```
Holodayo aims to be a valuable resource for vtuber fans, artists, and content creators by producing accurate and detailed representations of their favourite vtubers.
Holodayo 3.0 is here, the next evolution of the holodayo model, crafted by Moescape AI and co-trained with Cagliostro Research Lab. By combining tag-based training with natural language understanding, Holodayo 3.0 delivers a sharper, more natural grasp of English than ever before.
Choose the variant that fits your needs:
- Epsilon Model (Stable): Reliable, proven, and built on the SDXL standard.
- V-Prediction Model (Experimental): Trying to push the boundaries with groundbreaking training designed to capture true dark and true light.
```
Description
Recommended settings:
- For optimal results, it's recommended to follow the structured prompt template: `1girl/1boy, character name, from what series, by artist name, everything else in any order.`
- Put `masterpiece, best quality, very aesthetic, absurdres` at the end of the prompt.
- Sampler steps should be around 25 to 30; 28 is the sweet spot.
- CFG scale should be around 5 to 7; 10 is fried, >12 is deep-fried.
- Euler Ancestral is highly recommended.
Holodayo XL utilizes special tags to steer the result toward quality, rating, creation date, and aesthetic. While the model can generate images without these tags, using them can help achieve better results.
Quality tags: masterpiece, best quality, great quality, good quality, normal quality, low quality, worst quality
Rating tags: safe, sensitive, nsfw, explicit
Year tags: newest, recent, mid, early, oldest
Aesthetic tags: very aesthetic, aesthetic, displeasing, very displeasing
Style token: yodayo
FAQ
Details
Downloads
1,954,770
Platform
Yodayo
Platform Status
Available
Created
5/10/2024
Updated
8/25/2025
Deleted
-