Edit model card

AniPlus v1 is a Stable Diffusion model based on a mix of Stable Diffusion 1.5, Waifu Diffusion 1.3, TrinArt Characters v1, and several bespoke Dreambooth models. It has been shown to perform favorably when prompted to produce a variety of anime and semi-realistic art styles, as well as a variety of different poses.

This repository also contains (or will contain) finetuned models based on AniPlus v1 that are geared toward particular artstyles.

Currently there is no AniPlus-specific VAE to enhance output, but you should receive good results from the TrinArt Characters VAE.

AniPlus v1, from the leading provider* of non-infringing, anime-oriented Stable Diffusion models.
* Statement not verified by anyone.

Samples

All samples were produced using the AUTOMATIC1111 Stable Diffusion Web UI @ commit ac085628540d0ec6a988fad93f5b8f2154209571.

1girl, school uniform, smiling, looking at viewer, portrait
Negative prompt: nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
Steps: 15, Sampler: DPM++ 2S a, CFG scale: 11, Seed: 1036725987, Size: 512x512, Model hash: 29bc1e6e, Batch size: 2, Batch pos: 0, Eta: 0.69

AniPlus v1 Sample

1girl, miko, sitting on a park bench
Negative prompt: nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
Steps: 15, Sampler: DPM++ 2S a, CFG scale: 11, Seed: 3863997491, Size: 768x512, Model hash: 29bc1e6e, Eta: 0.69

AniPlus v1 Sample

fantasy landscape, moon, night, galaxy, mountains
Negative prompt: nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
Steps: 15, Sampler: DPM++ 2S a, CFG scale: 11, Seed: 2653170208, Size: 768x512, Model hash: 29bc1e6e, Eta: 0.69

AniPlus v1 Sample

semirealistic, a girl giving a thumbs up
Negative prompt: nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
Steps: 15, Sampler: DPM++ 2S a, CFG scale: 11, Seed: 2500414341, Size: 512x768, Model hash: 29bc1e6e, Eta: 0.69

AniPlus v1 Sample

What? Polydactyly isn't normal?

[semirealistic:3d cgi cartoon:0.6], 1girl, pink hair, blue eyes, smile, portrait
Negative prompt: nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
Steps: 15, Sampler: DPM++ 2S a, CFG scale: 11, Seed: 487376122, Size: 512x512, Model hash: 29bc1e6e, Batch size: 2, Batch pos: 0, Eta: 0.69

AniPlus v1 Sample

1boy, suit, smirk
Negative prompt: nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
Steps: 15, Sampler: DPM++ 2S a, CFG scale: 11, Seed: 4122323677, Size: 512x768, Model hash: 29bc1e6e, Batch size: 2, Batch pos: 0, Eta: 0.69

AniPlus v1 Sample

absurdres, semirealistic, a bunch of girls running in a marathon
Negative prompt: nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
Steps: 15, Sampler: DPM++ 2S a, CFG scale: 11, Seed: 2811740076, Size: 960x640, Model hash: 29bc1e6e, Eta: 0.69

AniPlus v1 Sample

The marathon test.

Downloads last month
5
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.