale generative prior, making significant strides towards intelligent and realistic image restoration. The authors demonstrate SUPIR's superiority in various IR tasks, achieving exceptional visual quality. A key innovation is the model scaling technique, offering dramatic improvements in capabilities and pushing the boundaries of image restoration. Additionally, the model offers the unique ability to be controlled via text prompts, greatly expanding its applications and potential.

Advanced Generative Prior: SUPIR utilizes StableDiffusion-XL (SDXL), a massive generative model with 2.6 billion parameters. SDXL serves as a powerful tool for introducing high-quality image generation abilities into the image restoration process.

Image Encoder Fine-Tuning: The image encoder is fine-tuned to improve its resilience to image degradations, ensuring robust interpretation of low-quality input images.