WorkflowListedExternal

[SDXL, SD1.5] IPAdapter_FaceID_Portrait workflow (Basic) — v1.0

This workflow is designed for creating IP-Adapter FaceID Portraits, compatible with both SD1.5 and SDXL models. It processes batch image inputs to generate images with similar facial features.

Sourcecivitai.com/models/1023435

TaskMultiCapabilitiesImage to image · Text to imageFamilyStable DiffusionEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access: External workflow
Status: Listed
Source: Civitai
Updated: Oct 2, 2026

Source description

This workflow is designed for creating IP-Adapter FaceID Portraits, compatible with both SD1.5 and SDXL models. It processes batch image inputs to generate images with similar facial features.

By default, the CLIP Text Encode node is set to the SDXL version.

For SD1.5, simply switch this node to the basic Text Encode.

Additional details, including how to download the models,

are provided in the workflow notes in both Korean and English. Enjoy!

The IP-Adapter-FaceID-portrait model

AI-generated commentary

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

Purpose

Use this workflow to turn batch image inputs into IP-Adapter FaceID portraits with similar facial features, for SD1.5 or SDXL.

Flow

The workflow lists ip-adapter-faceid-portrait_sdxl.bin as a required model file.

Inputs and outputs

Provide a batch of images as input; the workflow generates images with similar facial features.

Setup

The CLIP Text Encode node is set to the SDXL version by default.
For SD1.5, switch that node to the basic Text Encode node.
Suggestion · not verified

Dependencies

Named model files include CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors, ip-adapter-faceid-portrait_sdxl.bin, and juggernautXL_juggXIByRundiffusion.safetensors.
Named nodes include CheckpointLoaderSimple, CLIPTextEncodeSDXL, CLIPVisionLoader, EmptyLatentImage, Image Comparer (rgthree), ImageBatch, IPAdapterFaceID, IPAdapterInsightFaceLoader, IPAdapterModelLoader, KSampler, LoadImage, PreviewImage, SaveImage, and VAEDecode.

Configuration

The listed base model is SDXL 1.0.
Model download information is available at https://huggingface.co/h94/IP-Adapter-FaceID/tree/main.

Cautions

The workflow details do not specify a license.

Does this need to be edited?

Sources

1 source

CivitaiPrimary

civitai.com/models/1023435

Verified Jul 20

Source excerpts

1 excerpt

NoteJul 20civitai.com/models/1023435

Source context: 915 downloads · Type Workflows · Base model SDXL 1.0