MOSS-Image guide

Official prompts › English text

Kazusa from Blue Archive at a Tokyo crosswalk

Kazusa from Blue Archive at a Tokyo crosswalk

One English paragraph of about 230 words: an anime character standing in a real, overcast Tokyo street. Mixing an illustrated character into a photographic scene is something the official samples return to often.

ModelMOSS-Image-Base
Size1184 × 1776
Steps50
CFG3
Shift5
SamplerEuler
Skip layer (negative branch)22
Seed3537712559
PromptEnglish text, 1,351 characters
Negative promptwatermark, bad anatomy

To get close in ComfyUI, use Base, Euler, 50 steps, CFG 3, shift 5 and skip layer 22 rather than the template's faster defaults. The same seed will not give the identical image outside the official pipeline.

Prompt

Download
A young anime woman, Kazusa from Blue Archive, stands still at the edge of a crowded Tokyo crosswalk outside a busy train station on a damp, overcast dusk. Her short dark hair with soft magenta inner highlights frames her face, cat ears perked slightly beneath her distinctive glowing pink halo. She wears an oversized charcoal wool coat over a beige knit hoodie, a short pleated black skirt, black crew socks, and scuffed loafers, with a canvas tote bag slung over her shoulder. She holds a wired earphone in one hand as if pausing her music, looking slightly sideways with a quiet, unguarded expression while the evening rush hour flows around her.

In the immediate foreground, a heavily motion-blurred commuter in a dark coat walks right past the lens, partially framing the edge of the shot and giving it the raw, accidental feel of a candid street photograph. Around and behind Kazusa, a bustling crowd of out-of-focus pedestrians moves across the wet asphalt crosswalk under the muted glow of neon department store signs, traffic signals, and concrete office buildings. The image blends Kazusa’s anime appearance seamlessly into a gritty, photorealistic modern city environment, using natural ambient dusk lighting, shallow depth of field, motion blur on the passing crowd, muted cool tones, and a cinematic sense of stillness amid urban chaos.

Image and prompt by the OpenMOSS team: assets/images/007 in the MOSS-Image repo (Apache 2.0).