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
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 | ![]() | |
NovelAI | Driven by AI, painlessly construct unique stories, thrilling tales, seductive romances, or just fool around. Anything goes! | Proprietary | AI storyteller | Yes | ![]() |
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. | creativeml-openrail-m | Yes | ![]() | |
Trinart2 | Old trinart
https://huggingface.co/naclbit/trinart_characters_19.2m_stable_diffusion_v1 |
creativeml-openrail-m | No | ![]() | |
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 | ![]() |
beach, sea, sky, male, moustache, stomach, hands in air, masterpiece, artstation, dynamic pose, detailed face, chest hair, swimming trunksblurry, lowres, signature, broken anatomy, extra fingers, broken hand, ugly, bad face, abs, out of focus, deformed, gross proportions, creepy, public hair, female, Thong