sd-dynamic-prompts
sd-dynamic-thresholding
sd-dynamic-prompts | sd-dynamic-thresholding | |
---|---|---|
118 | 26 | |
1,907 | 1,019 | |
- | 4.8% | |
7.9 | 7.2 | |
14 days ago | 23 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.
sd-dynamic-prompts
-
Prompt Syntax Language--I know I saw it, but where?
I found some of the images I remember from the article I'm trying to find, buried deep in the StylePile Extension , but sadly not the article itself. The Wildcards Directory Extension looks promising as well, although it seems only tangentially related to what I'm looking for.
-
Can't get random combinations to work
While not really relevant to the issue I am trying to use a program to build wildcards to use with sd-dynamic-prompts. That is why the code contains a few weird things in how it outputs the files and why it restricts certain characters on input.
-
SDXL black people look amazing.
wildcards already done https://github.com/adieyal/sd-dynamic-prompts/blob/main/collections/nsp/nsp/nationality.txt
- Is there a way to get a random output of locations/backgrounds?
- Random or Logical operators in text prompt syntax?
-
Nearly Unlimited Female Faces
Body types is on my to-do list if I can make it work. As for custom categories, probably not. Honestly if that's what you want you should use a straightforward wildcard extension like Dynamic Prompts. Try it, it's fantastic.
-
Need help with ideas
First step: install the dynamic prompt extension (you may like some of its extra features as they fall directly in the type of work you are doing) or the barebones Wildcard extension that was initially released by A1111 himself.
-
Creating a randomized crowd with various expression through txt2img with adetailer + dynamic prompt extension
This is an experimental attempt in order to avoid "same face"/copypaste effect of having multiple subjects. It's simply using adetailer and dynamic prompt extension to create a group people with different clothing/expressions. The prompt in both txt2img and adetailer can be changed according to what the project need.
-
How do I create more varied images, in one batch?
https://github.com/adieyal/sd-dynamic-prompts let you add random (or controlled) info to your prompt
- What are some must-have/fun extensions or modules?
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?
stable-diffusion-webui-wildcards - Wildcards
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 - The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.
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
a1111-sd-webui-tagcomplete - Booru style tag autocompletion for AUTOMATIC1111's Stable Diffusion web UI
adetailer - Auto detecting, masking and inpainting with detection model.
unprompted - Templating language written for Stable Diffusion workflows. Available as an extension for the Automatic1111 WebUI.
multidiffusion-upscaler-for-automatic1111 - Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
sd-webui-regional-prompter - set prompt to divided region
sd_webui_SAG
ultimate-upscale-for-automatic1111