I cant get the same result, what am i missing? I'm already merging full pruned model 0.2 with the same trinart model 0.8 but still cant get the result, and the arstyle. Closer artstyle is when merging model around 0.3 instead of 0.2.
After a lot of tweak finally i get the the closer result with model NAI 0.75 + Trainart2 0.25 hash e7c39565 Can show me how you upscale this picture? Im new with upscaler so i can't get better result
I cant get the same result, what am i missing? I'm already merging full pruned model 0.2 with the same trinart model 0.8 but still cant get the result, and the arstyle. Closer artstyle is when merging model around 0.3 instead of 0.2.
After a lot of tweak finally i get the the closer result with model NAI 0.75 + Trainart2 0.25 hash e7c39565 Can show me how you upscale this picture? Im new with upscaler so i can't get better result
For upscaling I used the same exact model, prompt, negative prompt and CFG, but with DMP2 a Karras at 60 steps, denoising: 0.2, upscaler: ESGRAN_4x. Not sure if this is optimal, but it gives me reasonable results.
I have used Waifu Diffusion Demo and I have used these tags touhou Hakurei reimu 1girl blush breasts cleavage cowboy_shot crop_top gloves hair_ribbon hand_on_hip hands_on_hips heterochromia long_hair looking_at_viewer red_eyes red_hair ribbon skirt smile solo thigh_strap twintails virtual_youtuber yellow_eyes
Yes, I copied and pasted the tags from this post #4542 and forgot to remove heterochromia tag. also, I edited the image a bit before uploading it, especially the face which has generated a bad eye, and I edited a bit the hair and the midriff, no big deal.
2girls, long_hair, looking_at_viewer, (((pixel art))), frown, no clothes, nsfw, nude, nipples, red hair, blue hair, breast press, completely nude, sad, nsfw Negative prompt: ntonio Mora, Clive Barker, Egon Schiele, Ernst Ludwig Kirchner, By Francis Bacon, Frida Kahlo, Giuseppe Arcimboldo, Jean-Michel Basquiat, John Lasseter, John Wilhelm, Junji Ito, Kazuo Umezu, Laurie Lipton, Naoto Hattori, Otto Dix, deformed, bad anatomy, disfigured, mutation, mutated, extra limbs, ugly, fat, missing limb, floating limbs, disconnected limbs, long neck, long body, part of the head, mutated hands and fingers, intricate human hands fingers, poorly drawn hands, malformed hands, poorly drawn face, poorly drawn asymmetrical eyes, Steps: 60, Sampler: DPM2 Karras, CFG scale: 11, Seed: 372720024, Size: 512x768, Model hash: e6e8e1fc, Denoising strength: 0.5, Mask blur: 4
The idea of being able to turn a work into pixel art on the fly sounds really cool. Maybe in due time novelai will get better at it but now it doesn't seem to get it right most times.
