FLUX LORA ENHANCER/FACE DETAILER — v1.0

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.

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.

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.

Use it in ComfyUI with Flux.1 D as the base model.

The listing includes links to required files and optional enhancements.

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.

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.

Before using it, check that the listed model files and node types are available in your ComfyUI setup.

Vorschlag · nicht geprüft

The listing does not specify a license for sam_vit_b_01ec64.pth, so check its usage terms separately.

Vorschlag · nicht geprüft