I'm blending an update to my model, and I'm curious which one is the most aware of different manga artist's styles. As it stands, my current blend is not very responsive to different artist prompts. I know NAI has decent coverage, but it gets diluted to almost nothing in my blend, by the time I mix the other models in. Does any other model that I can consider incorporating in compare? I know LORAs are all the rage now, but being able to do famous artstyles without needing to train/download new models would be nice to have.
Prompt
masterpiece, best quality, (((nsfw))), a beautiful Red haired woman in the style of (Toriyama Akira), 1girl, full body, armpits, 4k, 8k, hyper detailed, intricately detailed, flat colours, limited palette, (sketch:1.2), multiple views, multiple angles, ass, hips, hip focus, breast focus
Negative prompt
worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, signature, out of focus, lowres, bad anatomy, ((bad hands)), mutated hand, error, missing fingers, extra digit, fewer digits, cropped, large breasts, huge breasts, simple background, headpiece, loli, lolicon, poorly drawn, blurry, out of focus, lowres, giant, giantess, 3d, 3dcg, realistic, sketch
Anonymous Tue 10 Jan 2023 17:53:03 No.7103423
I'm blending an update to my model, and I'm curious which one is the most aware of different manga artist's styles. As it stands, my current blend is not very responsive to different artist prompts. I know NAI has decent coverage, but it gets diluted to almost nothing in my blend, by the time I mix the other models in. Does any other model that I can consider incorporating in compare?
I know LORAs are all the rage now, but being able to do famous artstyles without needing to train/download new models would be nice to have.