Captured photo
Z-Image Turbo
20 +

Gallery

Robotic storefront

Original prompt
Full prompt

Photorealistic architectural street photograph of an independent robot shop at blue hour. Create a striking MODERN storefront title design that reads exactly "ropewalk". Invent expressive, memorable lettering and integrate it thoughtfully into the architecture; the title should feel like an original design statement and remain clearly readable. Explore the typography, sign materials, lighting and facade creatively. A graphite-and-mint visual identity, intriguing robots visible through the shop window, a welcoming interior, believable urban details and subtle reflections on the pavement. Confident composition showing both the title and the character of the shop. Square image, no watermark.

Photorealistic architectural street photograph of an independent robot shop at blue hour. Create a striking MODERN storefront title design that reads exactly "ropewalk". Invent expressive, memorable lettering and integrate it thoughtfully into the architecture; the title should feel like an original design statement and remain clearly readable. Explore the typography, sign materials, lighting and facade creatively. A graphite-and-mint visual identity, intriguing robots visible through the shop window, a welcoming interior, believable urban details and subtle reflections on the pavement. Confident composition showing both the title and the character of the shop. Square image, no watermark.

Glass beetle

Original prompt
Full prompt

A translucent mint-glass mechanical beetle resting on black volcanic stone. Fine wires and tiny moving components visible inside its body, iridescent wings slightly open. Extreme macro photography, hard studio lighting, deep shadows, startling physical realism.

A translucent mint-glass mechanical beetle resting on black volcanic stone. Fine wires and tiny moving components visible inside its body, iridescent wings slightly open. Extreme macro photography, hard studio lighting, deep shadows, startling physical realism.

Street-fashion portrait

Original prompt
Full prompt

Editorial street-fashion portrait of a young adult Japanese woman in Tokyo, with the inventive, eclectic spirit of early-2000s Harajuku street style. Playful experimentation, unexpected combinations, expressive layering, bold color relationships and a strong sense of personal identity. Create an original, coherent look; choose her clothing, hairstyle, accessories and pose freely within that aesthetic. Full-length portrait with a strong composition and a natural, self-assured presence. Eye-level 35mm street photography, direct flash mixed with daylight, subtle film grain, honest skin texture and an informal documentary feel. Square image, no magazine layout or added captions.

Editorial street-fashion portrait of a young adult Japanese woman in Tokyo, with the inventive, eclectic spirit of early-2000s Harajuku street style. Playful experimentation, unexpected combinations, expressive layering, bold color relationships and a strong sense of personal identity. Create an original, coherent look; choose her clothing, hairstyle, accessories and pose freely within that aesthetic. Full-length portrait with a strong composition and a natural, self-assured presence. Eye-level 35mm street photography, direct flash mixed with daylight, subtle film grain, honest skin texture and an informal documentary feel. Square image, no magazine layout or added captions.

About

Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

Available controls: Width, Height, Go Fast, output_format, Guidance Scale, Output Quality, Num Inference Steps.

Settings

Seed-  Random seed. Set for reproducible generation
Width-  Width of the generated image
Height-  Height of the generated image
Go Fast-  Apply additional optimizations for faster generation
output_format-  Format of the output images
Guidance Scale-  Guidance scale. Should be 0 for Turbo models
Output Quality-  Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
Num Inference Steps-  Number of inference steps.