Well, after training myself and hesitating for a year or two, I finally decided to release this model.


This model does not require fixed recommended prompt words, nor is it bound to specific clothing, scenes, or characters. As long as there is a portrait in your image, you can put the trigger word into the prompt to use it.


If you haven't registered for RunningHub yet, you can follow the steps below to claim your follower benefits.

Click the avatar in the top right corner - Invitation Code - Enter the invitation code to get 1,000 RH Coins, and log in daily to get 100 coins.
Invitation code: rh-v0990

Local decoding is no longer supported on the domestic site. If you need local decoding, please visit the overseas site:
Registration link: Overseas version of RunningHub (decoding test workflow, VPN required):
https://www.RunningHub.ai/user-center/1936823199386537986/webapp/?inviteCode=rh-v0990

Follower benefit: Register to get 1,000 points, log in daily for 100 points, and enjoy 4090 to the fullest! Experience the super-powered charm of 48G!
If you don't have 1,000 points, bind the activation code in the top right corner and enter the invitation code rh-v0990 to claim it!

This model's materials were produced and organized using Tutu's Image & Video Prompt Annotator, with meticulous editing and processing applied to the materials. The model was trained using Tutu Trainer.

Tutu's Image & Video Prompt Annotator is an AI-driven image and video tagging tool. Specially optimized for model training tagging, it can batch-generate high-quality training datasets with one click and quickly reverse-engineer prompts for images and videos.

Tutu Trainer is a free LoRA training tool supporting model training, dataset management, model resource management, parameter presets, training checks, and pre-release organization. Its goal is to allow creators to train high-quality LoRA faster and more stably without repeatedly tinkering with environments and parameters.

Official website: https://zhaotutu.xyz/
Tutu Trainer: https://zhaotutu.xyz/downloads/tututrainer/
Tutu Annotator: https://zhaotutu.xyz/downloads/tutuannotator/
Bilibili: https://space.bilibili.com/431046154
YouTube: https://www.youtube.com/@zhaotutu/videos
X: https://x.com/bigpox12
Telegram: https://t.me/zhaotutu
TikTok: https://www.tiktok.com/@zhaotututu
GitHub: https://github.com/zhaotututu
Email: bigpox12@gmail.com
QQ: 331506796

Model Introduction
Tutu's Little Face - KREA2 / 图图的小脸蛋 - KREA2 is a universal face model LoRA for KREA2.

Trigger word: tutulianmo
Recommended weight: 0.5 - 1.0
Suggested starting weight: 0.75

Usage Tips:

Simply place the trigger word at the beginning of your prompt.

Example:
tutulianmo, an adult womanXXXXX

If you are using other character LoRA, clothing LoRA, or style LoRA, you can also add tutulianmo directly. It does not strictly bind to a specific character or outfit, but primarily influences the facial appearance.

For more generation examples, please refer to the example images.