Sign up free, get 10,000 credits

Starter credits added when you sign up.

User LoRA

Community DiT
Style

Toratora style[MOSS // Anima]

Toratora style[MOSS // Anima] - AI Model cover image

Sign up free, get 10,000 credits

Starter credits added when you sign up.

Uploaded at
Nov 3, 2026, 1:16 PM
Uses
310
Reviews
No reviews
Trigger Words

@ttaistyle

Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Description

本页面包含 MOSS 和 Anima 两个版本,请选择对应的使用说明。This page includes both MOSS and Anima versions. Please follow the instructions for your model._______________________________________________________________________________________推荐参数/Recommended SettingsFOR ANIMA:触发词/Trigger word: @ttaistyle权重/Recommended weight:0.7~1Sampler: er_sde + beta OR euler + normalCFG:4STEPS:30FOR MOSS:复杂场景,请提高CFG和步数,SFT例外。For complex scenes, increase the CFG and sampling steps,except when using SFT.触发词/Trigger word: @ttaistyle权重/Recommended weight:1~1.2Sampler: er_sde + beta OR euler + simpleCFG:3-5STEPS:30-50____________________________________________________________________________________MOSSV1.1和ANIMA同数据集训练,感觉依然欠拟合,我大概会再作尝试。Trained on the same dataset as ANIMA. It still feels underfit, though, so I’ll probably keep experimenting.请测试,如果有什么问题,请留言告知。Please test it and let me know in the comments if you encounter any issues.____________ANIMAV2:新增了些许数据集。修改了配方和使用了新的训练器,整体表现更好,指令遵从度改善,光影、画面、阴影也有一定改善。解决了马赛克容易出现的问题,但由于数据集基本全是有马赛克,所以你仍然要透过提示词稍作控制。added a small amount of new training data.Updated the training settings and switched to a new trainer, resulting in better overall performance, improved prompt adherence, and noticeable improvements in lighting, image quality, and shadows.Fixed the issue of mosaics appearing too frequently.However, since most of the training dataset contains mosaic censorship, you'll still need to use prompts to keep it under control.

Comments

Artwork made by Toratora style[MOSS // Anima]