Fan benefits: Click the avatar in the upper right corner, enter the invitation code rh v0990 to claim 1000 RH coins; you can also receive 100 RH coins daily by logging in.
If the balance is not automatically credited, please bind/activate the invitation code in the upper right corner and enter rh v0990 to claim it.

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

Registration link: Overseas version RH (decoding test workflow, requires VPN):
https://www.runninghub.ai/user center/1936823199386537986/webapp?inviteCode=rh v0990

This model uses the Tutu Annotator for material annotation, combined with Banana 2 / Banana Pro for assisted annotation, and the Tutu intelligent subject filtering function for tag cleanup. Training is completed using the Tutu Trainer and Tutu Training Workflow.

Tutu Annotator is an AI-driven image and video annotation tool optimized for model training annotation. It can batch-generate high-quality training datasets and quickly reverse-engineer 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 allow creators to train high-quality LoRA models faster and more stably without repeatedly tweaking environments and parameters.

Tutu's HiSilk Black Accessories Jumpsuit Z Image workflow is bound with the "Tutu's HiSilk Black Accessories Jumpsuit Z Image Turbo" LoRA, which can be opened for online model effect testing.

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


Recommended usage

It is recommended to start testing LoRA weights at around 0.7.
If the effect is too weak, you can appropriately increase the weight; if the texture is too strong or affects other parts of the image, first lower the LoRA weight instead of stacking many negative prompts at the beginning.