Skip to main content

Uncensored — This model declares no content filter. SpicyAPI forwards the request without adding a platform content scan; legal and consent duties remain with the customer. Image editing — Uncensored; Text to image — Softened.Browse every model at this filtering level
alibaba/wan-2.7-pro/text-to-image

Wan 2.7 Pro is Alibaba's large-canvas text-to-image model, returning one image per request at 2k (about 4 megapixels) or 4k (about 16 megapixels). It supports seven aspect ratios from 1:1 to 16:9 and 9:16, plus a seed and colour palette.

Filtering differs by endpoint: Image editing — Uncensored, Text to image — Softened.

From $0.075/image
Run model

Workbench

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.

  • robe-window-someone-behindOutput
    robe-window-someone-behind

    Run at the `2k` default to show what the standard tier holds in the shadows, which is where this frame lives: a dark room, city lights broken into points across skin, and a second figure readable only as a reflection in the glass. The whole composition depends on separating three near-black values - room, reflection, night outside. Sodium orange against night blue gives that separation a colour axis as well as a tonal one.

    • 2k
    • 3:4
  • airship-gondola-twoOutput
    airship-gondola-two

    `resolution` is `4k`, and the brief earns it in the foreground rather than in the subject: brass instrumentation and rivets held sharp a hand's breadth from the lens, while two backlit silhouettes overlap into a single shape behind. Fine repeated hardware is the honest test of a large canvas, since it either resolves as separate objects or turns to noise. `aspect_ratio` is `3:2` to keep both figures inside one porthole without cropping the instrument panel away.

    • 4k
    • 3:2
  • neon-garageOutput
    neon-garage

    The exact request behind the image on this page — specular leather and reflected neon at 1:1.

    • 1:1
  • opera-double-exposureOutput
    opera-double-exposure

    A photographic process, not a subject: two frames registered over one another, with stage lights and gilt ornament ghosted across a shoulder and the folds of a gown. The instruction has to say how much overlap is allowed — enough to read as a double exposure, not so much that the profile stops being legible.

    • 1:1
  • candlelit-screenOutput
    candlelit-screen

    The second image on this page, at the 1:1 default. Backlit paper, one candle and impasto brush texture — soft falloff is where the larger canvas pays for itself.

This example starts at $0.075 per image. The Playground updates the estimate when you change the settings.