Anime styles in Stable Diffusion using a 3D model
Added 2022-11-14 14:33:44 +0000 UTCCheck out these prompts to help you generate better styles for Anime in StableDiffusion:
Use the Img2img tab with the presented video settings and your own 3D model.
Prompt keywords: (from below), cowboy shot, low angle foreshortening, anime screencap, 90's style, ((1990)), ((masterpiece)), ((best quality))
Negative words: Flat shading, flat color, bad anatomy, disfigured, deformed, malformed, mutant, gross, disgusting, out of frame, poorly drawn, extra limbs, extra fingers, missing limbs, blurry, out of focus, lowres, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, artist name, ((extra legs)), ((extra limbs)), ((twisted waist)), ((double head)), cloned head, blur
Happy ai-prompting!
-Pierre.
Comments
The Arcane trained model did not worked well for me, nor the Spiderverse. I am trying this last ont (Ghibli style): https://huggingface.co/nitrosocke/Ghibli-Diffusion
3DCinetv
2022-11-23 13:38:50 +0000 UTCI'll be running the ARCANE trained model with Fixy. Let's see where that take us. Also, the spiderverse model looks really good: https://huggingface.co/nitrosocke
3DCinetv
2022-11-15 09:20:32 +0000 UTC
