Apps Page Background Image
Workflows/Consistent Face v1.1

ContestConsistent Face v1.1

Save it for me
Operate
@
Tenofas
03/18/2025
ComfyUI
Image Generation
Portrait
AI Influencer
1 / 0
Detailed Introduction

Consistent Face v1.1

This workflow allows you to generate 9 portraits with a consistent face in 9 different poses.

It is very useful for creating AI-influencers or consistent characters for any other purpose.

The workflow will upscale by 3x an image and then generate 9 images (1024x1024) from it, this mean it has to process FaceDetailer, EyesDetailer, apply Skin Lora and apply Chin-fix Lora for 9 images.  This is why the whole generation will take very long.  It is normal.

How it works

(green nodes are the settings' nodes of the workflow you can change)

- Upload a reference 3x3 grid image (already provided).

- Set flux1-depth_dev_lora strength (default 0.75).

- Set FluxGuidance (default 4.0).

- Set Sampler and Scheduler (default euler/beta).

- Set Steps (default 35).

- Set Seed (random or fixed).

- Select an upscale model and set upscale_by 3 (default model 4x_RealWebPhoto_v4).

- Modify the prompt to describe in detail the subject's appearance (skin tone, physique, face shape, hair, and eyes).

- In the Step 2: Set the strength of the Skin LoRA (default 0.75)

- Set the dishonesty_factor for detail, lower negative numbers mean higher detail (default -0.05 - use this with care, it may change the image a lot!)

- Start generating the images.

- Sit down and relax.


Details
APPComfyUI(v0.3.23)
Update Time03/18/2025
File Space5.1 GB
Models2
Extensions17
About This Template

How it works

(green nodes are the settings' nodes of the workflow you can change)

- Upload a reference 3x3 grid image (already provided).

- Set flux1-depth_dev_lora strength (default 0.75).

- Set FluxGuidance (default 4.0).

- Set Sampler and Scheduler (default euler/beta).

- Set Steps (default 35).

- Set Seed (random or fixed).

- Select an upscale model and set upscale_by 3 (default model 4x_RealWebPhoto_v4).

- Modify the prompt to describe the subject's appearance in detail (skin tone, physique, face shape, hair, and eyes).

- In the Step 2: Set the strength of the Skin LoRA (default 0.75)

- Set the dishonesty_factor for detail, lower negative numbers mean higher detail (default -0.05 - use this with care, it may change the image a lot!)

- Start generating the images.

- Sit down and relax.