Examples | Z-Image Turbo API — Uncensored NSFW Images in ~1s | SpicyAPI

alibaba/z-image-turbo/text-to-image

Z-Image from Alibaba's Tongyi team is a compact 6B text-to-image model that returns a photoreal frame in roughly a second. Prompts run up to 1,000 characters, in five aspect ratios, delivered as lossless PNG.

From $0.016/image

Run model View API

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

Output
vanity-mirror-before-curtain
- 3:4
- png
Output
skater-mid-air
Fast enough to treat as a scratchpad, which is what the subject is chosen for: a mid-air moment is a timing problem, and timing is found by re-running a short brief many times rather than by writing a longer one. The wording here stays well inside the 1,000-character `prompt` limit. `output_format` is `png`, the only option, so a keeper out of a long run goes straight on without a re-export; `aspect_ratio` is `3:4` to hold the whole body at the top of the arc.
- 3:4
- png
Output
gym-mirror-selfie
A square take on the request behind the still on this page: a snapshot brief that names the light source, the blur and the framing rather than asking for quality.
- 1:1
- png
Output
motel-pool-lounger
The request behind the second frame on this page, square this time: faded stock, halation and thick grain asked for by name, which is how you keep this model out of the glossy register.
- 1:1
- png
Output
north-window-portrait
The two frames above it ask for snapshot artefacts — motion blur, halation, thick grain. This one asks for the opposite: 85mm at f/1.8 by a north window, twin catchlights, every pore and stray hair resolved, no colour cast, no retouching. Same tier, and skin at this honesty is the harder half.
- 3:4
Output
detective-under-the-el
- 16:9
- png
Output
umbrella-over-a-stranger
- 4:3
- png
Output
lantern-keeper-sleeping-dragon
- 16:9
- png
Output
monolith-highway
- 16:9
- png
Output
glacier-cave-vaults
- 3:4
- png
Output
aurora-cabin-frozen-lake
- 16:9
- png
Output
midnight-ramen-counter
- 4:3
- png
Output
fox-in-first-snow
- 4:3
- png
Output
subway-freeze
- 3:4
- png
Output
watch-in-ice
- 3:4
- png
Output
android-noodle-counter
- 3:4
- png

This example starts at $0.01 per image. The Playground updates the estimate when you change the settings.