#53 · Primary category: Image Generation
ComfyUI-Detail-Daemon
A port of muerrilla's sd-webui-Detail-Daemon as a node for ComfyUI, to adjust sigmas that control detail.
Project last updated:08/18/26
GitHub Stars
964
Forks
39
Contributors
4
License
MIT
Why we included this project
ComfyUI-Detail-Daemon is a port of muerrilla's sd-webui Detail Daemon reworked as ComfyUI nodes. Instead of sharpening in post, it changes what the sampler does with noise at each denoising step: injected noise stays the same while less is removed, so fine texture survives that would otherwise be smoothed away. The method works especially well with Flux models and can also clear stray bokeh or background blur. The pack has five nodes, including a full sampler, an interactive sampler GUI with a live schedule graph, a stripped-down 'lying sigma' variant, a stateless sigma multiplier, and a graph node that draws the curve you are about to apply. On the GUI you drag the schedule's control points and watch the curve redraw as you tune, which turns sigma tweaking from guesswork into something visible. Push the values too far, though, and you end up with an oversharpened, HDR-looking image. This suits ComfyUI users who want detail handled at the sampling stage instead of covered up later with a sharpen or upscale pass.
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.