WorkflowListedExternal

[FLUX] PuLID simple workflow (Beginner, Basic) — v1.0

This workflow is designed to help you easily understand how to generate consistent faces using PuLID in Flux.

Sourcecivitai.com/models/1032821

FamilyFLUXVersionRelease 1158375 — FLUX+PULID simple.jsonEstimated VRAMEstimate unavailableBgrade

Runtime profile

Access: External workflow
Status: Listed
Version: FLUX+PULID simple.json
Source: Civitai
Updated: Jul 20, 2026

Source description

This workflow is designed to help you easily understand how to generate consistent faces using PuLID in Flux.

While the default nodes are set up with GGUF models, users who prefer to use standard Flux models can easily switch by using the ClipLoader and Diffusion Model included in the workflow's Options.

The connection and configuration of PuLID nodes have been organized step by step so that even beginners can follow along easily. The workflow includes detailed download locations and installation instructions for the required models. Following the provided instructions will allow you to quickly implement the system.

=========================================================

이 워크플로우는 Flux에서 PuLID를 활용하여 일관된 얼굴을 생성하는 방법을

AI-generated commentary

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

Purpose

[FLUX] PuLID simple workflow (Beginner, Basic) is for learning to generate consistent faces in Flux with PuLID; it takes text and image inputs through CLIPTextEncode and LoadImage, and includes PreviewImage and SaveImage for image previews and saved images.

Flow

PuLID node connections and configuration are organized step by step for beginners.

Inputs and outputs

CLIPTextEncode and LoadImage are the named text- and image-input nodes; PreviewImage and SaveImage are included for image previews and saved images.

Setup

The instructions provide download locations and installation steps for the required model files.

Dependencies

Named model files are clip_l.safetensors, FLUX_VAE_diffusion_pytorch_model.safetensors, flux1-dev-fp8.safetensors, flux1-dev-Q8_0.gguf, pulid_flux_v0.9.0.safetensors, t5xxl_fp16.safetensors, and t5xxl_fp8_e4m3fn.safetensors.
Named components include ApplyPulidFlux, BasicGuider, BasicScheduler, CLIPTextEncode, DualCLIPLoader, DualCLIPLoaderGGUF, EmptySD3LatentImage, FluxGuidance, Image Comparer (rgthree), KSamplerSelect, and LoadImage.
Additional named components include PreviewImage, PulidFluxEvaClipLoader, PulidFluxInsightFaceLoader, PulidFluxModelLoader, RandomNoise, SamplerCustomAdvanced, SaveImage, UNETLoader, UnetLoaderGGUF, VAEDecode, and VAELoader.

Configuration

The default nodes use GGUF models; the Options include ClipLoader and Diffusion Model for switching to standard Flux models.
The listed base model is Flux.1 D, and the listed version is v1.0.

Cautions

Before using it, check that the required model files and named components are available in your setup.
Suggestion · not verified
No license is listed for the workflow.

Does this need to be edited?

Sources

1 source

CivitaiSourceVersion 1158375

civitai.com/models/1032821

Verified Aug 7

Source excerpts

2 excerpts

NoteAug 7civitai.com/models/1032821

Source context: 1770 downloads · Type Workflows · Base model Flux.1 D

NoteJul 20civitai.com/models/1032821