Introduction
For larger NSFW canvases, Z-Image Spicy Pro exposes separate width and height controls from 256 to 2560 pixels, both starting at 1024.
Pro’s optional prompt expansion is disabled initially; switch enable_prompt_expansion on only when you want the written idea expanded before the large-frame generation.
Keep Pro’s canvas dimensions fixed when comparing a seed, since changing the frame also changes the composition; a repeated seed cannot promise identical output, and 0 selects randomness.
Spicy Pro’s 2560px controls apply to new images from text, with no image upload or negative prompt and no output-format selector.
Pro returns one generated asset after asynchronous completion, charged by image; request dimensions above the 1024 defaults explicitly when you need the larger canvas.
Z-Image Spicy Pro handles adult and ordinary image briefs through its large-frame endpoint without a maturity declaration or an added platform prompt scanner.
| Field | Value |
|---|---|
| Input | Text |
| Output | Image |
| Endpoint | Text to Image |
| Required input | Prompt (no character cap) |
| Dimensions | width and height set independently, 256-2560 pixels each (1024 default) |
| Prompt handling | Pro’s optional prompt expansion is disabled initially; switch |
| Reproducibility | Keep Pro’s canvas dimensions fixed when comparing a |
| Content policy | Z-Image Spicy Pro handles adult and ordinary image briefs through its large-frame endpoint without a maturity declaration or an added platform prompt scanner. |
Key features & highlights
2560 pixels a side, generated rather than upscaled
The whole difference from the standard Spicy tier is headroom: each side runs to 2560 instead of 1536. A 1728x2560 editorial portrait or a 2560x1440 hero comes out of the model at that size, so skin texture and fabric detail are rendered rather than interpolated by an upscaler afterwards.
Expansion stays off unless you ask for it
Pro’s optional prompt expansion is disabled initially; switch enable_prompt_expansion on only when you want the written idea expanded before the large-frame generation.
A dedicated uncensored tier, not a loosened general one
Unfiltered briefs use the same five inputs as other work here: prompt, width, height, enable_prompt_expansion and seed. Set the frame for its placement and leave expansion off when you want the model to receive your own wording.
Request parameters
| Parameter | Required | Description |
|---|---|---|
prompt | Yes | No character cap. Concrete description of light direction, fabric, palette and lens is used well at this size; adjective stacking is not. at least 1 characters |
width | No | Output width in pixels, 256 to 2560, defaulting to 1024. Keep the long side within roughly twice the short side unless you are writing the composition for a strip. |
height | No | Output height in pixels, 256 to 2560, defaulting to 1024. The large frame is opt-in — leaving this at the default is the usual reason a result comes back smaller than expected. |
enable_prompt_expansion | No | Pro’s optional prompt expansion is disabled initially; switch |
seed | No | Keep Pro’s canvas dimensions fixed when comparing a |
Pricing
$0.019 / image
Use cases
Uncensored editorial at full frame
High-key portraits, POV compositions and fashion editorial generated at 1728x2560 so the frame goes straight into a layout. No upscaling pass inventing skin detail that was never rendered.
Large-frame adult art on Spicy Pro
Uncensored wording passes through unchanged with expansion off, and the request looks identical to any other model here — create the task, poll, fetch the asset from platform storage. Nothing about uncensored work takes a different code path.
Large-format companion art
Character portraits for companion and role-play products at banner and full-bleed sizes, generated at the exact dimensions the interface uses rather than resampled up from a smaller square, so the face survives the trip to the screen.
Print-adjacent comps
2560x1440 and 2048x2560 give enough pixels for a comp that will be projected or printed small. Below that ceiling nothing needs an upscaler, which is where most uncensored pipelines lose texture.
Prompt guide & pro tips
Ask for the size you actually want
Both sides default to 1024, so the large frame this tier exists for only happens if you set it — 1728x2560 for a portrait, 2560x1440 for a hero. Anything from 256 up to 2560 is accepted on each side.
Write the full brief with expansion off
Write the lighting, fabric, pose and setting in concrete terms. The Pro example on this page uses a black satin top, silk trousers and a warm hotel lamp at 1728 × 2560. The brief below is the recorded prompt for that image; use the satin, lace trim and hands as details to inspect when adapting it.
Photograph of an adult woman in her thirties lying back across a hotel bed in an opaque black satin bralette with a thin scalloped lace trim along the edges and high-waisted black silk trousers, one arm above her head, looking at the camera with a slow smile. Low warm bedside lamp, city lights through the window, 50mm, soft film grain, editorial lingerie campaign.
Compare at the size you plan to deliver
Choose the delivery dimensions first. Accepted sizes currently share one per-image price, so a 1024-square draft does not reduce the cost of a call. Keep the seed and dimensions fixed while changing one part of the brief; budget by the number of variations. A seed of 0 requests a fresh draw.
For larger NSFW canvases, Z-Image Spicy Pro exposes separate width and height controls from 256 to 2560 pixels, both starting at 1024.
Pro’s optional prompt expansion is disabled initially; switch enable_prompt_expansion on only when you want the written idea expanded before the large-frame generation.
Keep Pro’s canvas dimensions fixed when comparing a seed, since changing the frame also changes the composition; a repeated seed cannot promise identical output, and 0 selects randomness.
Spicy Pro’s 2560px controls apply to new images from text, with no image upload or negative prompt and no output-format selector.
Pro returns one generated asset after asynchronous completion, charged by image; request dimensions above the 1024 defaults explicitly when you need the larger canvas.
Z-Image Spicy Pro handles adult and ordinary image briefs through its large-frame endpoint without a maturity declaration or an added platform prompt scanner.
Photograph of an adult woman in her thirties lying back across a hotel bed in an opaque black satin bralette with a thin scalloped lace trim along the edges and high-waisted black silk trousers, one arm above her head, looking at the camera with a slow smile. Low warm bedside lamp, city lights through the window, 50mm, soft film grain, editorial lingerie campaign.
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SPICY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "alibaba/z-image-spicy-pro/text-to-image",
"input": {
"prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.












