About this model

This model is capable of generating anime-style vividly colored hair, eyes, and skin, which are typically difficult to achieve using traditional realistic models. This allows for easy creation of "AI cosplayers" with striking visual features.

One of the advantages of this model is that it can be used with the character LoRA, which was trained using Anything-V3, without requiring any modifications.

By using the NAI-tag as a prompt, It is possible to create realistic images using prompts similar to those used with Anything-V3.

It is recommended to include phrases such as "best quality," "ultra high res," and "(photorealistic: 1.4)" as prefixes to the prompt.

Using a VAE is not necessary for this ckpt.

Do not use Restore faces.