sdweb-auto-MBW
stable-diffusion-webui-model-toolkit
sdweb-auto-MBW | stable-diffusion-webui-model-toolkit | |
---|---|---|
4 | 16 | |
196 | 218 | |
- | - | |
4.8 | 10.0 | |
6 months ago | about 1 year ago | |
Python | Python | |
- | 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.
sdweb-auto-MBW
-
2.3 Mega Model (controlnet and kadinsky in the model) adds quality to outputs
Repo: https://github.com/Xerxemi/sdweb-auto-MBW
-
I tried merging a model with ProtoThing_200 using AutoMBW (ft. custom model)
AutoMBW is an extension made by Xynon#7407 and Xerxemi#6423, and performs block weight merging automatically.
-
ControlNet Character Design Workflow (links in comment)
Alternatively, something I've been working on is applying block merges to the fantasy art style model. However, even with auto block merging (https://github.com/Xerxemi/sdweb-auto-MBW), I can't get anything decent. I probably don't understand enough of the block merge theory, yet.
-
Automatic checkpoint merging is now possible
I haven't tried this out yet myself, but it's something that looks major. If I read the article correctly, autoBWM basically fiddles with the weight merge sliders and puts the result through aesthetic scoring in order to discover the best results (according to the aesthetic scoring thing(s)).
stable-diffusion-webui-model-toolkit
-
DreamShaper 6 Released!
I think you can prune your model to under 4G using the webui-model-toolkit
-
Why some models are bigger than other?
I am using Model Toolkit in A1111, and most of the time it does it's job well by removing junk data and converting model to fp16. This results in 2GB file, but... There are models that cannot be converted to 2GB version. Noticeably CyberRealistic v2.0 has this "issue".
- Still Need Help: How to prune a ckpt on colab?
-
CKPT to Safetensors
Use the model toolkit extension in A1111 -> https://github.com/arenatemp/stable-diffusion-webui-model-toolkit
-
I tried merging a model with ProtoThing_200 using AutoMBW (ft. custom model)
I merged this on Colab, so you don't need a powerful graphics card. You'll need the block merge extension,the model toolkit extension and the supermerger extension.
-
problem with models.
If issue persists after trying the suggestions given, fix the model by using the model toolkit: https://github.com/arenatemp/stable-diffusion-webui-model-toolkit
-
Is it possible to make 3D realistic renders of architecture from low polly pictures like this with SD that will keep the elements like furniture, windows, doors etc. in the same place just add realistic textures (and variations of it)? What would be best general workflow for that?
Also, I'd highly recommend getting the Model Toolkit. It's an extension that can load up your models and prune information it doesn't need, making them drastically smaller. It can also fix broken models. You have to install it manually, but it's pretty easy (and explained on the GitHub). Well worth downloading.
-
My new favorite models for photorealism
Protogen Infinity has been my go to in recent weeks (I recommend getting the full unpruned version, and pruning/fixing it with arenatemp's toolkit). Very versatile, flexible, creative, diverse, high quality, etc., but I think I'll be trying Realistic Vision 1.4 (and maybe Deliberate v2) more now. I might try merging Realistic Vision and Protogen Infinity, and see if that improves on either of them (merging RV and Deliberate together didn't necessarily see any improvements).
-
Stable Diffusion crashing my laptop's GPU
Someone made a "model fixer" for this reason too apparently.
-
Quantizing Diffusion Models : Running Stable Diffusion in only 4-bit weights without losing much perceptual quality
I agree about having to reload the UI. Since I have some pluigins installed I have to restart the UI or the engine (via CTRL-C) to maintain that 576x576 resolution as it'll run out of just enough memory to do it sometimes. I've found that safetensor format makes reloading MUCH QUICKER after a restart and I've used the Basic tab on this extension to trim the fat out of models I use, while converting them to fp16 and safetensor format.
What are some alternatives?
sd-webui-supermerger - model merge extention for stable diffusion web ui
safetensors - Simple, safe way to store and distribute tensors
ControlNet - Let us control diffusion models!
stable-diffusion-webui-model-toolkit - A Multipurpose toolkit for managing, editing and creating models.
instruct-pix2pix
k-diffusion - Karras et al. (2022) diffusion models for PyTorch
sd-webui-model-converter - model convert extension for stable-diffusion-webui. supports convert fp16/bf16 no-ema/ema-only safetensors
stable-diffusion-webui - Stable Diffusion web UI
civitai - A repository of models, textual inversions, and more
InvokeAI - InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.