tomesd
stable-diffusion-webui-ux
tomesd | stable-diffusion-webui-ux | |
---|---|---|
18 | 30 | |
1,207 | 939 | |
- | - | |
5.4 | 9.9 | |
5 months ago | 16 days ago | |
Python | Python | |
MIT License | GNU Affero General Public License v3.0 |
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.
tomesd
-
List of all the ways to improve performance for stable diffusion.
They show up to 5.4 times greater: you can see his results in the image on the github repo here: https://github.com/dbolya/tomesd
-
Question about automatic1111 set up after changing gpu
Another optimization extension you can use as well is token merging which has reported around 5.4x faster image generation.
- +39%~51% faster at the cost of some details? ToMe officially arrives to Auto1111's webui v1.3.0
-
AUTOMATIC1111 updated to 1.3.0 version
It merges redundant tokens: https://github.com/dbolya/tomesd So it can make the generation slightly faster.
-
I made some changes in AUTOMATIC1111 SD webui, faster but lower VRAM usage
Mods patched - Tomesd - Pillow-SIMD - OpenCV-CUDA (WIP) - Removed some unused imports and startup checking - Improved performance with reduced VRAM usage (tested on txt2img only) - Added a new option to use external RealESRGAN with --external-realesrgan
-
Honest question, how are people getting ~35-40 it/sec on 4090? My spits 20 at most
Were the 40 it/s perhaps achieved with ToMe?
-
Vlad diffusion keeps growing. Big thanx to all supporters :)
Done! Proposal
-
Token Merging actually works and reduces generation time as well as RAM
This feature comes from this project: https://github.com/dbolya/tomesd
-
How can I squeeze every ounce of performance from web UI?
GitHub - dbolya/tomesd: Speed up Stable Diffusion with this one simple trick!
- Token Merging for Fast Stable Diffusion
stable-diffusion-webui-ux
- Wildly unpredictable faces quality
-
Alternative to Canvas Zoom Extension?
If you're open to trying a fork of auto1111, I'd recommend using the Ui-UX fork of auto1111 by anapnoe. It has a big ui overhaul, one item of which is improved inpainting. Has move, zoom, and full a screen mode. Take a look at the screenshots and see if that seems to fit your need.
-
Better mobile Inpainting from locally hosted Stable Diffusion?
I'd highly recommend using the Ui-UX fork of auto1111 by anapnoe. It is designed with mobile in mind, and has a custom interface for img2img and inpainting.
- SDFX : New UI for Stable Diffusion
- Is there any interest in a mobile companion app to go with automatic1111?
-
AUTOMATIC1111 updated to 1.3.0 version
If you want more than that, the only thing I know of is a fork that needs a fresh install: https://github.com/anapnoe/stable-diffusion-webui-ux
-
What is the text-to-image AI tool?
https://github.com/vladmandic/automatic or https://github.com/anapnoe/stable-diffusion-webui-ux
- What web UI should I go for for SD generation? I currently use Easy Diffusion 2.5, but I’ve been meaning to switch since I just got a GeForce RTX 3070. Any good recommendations?
-
webui.bat closes instantly?
Yes that's the fork I'm using, it's got a great UX, and I much preferred it when it was working!
-
What's your opinion on InvokeAI compared to Automatic1111
Seriously, if anyone wants to use Auto1111 (which supports all the important SD "extras") but are turned off by the clunky interface, try this fork: https://github.com/anapnoe/stable-diffusion-webui-ux. It has a much better UI, runs nearly every Auto1111 extension without issues AND only merges stable commits. If you were already considering InvokeAI (which is in itself a great downscaled SD environment) then try Anapnoe's webui. It's closer to bleeding edge, but without the actual bleeding.
What are some alternatives?
ComfyUI - The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.
automatic - SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models
stable-diffusion-webui-tensorrt
a1111-nevysha-comfy-ui - A collection of tweak to improve Auto1111 UI//UX [Moved to: https://github.com/Nevysha/Cozy-Nest]
sd-web-ui-kitchen-theme - 🧿 Kitchen theme for stable diffusion webui [Moved to: https://github.com/canisminor1990/sd-webui-kitchen-theme]
sd-extension-system-info - System and platform info and standardized benchmarking extension for SD.Next and WebUI
diffusers - 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
Visual Studio Code - Visual Studio Code
stable-diffusion-webui-directml - Stable Diffusion web UI
StableStudio - Community interface for generative AI