I trained this LoRa to recreate the style of artist Aomizuan, specifically from the doujin Koumi-jima ~Shuu 7 de Umeru Mesu-tachi~

It was trained with cleaned screenshots so you won't get any artifacts.

*Edit: I trained V2 on several images I generated by mixing some other models with and V1 together. Surprisingly the generated images of such a mix were closer to the original style that V1 so I decided to train and offer it as an update for those of you that like this artist's style.

V1 Activation Prompt: 40mizu4n

V2 Activation Prompt: 40mizu4nV2

Negative Prompt: keychain, lowres, worst aesthetic, (worst quality, bad quality, low quality:1.2), bad anatomy, old, signature, watermark, artist name, 3d

*This ^^^ negative prompt works best.

To get the same results like the sample images follow this prompting formula: Your Prompt + BREAK Prompt + LoRa

Break Prompt: BREAK character_concept, cowboy_shot, (dutch_angle:1.25), masterpiece, best quality, amazing quality, very aesthetic, absurdres, modern, recent, newest

Prompt Example: 1girl, solo, virgin ribbed sweater, destroyer sweater, dark violet green sweater, navel, thighhighs, smile, looking at viewer, library, thick thighs, wide hips, large breasts, curvy, BREAK character_concept, cowboy_shot, (dutch_angle:1.25), masterpiece, best quality, amazing quality, very aesthetic, absurdres, modern, recent, newest, <lora:Aomizuan_IL_Style_epoch_8:1> 40mizu4n

*This prompt formula works best if you are using reForge or StableDiffusion locally. Based on my tests it does not work as good if you generate them here on the site.

Weight: 1

Sampler: Euler a - Automatic

Recommended Base Models: WAI-NSFW-illustrious-SDXL V13

Make sure to post your favorite generations on the Gallery by simply clicking +Add Post button.