Alright, practice on your own, after struggling for one or two years, I finally decided to release this model.


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


If you haven't registered on RH yet, you can follow the steps below to claim fan benefits.

Click on the avatar in the upper right corner, then select "Invitation Code," enter the invitation code to get 1000 RH coins. You can also get 100 coins daily by logging in.
Invitation Code: rh v0990

The domestic site no longer supports local decoding. For local decoding, please visit the overseas site:
Registration link: Overseas RH (Decoding test workflow, requires VPN):
https://www.runninghub.ai/user center/1936823199386537986/webapp/?inviteCode=rh v0990

Fan benefits: Register to get 1000 points, log in daily to get 100 points, enjoy the power of 4090! Experience the super charm of 48G!
If you don't have 1000 points, bind the activation code in the upper right corner and enter the invitation code rh v0990 to claim it!

This model uses Tutu's image and video prompt word reverser to create and organize materials, and the materials are finely edited and processed. The model is trained using Tutu Trainer.

Tutu's image and video prompt word reverser is an AI-driven image and video annotation tool. It is specially designed for model training annotation optimization, capable of batch-generating high-quality training datasets with one click and quickly reversing image and video prompt words.

Tutu Trainer is a free LoRA training tool that supports 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 struggling 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 general face model LoRA for KREA2.

Trigger Word: tutulianmo
Recommended Weight: 0.5 - 1.0
Suggested Starting Weight: 0.75

Usage Suggestions:

Place the trigger word at the beginning of the prompt.

For example:
tutulianmo, an adult womanXXXXX

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

For more output examples, please refer to the sample images.