Fan Benefit: Click the top-right avatar - Invitation Code - Enter the invitation code to claim 1000 RH Coins, and log in daily for 100 coins
Invitation Code: rh-v0990

The domestic site no longer supports local decoding. For local decoding, please visit the overseas site:

Registration Link: Overseas version of RunningHub (Decoding test workflow, proxy required):https://www.RunningHub.ai/user-center/1936823199386537986/webapp/?inviteCode=rh-v0990
Fan Benefit: Register to get 1000 points, log in daily for 100 points, and fully enjoy 4090! Experience the super-powered charm of 48G! If you don't have 1000 points, bind the activation code in the top-right corner and enter the invitation code rh-v0990 to claim them!

If you want to train a model, but you don't even have a single decent image as source material, can this model still be made?

The answer is yes.

Ms. Elda Wanzhou doesn't have a single decent image across the entire web. I crafted this model by repeatedly studying the details from a two-second official PV video. It's been a long time since I spent two hours making a model, and the quality is super high.

This model was created using Tutu's Image & Video Prompt Annotator for materials, with meticulous editing and processing applied to the materials. Trained using Tutu Trainer.

Tutu's Image & Video Prompt Annotator is an AI-powered image and video annotation tool. Specially optimized for model training annotation, it generates high-quality training datasets in batches with a single click, quickly generating prompts for images and videos.

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 let creators train high-quality LoRA faster and more stably without constantly wrestling 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
This is an Elda Wanzhou character LoRA for Anima. Elda Wanzhou is from Zenless Zone Zero.

The model is mainly used to stabilize Elda Wanzhou's character appearance and outfit direction.

During testing, a weight of around 0.75 is relatively stable.

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

If you want to reproduce the character and outfit more stably, it is recommended to place the trigger word at the beginning of the prompt and include the main clothing elements.

Recommended Prompts

tutuwanzhou, best quality, score_7, score_9, sensitive, very aesthetic, ultra detailed,
cleavage, blue_eyes, cape, white_hair, heterochromia, black_gloves, yellow_eyes, fingerless_gloves, hair_ornament, large_breasts, very_long_hair, thigh_strap, asymmetrical_clothes, bodysuit, strapless,
high_heels, asymmetrical_footwear, mole_on_thigh, boots, black_footwear,

Negative Prompt:
worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts,

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