maxim-pytorch
SwinIR
maxim-pytorch | SwinIR | |
---|---|---|
1 | 27 | |
159 | 4,082 | |
- | - | |
1.6 | 0.0 | |
about 1 year ago | 27 days ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
maxim-pytorch
-
Need help to reduce vision transformer patch artifacts
Hi there, i'm trying to do image enhancement task. Basically you give it some image and it makes it more colorful, vibrant, changes up some exposure and other things. I'm implementing it with Google Maxim architecture in pytorch. Unfortunately they dont include training code (original one is in JAX) and pyotorch only has the network, not training code.
SwinIR
- Certain directories (e.g. SwinIR) are empty (version: Empire Media Science A1111 Web UI Installer)
-
I used Real-ESRGAN to upscale my image, but if you zoom in you can see that “water particles” looks like some random lines and image overall looks cartoonish. Is there a way to fix it?
003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR-L_x4_GAN.pth
-
Any luck changing the upscaler? They seem to be hard coded
I was trying to get a new upscaler working, as someone pointed me to one that did a good job of preserving and creating new details: https://github.com/JingyunLiang/SwinIR
-
Spatial-temporal denoising
SwinIR: https://github.com/JingyunLiang/SwinIR
-
A Monster Hunter: World Virtual Photography Tutorial - YouTube
Upscalers that I use SwinIR https://github.com/JingyunLiang/SwinIR https://github.com/AUTOMATIC1111/stable-diffusion-webui (Use 'extras' tab for the upscaler function) Topaz Gigapixel AI https://www.topazlabs.com/gigapixel-ai
-
what are the alternatives to letsenhance.io?
You could try out chaiNNer, it is a free local/offline application. There are a lot of (upscaling) models which you can download an use with it. You can for example try out SwinIR-L (link will start a model download) or any other model you like depending on your input images.
-
[R] Swin transformer while using a rectangular attention window
the relative attention bias can be made non-square in the original implementation, there is a parameter window_size, at 7, that is forced to (7,7) directly, but you can change it easily. https://github.com/JingyunLiang/SwinIR/blob/main/models/network_swinir.py
-
Robot dance animation with Robo-Diffusion (1024x576)
Use SwinIR medium model to upscale by 2 times. This will result in a video of 2048x1152.
- Help Need to get my VQGAN images to 10000 x 10000
- Made with Outpainting + Inpainting(original picture and promt in comments)
What are some alternatives?
maxim - [CVPR 2022 Oral] Official repository for "MAXIM: Multi-Axis MLP for Image Processing". SOTA for denoising, deblurring, deraining, dehazing, and enhancement.
Real-ESRGAN - Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
Restormer - [CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.
image-super-resolution - 🔎 Super-scale your images and run experiments with Residual Dense and Adversarial Networks.
GIMP-ML - AI for GNU Image Manipulation Program
Real-ESRGAN-ncnn-vulkan - NCNN implementation of Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.
swin2sr - Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. Advances in Image Manipulation (AIM) workshop ECCV 2022. Try it out! over 3.3M runs https://replicate.com/mv-lab/swin2sr
Ne2Ne-Image-Denoising - Deep Unsupervised Image Denoising, based on Neighbour2Neighbour training
VRT - VRT: A Video Restoration Transformer (official repository)
chaiNNer - A node-based image processing GUI aimed at making chaining image processing tasks easy and customizable. Born as an AI upscaling application, chaiNNer has grown into an extremely flexible and powerful programmatic image processing application.
MPRNet - [CVPR 2021] Multi-Stage Progressive Image Restoration. SOTA results for Image deblurring, deraining, and denoising.
LaTeX-OCR - pix2tex: Using a ViT to convert images of equations into LaTeX code.