Real-ESRGAN
txt2imghd
Real-ESRGAN | txt2imghd | |
---|---|---|
131 | 22 | |
26,111 | 689 | |
- | - | |
2.7 | 0.0 | |
22 days ago | over 1 year ago | |
Python | Python | |
BSD 3-clause "New" or "Revised" License | MIT License |
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.
Real-ESRGAN
-
AI-Powered Nvidia RTX Video HDR Transforms Standard Video into HDR Video
It's not exactly what you're after, as it's anime specific and you need to process the video yourself (eg disassemble to frames, run the upscaler, then assemble back to a movie file), but Real-ESRGAN is really good:
https://github.com/xinntao/Real-ESRGAN/
It's pretty brilliant for cleaning up very old, low resolution anime.
-
Photorealistic Video Generation with Diffusion Models
Just a note you can run upscaling on your home desktop with Real-ESRGAN:
https://github.com/xinntao/Real-ESRGAN
- What software to use for upscaling anime edits
-
What neural net for SISR?
Maybe Real-ESRGAN is a good fit? Even tho it's a couple of years old
- Cant make concurrent calls to Model
-
Outis my beloved
I'm glad you noticed! I upscaled the icon from the wiki using Real-ESRGAN's 4xplus anime model, then photoshopped out the text. Worked far better than waifu2x.
-
ComicMerge (Beta testing version - SafeTensors)
A: Try using High-res Fix and R-ESRGAN 4x+ Anime6B as upscaler
-
Is there any way to upscale local files permanently using Nvidia's RT VSR?
Maybe try this one https://github.com/xinntao/Real-ESRGAN it may work even better.
-
YOASOBI Idol [3840 x 2160]
Screenshotted from the official music video, upscaled to 4k using a state of the art ML model.
-
Compilation of (almost) all end of chapter panels
Do you happen to remember which chapter has that "scene"? You could also try to enhance it yourself, I did it using Real-ESRGAN, which is really easy to use.
txt2imghd
-
Any sites or Programs with txt2imghd/SD Upscale as an upscaler?
I mean this tool: https://github.com/jquesnelle/txt2imghd
-
What do the "Scale Latent" and "Denoising strength" settings (under Highres. fix) do in the Automatic1111 repo?
The dictionary definition of upscale is to increase the size or improve the quality of. or convert (an image or video) so that it displays correctly in a higher resolution format. It's just scaling in one direction, the opposite of downscaling. Even the original author of high res fix uses word upscaling because the original library uses Real-ESRGAN to upscale transient images. A1111 repo provides an option to use an upscaling model or just bilinear interpolation for this step.
-
Upscale to huge sizes and add detail with SD Upscale, it's easy!
(4) What the SD upscaler does is chop the image into tiles, re-run SD on the tiles, and then stitch them back together. img2imgHD, and this custom script are other options that do a similar thing. You can also do it manually and combine the tiles in photoshop/gimp/krita, but it's a lot more work.
-
My best cyborgs so far
Im not using Collab. Running these on NVIDIA RTX A6000. I use SD then upscale with https://github.com/jquesnelle/txt2imghd
- My process to upscale an image through img2img
- The upscaling tech is really impressive
- What should I even call this?
- Obama Biden is pretty cursed...
- Landscapes, both scifi and fantasy, are incredible in this model. Made a few new wallpapers using a combination of img2imghd + RealESRGan with some great results. Things really took off once I learned how to use the --generated option to upscale other finds! Original pics at 150 steps, 768x512
-
A better (?) way of doing img2img by finding the noise which reconstructs the original image
https://github.com/jquesnelle/txt2imghd The link was literally in the Auto's code's comments.
What are some alternatives?
ESRGAN - ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.
stable-diffusion - This version of CompVis/stable-diffusion features an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, a WebGUI, and multiple features and other enhancements. [Moved to: https://github.com/invoke-ai/InvokeAI]
SwinIR - SwinIR: Image Restoration Using Swin Transformer (official repository)
stable-diffusion-gobig-txt2imghd - Stable diffusion using a standalone implementation of txt2imghd, which is similar to GoBig
GFPGAN - GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
stable-diffusion-webui - Stable Diffusion web UI [Moved to: https://github.com/sd-webui/stable-diffusion-webui]
BSRGAN - Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV, 2021) (PyTorch) - We released the training code!
stable-diffusion - A latent text-to-image diffusion model
waifu2x - Image Super-Resolution for Anime-Style Art
stable-diffusion-webui - Stable Diffusion web UI
Real-ESRGAN-colab - A Real-ESRGAN model trained on a custom dataset
stable-diffusion-webui - Stable Diffusion web UI [Moved to: https://github.com/Sygil-Dev/sygil-webui]