I'm having a hard time recreating this prompt, do you generate at 1024x1920 or upscale there? Any other ideas for settings or variables I might be missing?
masterpiece, best quality, highest detail, solo, nsfw, embarassed, flushed, green eyes, dark hair, medium hair, shoulder length hair, cleavage, big breasts, nsfw, undressing, (anime screencap), red clothes
Negative prompt: 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, artist name
masterpiece, best quality, 8k, 1girl, standing, catgirl, cat ears, short black hair, portrait, green eyes, full body, petite, small breasts, looking at viewer, denim shorts, midrif,
Non: 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, artist name, large breasts, futa, extra limbs, (mutated hands and fingers),
uncensored, masterpiece, best quality,excessive cum, huge breasts,heart effects,(((Girl trembling with sexual climax))),(((motion lines))),cum on body,((squatting)),((girl on top)),penis,ejaculate,(sex),Nsfw, (wet),blonde hair,girl is grapping legs, fully naked,puffy vagina, in bedroom, open mouth, drivel, be breathless, blush, very humid, steam,pale white skin Negative prompt: low quality, bad art, bad anatomy, asymmetrical, censored, bad art, glasses, disfigured, no arms, extra arms, extra fingers, transsexual, multiple arms, more than two legs,monochrome Steps: 50, Sampler: Euler, CFG scale: 15, Seed: 1556087684, Size: 512x768, Model hash: e6e8e1fc, Denoising strength: 0.7, Clip skip: 2
I don't have the exact prompt or seed, but it was very similar to: monocolored, sketch, line-art, masterpiece, highest quality, high quality, highres, nude, trembling, skirt, pussy, nipples, detailed face+eyes, skinny, sweaty, (cumshot:1.3), (loli), (child:1.25), cute, detailed face and eyes, wavy hair, frills, aroused, by Jeremy Lipking, by (Alphonse Mucha:0.5)
Negative prompt: 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, out of focus, censorship, ugly, old, deformed, amateur drawing, odd, fat, morphing, black and white, realistic
to be honest I just use the arknights prompt to get the average looking foxgirl look drawn in the arknights style. I don't think its based off any arknights character that I know off(I dont play the game).
Oh. I got ya. Just confused me for a sec but you're good.
@Kuji, prompt mentions Arknights but this is tagged original. Is this based off of an Arknights character?
to be honest I just use the arknights prompt to get the average looking foxgirl look drawn in the arknights style. I don't think its based off any arknights character that I know off(I dont play the game).
1girl, ahoge, animal ear fluff, animal ears, blonde hair, blue eyes, blush, breasts, cat ears, cat girl, cat tail, collarbone, cum, cum in mouth, cum on body, cum on breasts, cum on hair, cum on tongue, eyebrows visible through hair, facial, gradient background, hair between eyes, jacket, long hair, long sleeves, looking at viewer, navel, open mouth, pantyhose, sitting, small breasts, solo, tail, tongue, tongue out, very long hair, wariza, white legwear, facing viewer Negative prompt: 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: 28, Sampler: Euler a, CFG scale: 6, Seed: 114517611, Size: 768x1024, Model hash: 925997e9, Batch size: 4, Batch pos: 2, Denoising strength: 0.55, Clip skip: 2, ENSD: -1
1girl, 1boy, ahoge, animal ear fluff, animal ears, blonde hair, blue eyes, blush, breasts, cat ears, cat girl, cat tail, collarbone, cum, cum in mouth, cum on body, cum on breasts, cum on hair, cum on tongue, eyebrows visible through hair, facial, gradient background, hair between eyes, jacket, long hair, long sleeves, looking at viewer, navel, open mouth, pantyhose, sitting, small breasts, solo, tail, tongue, tongue out, very long hair, wariza, white legwear, facing viewer, (sex_toy) Negative prompt: 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: 28, Sampler: Euler a, CFG scale: 11, Seed: 321322816, Size: 768x1024, Model hash: 925997e9, Batch size: 4, Batch pos: 3, Denoising strength: 0.55, Clip skip: 2, ENSD: -1
1girl, ahoge, animal ear fluff, animal ears, blonde hair, blue eyes, blush, breasts, cat ears, cat girl, cat tail, collarbone, cum, cum in mouth, cum on body, cum on breasts, cum on hair, cum on tongue, eyebrows visible through hair, facial, gradient background, hair between eyes, jacket, long hair, long sleeves, looking at viewer, navel, open mouth, pantyhose, sitting, small breasts, solo, tail, tongue, tongue out, very long hair, wariza, white legwear, facing viewer Negative prompt: 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: 28, Sampler: Euler a, CFG scale: 11, Seed: 4007248977, Size: 768x1024, Model hash: 925997e9, Batch size: 4, Batch pos: 1, Denoising strength: 0.55, Clip skip: 2, ENSD: -1
I know right? Although, this is one of my already-existing OCs and hence the clothing is not 1-to-1 as how it's supposed to be, but I am quite amazed at how closed I managed to get it.
I do get what you mean about using AI to design though, as I have created multiple character concepts even before NovelAI/Dall-E/Satble Diffusion etc. by using Waifulabs. These new models and tools are even better at designing though since you can choose what you need, but also have the option to get random results if you please.
I've spent many hours just drawing up ideas for a single character (and still happily do), so something like these AI tools coming along certainly streamlines the process a lot. My desire to draw will likely never go away, but I think it's great for people to have something to play around with and maybe even make the character of their dreams.
It's the accessibility that's really cool to me and I've really been enjoying seeing what people have been making, especially in the realm of OCs.
The ability to design or even create art involving OCs so easily is definitely a huge plus. I think I'll make one for myself.
I know right? Although, this is one of my already-existing OCs and hence the clothing is not 1-to-1 as how it's supposed to be, but I am quite amazed at how closed I managed to get it.
I do get what you mean about using AI to design though, as I have created multiple character concepts even before NovelAI/Dall-E/Satble Diffusion etc. by using Waifulabs. These new models and tools are even better at designing though since you can choose what you need, but also have the option to get random results if you please.
((1girl)), long hair, blue eyes, brown hair, gradient hair, full body, atmospheric perspective, glitch, backlighting, (best quality), (high resolution), (masterpiece)
((1girl)), long hair, blue eyes, brown hair, gradient hair, full body, atmospheric perspective, glitch, backlighting, (best quality), (high resolution), (masterpiece)
This is picked out from 400+ generated images. Inpaint and img2img used. Conclusion is, use SD to draw finger and toes count correct is hard, and not worth it.
