Ai art wiki is a free online encyclopedia, created and edited by volunteers. If you see wrong or missing information, feel free to edit it. Guidelines

Comparison of anime text-to-image models

From AI art wiki
Jump to navigation Jump to search

This page covers differences between most common base (not mixes) anime models.

Key Description License Extra features NSFW Samples
Waifu Waifu Diffusion is a latent text-to-image diffusion model that has been conditioned on high-quality anime images through fine-tuning.

Based on Stable Diffusion https://github.com/harubaru/waifu-diffusion

Code: AGPL-3.0 license

Weights: CreativeML Open RAIL-M

Yes Normal.jpg
NovelAI Driven by AI, painlessly construct unique stories, thrilling tales, seductive romances, or just fool around. Anything goes!

https://novelai.net/

Proprietary AI storyteller Yes Nai.jpg
Anything_v3 Welcome to Anything V3 - a latent diffusion model for weebs. This model is intended to produce high-quality, highly detailed anime style with just a few prompts. Like other anime-style Stable Diffusion models, it also supports danbooru tags to generate images.

https://huggingface.co/Linaqruf/anything-v3.0

creativeml-openrail-m Yes 1girl.png
Trinart2 Old trinart

https://huggingface.co/naclbit/trinart_characters_19.2m_stable_diffusion_v1

creativeml-openrail-m No Trinart samples.jpg
Derrida Derrida (formerly TrinArt Characters v2) is a stable diffusion anime models that aims to produce pictures of characters with anatomical accuracy, but without explicit content.

https://huggingface.co/naclbit/trinart_derrida_characters_v2_stable_diffusion

creativeml-openrail-m No Derrida.jpg