WorkflowListedExternal

FLUX LORA ENHANCER/FACE DETAILER — v1.0

FLUX LoRA ENHANCER/FACE DETAILER by weshouldhaveshotguns

Sourcecivitai.com/models/954879

TaskMultiCapabilitiesImage edit · Text to imageFamilyFLUXEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access: External workflow
Status: Listed
Source: Civitai
Updated: Sep 25, 2026

Source description

FLUX LoRA ENHANCER/FACE DETAILER by weshouldhaveshotguns

This workflow takes the power of LoRAs even further, unlocking their full potential in ComfyUI. Think of it like going Super Saiyan 3 for your character art and portraits. It starts by generating an initial image using your text prompt and LoRA settings, then cranks it up a notch with a Face Detailer that applies those same settings. This reinforces character traits, enhances facial details, and takes your creations to the next level. And if you’re not using a character LoRA? No problem—it functions as a standalone Face Detailer to sharpen and refine any portrait.

Key Features:

Effortless Setup: Everything you need is included, with links to required files and optional enhancements for a hassle-free start.

General and Face Detailer Settings Guide: A breakdown of key settings makes it easy to tweak and understand how each component influences the final result.

AI-generated commentary

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

Purpose

This ComfyUI workflow creates and refines portraits or character-focused images from a Flux text prompt and LoRA settings, optionally using a character LoRA; it produces an initial image and a face-refined portrait.

Flow

It first generates an initial image from the text prompt and LoRA settings, then applies Face Detailer with those same settings.
Without a character LoRA, it can be used as a standalone Face Detailer to sharpen and refine a portrait.

Inputs and outputs

Provide a Flux text prompt and LoRA settings; a character LoRA is optional.
The workflow produces an initial image and a portrait with reinforced character traits and enhanced facial details.

Setup

Use it in ComfyUI with Flux.1 D as the base model.
The listing includes links to required files and optional enhancements.

Dependencies

The listed model files are: ae.safetensors; bbox/face_yolov8m.pt; clip_l.safetensors; flux1-dev.safetensors; sam_vit_b_01ec64.pth; and t5xxl_fp8_e4m3fn.safetensors.
Listed node types include AV_FaceDetailer, BasicGuider, BasicScheduler, CLIPTextEncode, ConditioningZeroOut, DualCLIPLoader, EmptyLatentImage, FluxGuidance, Image Comparer (rgthree), and KSamplerSelect.
Additional listed node types are Power Lora Loader (rgthree), RandomNoise, SAMLoader, SamplerCustomAdvanced, SaveImage, UltralyticsDetectorProvider, UNETLoader, VAEDecode, and VAELoader.

Configuration

The guide covers general and Face Detailer settings and explains how each component affects the final result.
It includes Flux prompting tips and names the LoRA as “Vanessa” from random flux girlfriends by TechnicianSpecial666.

Cautions

Before using it, check that the listed model files and node types are available in your ComfyUI setup.
Suggestion · not verified
The listing does not specify a license for sam_vit_b_01ec64.pth, so check its usage terms separately.
Suggestion · not verified

Does this need to be edited?

Sources

1 source

CivitaiPrimary

civitai.com/models/954879

Verified Jul 20

Source excerpts

1 excerpt

NoteJul 20civitai.com/models/954879

Source context: 1564 downloads · Type Workflows · Base model Flux.1 D