Jonseed/ComfyUI-Detail-Daemon

A port of muerrilla's sd-webui-Detail-Daemon as a node for ComfyUI, to adjust sigmas that control detail.

What it solves

This project provides a set of ComfyUI nodes that allow users to enhance the fine details of generated images and reduce unwanted background blurring (bokeh) by adjusting the noise schedules (sigmas) during the sampling process. It is particularly effective for Flux models, but also supports SDXL, SD1.5, Qwen, and Z-Image.

How it works

The tool modifies the amount of noise removed at each step of the image generation process. By lowering the amount of noise removed in specific steps (typically the middle steps), it effectively adds more detail to the image.

It offers several methods for this adjustment:

  • Detail Daemon Sampler: Adjusts sigmas using a customizable curve (controlled by parameters like detail_amount, start, end, bias, and exponent).
  • Detail Daemon Sampler GUI: An interactive node that allows users to visually edit the adjustment curve via a graph.
  • Multiply Sigmas: A stateless node that multiplies all noise levels by a specific factor to increase detail.
  • Lying Sigma Sampler: A simplified version of the Detail Daemon sampler with basic amount and timing adjustments.

Who it’s for

Digital artists and AI image generation enthusiasts using ComfyUI who want more control over the level of detail and sharpness in their AI-generated images without relying solely on prompts.

Highlights

  • Interactive GUI: Includes a node with a live, interactive schedule graph for visual tuning of detail levels.
  • Broad Model Support: Works with Flux, SDXL, SDXL, SD1.5, and Z-Image models.
  • Flexible Adjustment: Allows for both increasing (positive values) and decreasing (negative values) image detail.
  • Visual Graphing: Provides a separate node to visually graph the adjusted sigmas to understand the effect of parameters.

Related

  • Project
    pixaroma/ComfyUI-Pixaroma

    ComfyUI‑Pixaroma is a genuine open‑source extension for the ComfyUI diffusion‑workflow editor. It adds a large collection of ready‑made nodes—image loading/resizing, visual crop & paint tools, 3‑D scene builder, audio‑reactive video, LoRA stacking, text utilities, XY‑plot comparison, and workflow helpers—plus built‑in help panels and example workflows. The goal is to make everyday AI‑image generation tasks more visual and user‑friendly, letting artists and developers build, preview, and tweak pipelines without leaving ComfyUI.

  • Project
    martin-rizzo/ComfyUI-ZImagePowerNodes

    A collection of ComfyUI custom nodes optimized for the Z-Image Turbo model, offering enhanced style control, low-step consistency, and compositional variety.

  • Project
    filliptm/ComfyUI_Fill-Nodes

    A versatile collection of custom nodes for ComfyUI that adds advanced image processing, VFX, file handling, and integrations with external AI APIs like GPT and Gemini.

  • Project
    Acly/comfyui-inpaint-nodes

    A collection of ComfyUI nodes that enhance image inpainting and outpainting using Fooocus SDXL models, LaMa, MAT, and advanced mask pre-processing tools.

  • Project
    ssitu/ComfyUI_UltimateSDUpscale

    A set of ComfyUI nodes that perform image-to-image diffusion on large images using a tiled approach to improve detail and reduce hardware requirements.