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/text-to-image

Alibaba's Wan 2.7 text-to-image uses a reasoning pass to plan the composition before drawing. It returns one to four images per request at about 1 megapixel across seven aspect ratios, with a seed to steady comparisons.

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

From $0.03/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.

  • wasteland-three-depthsOutput
    wasteland-three-depths

    Built for the planning pass this endpoint runs before it draws: three figures placed on three distinct depth planes, focus held on the middle one, and a diagonal shaft crossing all three. Depth staging is what goes wrong when a composition is assembled greedily from the foreground inward - you get three subjects at the same distance. `resolution` is `2k` and `aspect_ratio` is `3:2`, wide enough for the planes to separate laterally as well as in depth.

    • 2k
    • 3:2
  • mirror-maze-second-figureOutput
    mirror-maze-second-figure

    A reflection puzzle rather than a lighting one: a run of mirrors in which the second figure is meant to appear only in the third reflection, with candlelight offset differently in every pane. That is a constraint the model has to hold across the whole frame at once, which is what the planning pass is for. `resolution` is `2k` and `aspect_ratio` is `3:4` so the run of mirrors recedes vertically. Count the panes before judging the result.

    • 2k
    • 3:4
  • cafe-povOutput
    cafe-pov

    The exact request behind the image on this page — one plain prompt at 1:1, no reference image and no content flag to set. It is also about as far as text alone goes.

    • 1:1
  • vineyard-backlitOutput
    vineyard-backlit

    The other two frames on this page are night interiors shot from the viewer's own seat; this one goes outside on a 200mm at golden hour, with the sun behind the subject so the light passes through thin linen and the silhouette reads through the cloth. Backlight through fabric is a much harder ask than a lamp in a room.

    • 1:1
  • taxi-back-seatOutput
    taxi-back-seat

    The second image on this page. Aspect ratio and seed left out entirely, so it runs at the 1:1 default — POV framing and film grain carried by the prompt alone.

This example starts at $0.03 per image. The Playground updates the estimate when you change the settings.