stable-diffusion-webui-composable-lora
sd-dynamic-thresholding
stable-diffusion-webui-composable-lora | sd-dynamic-thresholding | |
---|---|---|
16 | 26 | |
461 | 1,019 | |
- | 4.8% | |
4.2 | 7.2 | |
about 1 year ago | 19 days ago | |
Python | Python | |
MIT 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.
stable-diffusion-webui-composable-lora
-
Discussion Thread
They do, it just needs more work. Stable Diffusion + Latent Couple + Composable LoRA let's you have an Elon model and a Mark model in different parts of the image. No Elon/Mark-ness dominating all the subjects.
-
ControlNet Reference-Only problems
https://github.com/opparco/stable-diffusion-webui-two-shothttps://github.com/butaixianran/Stable-Diffusion-Webui-Civitai-Helper https://github.com/opparco/stable-diffusion-webui-composable-lora https://github.com/thomasasfk/sd-webui-aspect-ratio-helper
-
[STABLE DIFFUSION] I need help with seperating characters. (LORA)
Possibly with something like the Latent Couple extension + Composable LoRA, cf this video.
-
Make a Lora only apply to specific aspect of my image?
I think it works with Regional Prompting in combination with and Composable LoRA (both std. Auto1111-extensions). Never tried myself, though.
-
Is there someway to make Latent Couple + Composable Lora work on Vlad Automatic webUI?
So i noticed that Latent Couple and Composable Lora don't work on Vlad Automatic (something to do with those extensions beind made for a outdated version of A1111 webUI).
-
In the prompt, how to limit the description to the outfit or an object without affecting the background?
Composable LoRA Enables using AND keyword(composable diffusion) to limit LoRAs to subprompts. Useful when paired with Latent Couple extension.
-
What is the extension that makes negative Prompt not effect on Lora??? like when i type "man" that effect just on checkpoint not lora !
Its https://github.com/opparco/stable-diffusion-webui-composable-lora
-
The Joker 2019 Cosplay Lora tests WIPS
I tried using composable lora but it is hardcoded to look for the "and", plus it has certain issues that haven't been resolved..
-
Can anyone suggest ways I can use several trained characters in one picture (using LORA)?
Only one good suggestion can be had here and that is the composable lora extension. I think you need to use it together with the latent couple extension.
-
Using multiple Loras without blending faces
Oh this is super easy, just grab the Latent Couple extension and the Composable LoRA extension. Using this you can define multiple sections for different characters, then you can have a prompt/lora unique to each section/character.
sd-dynamic-thresholding
-
ZeroDiffusion -- a clean zero terminal SNR training 1.5 base model + experimental inpainting model
For outputs to look right, you will need some form of CFG rescale or dynamic thresholding in order to correct for overexposure (A1111 extensions are linked -- I am told that ComfyUI has nodes available for these functions). A good starting point for CFG rescale is 0.7, as recommended in the paper. I strongly suspect that CFG rescale is not an ideal solution and leaves a substantial training-inference gap, and when using zero terminal SNR models I find that Dynamic Thresholding can give better outputs that are closer to what I expect from the data without the brownout often caused by CFG rescale. A potential starting point for Dynamic Thresholding would be: Restart sampler, 15 CFG scale, Mimic CFG scale 15 7.5, Sawtooth on both scale schedulers, 6 for both minimum values, scheduler value 4, do not separate feature channels, ZERO, STD. You will likely have to experiment a lot with Dynamic Thresholding. (edit: small correction to DT settings)
-
Dynamic Thresholding for comfyui?
Recently switched from A1111 and i love it so far, flexibility to orchestrate complex workflows automatically instead of manual operations is a life changer. Anyhow, one extension i like on A1111 was this one: https://github.com/mcmonkeyprojects/sd-dynamic-thresholding
-
How do I implement Dynamic Thresholding (CFG scale fix) in ComfyUI?
In the Automatic1111 webui, there is a Dynamic Thresholding (CFG scale fix) extension that:
-
How to diffuse better faces?
Ive found using ADetailer (https://github.com/Bing-su/adetailer, using their reccomended advanced settings and face_yolov8n.pt) and Dynamic Thresholding (CFG set to 12 and Mimic to 7) has vastly improved my face renders. (https://github.com/mcmonkeyprojects/sd-dynamic-thresholding) GL!
-
Kohya UI settings as asked (style+character training)
The output LoRA works best with CFG at 4, because at 7 it gets that gasoline colors and contrast of overbaking, but I guess this is a tradeoff of that many steps in total (5200) since the earlier snapshots were not that good in style and with character details. You can use a workaround like the Dynamic Trescholding extention: https://github.com/mcmonkeyprojects/sd-dynamic-thresholding.git - helps a lot in many cases when you want a high CFG but the model/lora overbakes them (it mimics a lower CFG while keeping the high CFG details and prompt alignment).
-
Does anyone know how to create this type of hyper realistic pic?
Use sd-dynamic-thresholding extension (set CFG scale to 12 or more and mimic CFG scale to 7): https://github.com/mcmonkeyprojects/sd-dynamic-thresholding
- ControlNet Reference-Only problems
-
What's your favorite small tweaks to make? I'll go first
Tweak this up or down for small changes. Too far and you’ll get a different image. Extensions like Dynamic Thresholding can let you go much higher without the overexposed look.
-
Blurred/Low quality/Low details images
Turn CFG scale down or maybe use this extension, I've never used Dynamic Thresholding before but I think its what you want
- Dynamic threshold & Offset noise - The answer to oversaturated images?
What are some alternatives?
adetailer - Auto detecting, masking and inpainting with detection model.
stable-diffusion-webui-anti-burn - Extension for AUTOMATIC1111/stable-diffusion-webui for smoothing generated images by skipping a few very last steps and averaging together some images before them.
sd-webui-regional-prompter - set prompt to divided region
Stable-Diffusion - Stable Diffusion, SDXL, LoRA Training, DreamBooth Training, Automatic1111 Web UI, DeepFake, Deep Fakes, TTS, Animation, Text To Video, Tutorials, Guides, Lectures, Courses, ComfyUI, Google Colab, RunPod, NoteBooks, ControlNet, TTS, Voice Cloning, AI, AI News, ML, ML News, News, Tech, Tech News, Kohya LoRA, Kandinsky 2, DeepFloyd IF, Midjourney
ComfyUI_Cutoff - cutoff implementation for ComfyUI
stable-diffusion-webui-two-shot - Latent Couple extension (two shot diffusion port)
multidiffusion-upscaler-for-automatic1111 - Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
Stable-Diffusion-Webui-Civitai-Helper - Stable Diffusion Webui Extension for Civitai, to manage your model much more easily.
sd_webui_SAG
sd-webui-latent-couple - Latent Couple extension (two shot diffusion port)
sd-dynamic-prompts - A custom script for AUTOMATIC1111/stable-diffusion-webui to implement a tiny template language for random prompt generation