#94 · Primary category: Image Generation
sd-dynamic-thresholding
Dynamic Thresholding (CFG Scale Fix) for Stable Diffusion (SwarmUI, ComfyUI, and Auto WebUI)
Project last updated:03/14/25
GitHub Stars
1.2K
Forks
107
Contributors
12
License
MIT
Why we included this project
Stable Diffusion users who crank the guidance scale past the usual sweet spot often end up with blown-out colors, harsh contrast, or oversaturated edges. Dynamic Thresholding fixes that by clamping the latents between sampler steps, which keeps higher CFG values usable without the visual degradation. It ships as a plugin for the three common interfaces: AUTOMATIC1111 WebUI, ComfyUI, and SwarmUI. SwarmUI includes it out of the box, WebUI users install it through the Extensions tab, and ComfyUI users add a node. The demo grid on the project site makes it easy to compare how different threshold settings affect the same prompt before you commit one to your workflow.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
stable-diffusion-webui
Stable Diffusion web UI
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
upscayl
🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.
InvokeAI
InvokeAI is a leading open-source creative engine for Stable Diffusion, offering an industry-leading web UI for generating and editing visual media.