sd-dynamic-thresholding
Stable-Diffusion-Webui-Civitai-Helper
sd-dynamic-thresholding | Stable-Diffusion-Webui-Civitai-Helper | |
---|---|---|
26 | 20 | |
1,031 | 2,315 | |
5.9% | - | |
7.2 | 7.4 | |
15 days ago | about 1 month 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.
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?
Stable-Diffusion-Webui-Civitai-Helper
-
How do you keep your models "up-to-date"?
While I've never used the check for new version option, the Civitai Helper extension has said option. Based upon the docs it looks like it would go out and check to see if there are new versions and provide you a URL to them and an option to just automatically download it if you want. https://github.com/butaixianran/Stable-Diffusion-Webui-Civitai-Helper for the extension if you don't have it, I find it to be immensely helpful for the preview, trigger tags, and sample image tags when trying to use LORAs or Textual Inversions.
-
How do you organize your AI-generated content? Need advice!
As far as loras go, the https://github.com/butaixianran/Stable-Diffusion-Webui-Civitai-Helper puts some buttons in for each lora, and one of them is to add the trigger keywords.
-
AUTOMATIC1111 updated to 1.4.0 version
I've found the Civitai helper extension invaluable! I had to do the Lyco mod tho, for my..ocd-ness
-
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
-
Trigger words?
i use Civitai Helper extension, it stores the front image, link to the model, and the trigger words. https://github.com/butaixianran/Stable-Diffusion-Webui-Civitai-Helper
-
Accessing the Civitai Info to display Model names?
This request goes out to people far more clever than I. Currently using the Civitai Helper extension, which is a godsend for organizing all your downloaded models etc. I modified it a bit so it handles the lyCORIS extra network and files properly (i.e allowing it to be separate from LORAS) and that works great, but i can't quite figure out how to replace the name shown in the cards, with the actual mode name from the info file, vs the file name.
-
Any way to record notes on models / Loras in SD?
add a .txt, with the same name in the same place, the information to be displayed in the preview. If you are using civitai I also recommend that you install civitai-helper.
-
What are some of the best and the easiest to install modules for this? I got web ui. And I got some face restoration thing. (Apologies, I'm not very smart.)
Stable-Diffusion-Webui-Civitai-Helper: to download and get the info of the civitai models.
- How do I update the descriptions and thumbnails of the LORAs and extra networks in the Vlad Auto1111 fork? I can't figure out how to do it.
-
How do I use, LyCORIS? (First Timer)
If you've downloaded your Lora model from CivitAI, you can also make use of this CivitAI Helper Extension
What are some alternatives?
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.
ComfyUI_Cutoff - cutoff implementation for ComfyUI
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
sd-webui-additional-networks
adetailer - Auto detecting, masking and inpainting with detection model.
ultimate-upscale-for-automatic1111
multidiffusion-upscaler-for-automatic1111 - Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
Config-Presets - Extension for Automatic1111
sd_webui_SAG
sdweb-easy-prompt-selector
sd-dynamic-prompts - A custom script for AUTOMATIC1111/stable-diffusion-webui to implement a tiny template language for random prompt generation
sd-civitai-browser - An extension to help download models from CivitAi without leaving WebUI