WorkflowListedExternal

Flux with Skin_Detailer [ComfyUi] — Detail Daemon + NI

Update 26.11.24 This workflow eliminates the need for a face and skin detailer. The idea is to render directly at a significantly higher resolution and then correct any imperfections in the image using a simple...

Sourcecivitai.com/models/617451

TaskMultiCapabilitiesText to image · UpscalingFamilyFLUXEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access: External workflow
Status: Listed
Source: Civitai
Updated: Sep 3, 2026

Source description

Additionally, image details are enhanced through the Detail Daemon and additional noise injection. In the initial samplers, the sigmas are split to allow the first steps to render with high guidance and the final steps with low guidance. This makes the images appear more natural and less AI-like.

This approach works very well but requires extremely powerful hardware and is not particularly fast. However, the resulting images are of exceptionally high quality.

Update 07.10.24

The workflow now supports GGUF models, improved ViT-L/14 CLIP, and has a significantly enhanced UltimateUpscaler thanks to the fill nodes.

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

This ComfyUI workflow uses Flux.1 D to render high-resolution portraits, then upscales them to correct image imperfections.

Flow

Detail Daemon and added noise injection are used to enhance image details.
Sampling splits the sigmas so early steps use high guidance and final steps use low guidance.

Inputs and outputs

The creator says this approach avoids the need for a separate face and skin detailer.

Setup

Flux model download links are in the workflow notes.

Dependencies

Required ComfyUI node packs include ComfyUI-Impact-Pack, ComfyUI-Impact-Subpack, ComfyUI_essentials, ComfyUI-Inspire-Pack, and ComfyUI_Comfyroll_CustomNodes.
Named model files include epicrealism_naturalSinRC1VAE.safetensors, more_details.safetensors, sam_vit_b_01ec64.pth, and t5xxl_fp16.safetensors.

Configuration

The description lists GGUF model support, an improved ViT-L/14 CLIP, and fill nodes for UltimateUpscaler.

Cautions

Plan for a demanding run: the creator describes this workflow as extremely hardware-intensive and reports about 10–12 minutes per image on an RTX 3090.
Suggestion · not verified

Does this need to be edited?

Sources

1 source

CivitaiPrimary

civitai.com/models/617451

Verified Jul 20

Source excerpts

2 excerpts

NoteJul 20civitai.com/models/617451

Source context: 11497 downloads · Type Workflows · Base model Flux.1 D

NoteJul 15civitai.com/models/617451