Anima seems to do impressively well on json formatted prompt

No cherry picking. These are the results of the json formatted prompt { "tags": "@eiichiro oda, score_9, score_8, score_7, high resolution, highres, absurdres, masterpiece, 2girls\/1boy, general, official art", "characters": [ { "girl1": "Nami \(One Piece\)", "appearance": "woman, orange hair tied to a ponytail, light skin, sweaty", "clothes": "white tanktop with blue trim and a number '0' printed on it, orange shorts", "action": "standing up, grinning, kawaii pose, peace sign" }, { "girl2": "Ni

More from StableDiffusion

Is this result possible using local models? What could they be using?

StableDiffusion·5

Phosphene — local video and audio generation for Apple Silicon ( LTX2.3 )

StableDiffusion·3

Comfyui Video Combine Plus

StableDiffusion·4

He created another self : Sci-Fi Short Film

StableDiffusion·5

Amazing style made using Ernie Image Turbo

StableDiffusion·5

SFW Prompt Pack - v4.0

StableDiffusion·3