StableSR
sd-webui-stablesr
StableSR | sd-webui-stablesr | |
---|---|---|
1 | 4 | |
1,856 | 961 | |
- | - | |
6.9 | 5.2 | |
about 2 months ago | 5 months ago | |
Python | Python | |
GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
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.
StableSR
-
What neural net for SISR?
A professor suggested to try to fine tune the state of the art model StableSR, but there's just no way I can run the it on either the hardware I have access to or Colab (even tho I do have the pro version).
sd-webui-stablesr
-
Upscaling Realism of an Image
I've been interested in this sorta thing as well recently. This is an outstanding upscaler that uses SD2.1 to add detail to the image: https://github.com/pkuliyi2015/sd-webui-stablesr - A1111 Extension hardly mentioned. Developers have an SDXL trained models listed on their todo/coming soon. Heavy on the resources but for me the results have been excellent. Prob some other more known things (like a complicated comfy workflow maybe you can just download)
-
Upscaling - not sure what's going wrong
- Try with StableSR, it can add lots of details (https://github.com/pkuliyi2015/sd-webui-stablesr) this is my upscaler method of choice.
-
Optimization tips for 4GB vram gpu?
Then I upscale to 4k using StableSR+Tiled Diffusion+Tiled VAE (https://github.com/pkuliyi2015/sd-webui-stablesr) (I used to use Ultimate SD Upscaler)
-
A Simple Comparison of 4 Latest Image Upscaling Strategy in Stable Diffusion WebUI
StableSR (for webui): https://github.com/pkuliyi2015/sd-webui-stablesr.git
What are some alternatives?
GFPGAN - GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
stable-diffusion-webui-two-shot - Latent Couple extension (two shot diffusion port)
Real-ESRGAN - Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
PromptHub - Prompt history and management for the Stable Diffusion AUTOMATIC1111 WebUI
video2x - A lossless video/GIF/image upscaler achieved with waifu2x, Anime4K, SRMD and RealSR. Started in Hack the Valley II, 2018.
stable-diffusion-webui-vid2vid - Translate a video to some AI generated stuff, extension script for AUTOMATIC1111/stable-diffusion-webui.
CodeFormer - [NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
shift-attention - In stable diffusion, generate a sequence of images shifting attention in the prompt.
SUPIR - SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild
sd-webui-cloud-inference - Stable Diffusion(SDXL/Refiner)WebUI Cloud Inference Extension
multidiffusion-upscaler-for-automatic1111 - Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
stable-diffusion-webui-composable-lora - This extension replaces the built-in LoRA forward procedure.