I run Stable Diffusion using A111’s webUI. The model is 0001SemiRealistic.
The prompt
1girl, (huge breasts:1.3), (nsfw:1.3), rainbow colored hair, liquid hair, long hair, floating hair, full body, flamenco dancing, sundress, liquid clothes, style-swirlmagic, water,waves, tsunami,tide,sea,water dress,fantasy, high contrast, ink strokes, explosions, over exposure, purple and red tone impression , abstract, ((watercolor painting by John Berkey and Jeremy Mann )) brush strokes, negative space, perfect lighting, perfect shading, stunning, beautiful, gorgeous, <lora:LiquidClothesV1fixed:1> <lora:epiNoiseoffset_v2-pynoise:1> <lyco:GoodHands-beta2:1.2> kkw-ph1
Negative prompt: closed eyes, BadDream, UnrealisticDream, FastNegativeEmbedding, kkw-ph1-neg
Steps: 30, Sampler: DPM++ 2M SDE Heun Exponential, CFG scale: 7, Seed: 1065894193, Size: 512x768, Hires upscale: 3, Hires steps: 10, Hires upscaler: 4x-UltraSharp
Wouldn’t be AI art without a little body horror!
Overall, I’m pretty happy with the gallery, considering the minimal effort needed to make it. Just one wildcard prompt and a wee bit of cherry picking.