WorkflowListedExternal

[FLUX] PuLID + LORA simple workflow (Basic, Beginner)

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

Sourcecivitai.com/models/1033132

TaskImage to imageFamilyFLUXEstimated VRAMEstimate unavailableBgrade

Runtime profile

Access: External workflow
Status: Listed
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 basic node is configured with a GGUF model, users who prefer to use standard Flux models can easily switch to the ClipLoader and Diffusion Model included in the workflow's Options.

The workflow provides step-by-step instructions for connecting and configuring PuLID nodes, making it easy even for beginners to follow. Detailed information about where to download and how to install the required models is included within the workflow.

Additionally, this workflow supports the integration of LoRA) models, allowing you to incorporate specific styles or character features into your image generation. By applying LoRA, you can effectively enhance the base model's output with desired styles or characteristics, enabling the creation of more diverse results.

AI-generated commentary

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

Purpose

Use the [FLUX] PuLID + LORA simple workflow to generate images with consistent faces using PuLID. It takes text prompts and input images, can apply LoRA models for styles or character features, and provides preview and saved-image outputs.

Flow

The workflow loads models, encodes text, applies PuLID guidance, samples and decodes an image, and supports comparison, preview, and saving.

Inputs and outputs

Enter a text prompt through CLIPTextEncode and provide an image through LoadImage.
PreviewImage and SaveImage provide preview and saved-image outputs.

Setup

The workflow includes step-by-step guidance for connecting and configuring PuLID nodes, plus information about downloading and installing required models.

Dependencies

Model files named in the workflow include: 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 workflow nodes include ApplyPulidFlux, BasicGuider, BasicScheduler, CLIPTextEncode, DualCLIPLoader, DualCLIPLoaderGGUF, EmptySD3LatentImage, FluxGuidance, Image Comparer (rgthree), KSamplerSelect, LoadImage, and Power Lora Loader (rgthree).
Other named workflow nodes are PreviewImage, PulidFluxEvaClipLoader, PulidFluxInsightFaceLoader, PulidFluxModelLoader, RandomNoise, SamplerCustomAdvanced, SaveImage, UNETLoader, UnetLoaderGGUF, VAEDecode, and VAELoader.

Configuration

The basic node uses a GGUF model, while Options includes ClipLoader and Diffusion Model for switching to standard Flux models.
LoRA models can add specific styles or character features to generated images.
The base model is Flux.1 D.

Cautions

Before use, verify that pulid_flux_v0.9.0.safetensors, EmptySD3LatentImage, BasicGuider, DualCLIPLoader, and UnetLoaderGGUF are available in your setup.
Suggestion · not verified

Does this need to be edited?

Sources

1 source

CivitaiPrimary

civitai.com/models/1033132

Verified Jul 20

Source excerpts

1 excerpt

NoteJul 20civitai.com/models/1033132

Source context: 1653 downloads · Type Workflows · Base model Flux.1 D