popnow
Sign inStart creating

alibaba/wan-2.7-pro/text-to-imageFrom 12 credits per image· Create Image

Wan 2.7 Pro is the large-canvas edition of Alibaba's Wan 2.7 image family. Text-to-image runs at 2k by default and adds a 4k tier of about 16 megapixels; image-to-image works at 2k and spends its budget on holding multi-constraint edit instructions.

Call it with the model name alibaba/wan-2.7-pro/text-to-image on POST /jobs/createTask, from 12 credits per image ($0.12). New accounts get 30 free credits to try it in the Playground first.

  • Create Image
  • Edit Image
  • Up to 4K
  • Up to 9 reference images
  • 7 aspect ratios
by AlibabaGet API keyWan 2.7 Pro examples and prompts →

Introduction

Wan 2.7 Pro Text to image turns a written art direction into a new image. Use it when composition, subject, lighting, and visual hierarchy need to be designed from a brief.

Choose a Wan 2.7 Pro mode by starting material

What you have at the startMode
a written visual briefWan 2.7 Pro Text to image
an image that needs a directed changeWan 2.7 Pro Image to image

Key features

Up to 4K, on text-to-image

Text-to-image here defaults to 2k, about 4 megapixels, and goes up to 4k, about 16 megapixels, where the standard family stops at 2k. Image-to-image works at 2k. That split is the point: reach for 4k when you are generating a hero frame that will be cropped or printed, not when you are recolouring a packshot.

Candlelight, skin and brushwork

The second frame for this endpoint is a painterly interior: a figure against a backlit folding screen, one candle and a glass of wine on a lacquer table. Soft falloff, visible brush texture and a face read at that size are the first things to collapse on a small canvas, and exactly what the larger one is for.

It keeps every clause of a long instruction

On image-to-image the extra capacity goes into following compound instructions — take this object, put it on that surface, match the second image's light, leave the condensation alone. The standard family drops one clause of an instruction like that more often than this one does.

Request parameters

ParameterRequiredDescription
seedNoReuse the same number to get a repeatable result. ≥ 0 · ≤ 2147483647
promptYesDescribe the image to generate: subject, composition, style, and lighting.
resolutionNoOutput size. Bigger sizes look sharper and cost more. 2k · 4k · Default: 2k
aspect_ratioNoThe shape of the frame: wide, square or tall. 1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 3:2 · 2:3 · Default: 1:1
color_paletteNoCustom colour theme: 3 to 10 colours, each with an optional share of the image in percent. Leave the shares empty to split them evenly.

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

OptionCredits per image≈ USD
Standard11.25$0.11

Each task is rounded up to whole credits, so one run at the lowest tier costs 12 credits per image ($0.12).

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Explore a visual concept before production

Use text-to-image when nothing has to survive from a source and the frame will be cropped, enlarged or printed. It runs at 2k by default, about 4 megapixels, and 4k gives about 16 megapixels; every ratio gets the same pixel budget.

Create a storyboard key image

Render the still at 4k, then feed it to a 4K image-to-video endpoint as the opening frame. Video resolution governs the render, not the source, so starting from a large sharp still is what keeps fabric and skin texture alive in the clip.

Establish a campaign visual system

A magazine-cover frame with legible masthead type and cover lines needs the larger canvas to keep the lettering crisp. Generate at 3:2 or 2:3, hold the seed, and iterate on the typography clause alone until the words come out clean.

Prompt guide & pro tips

Write composition before decoration

Describe the frame, then name the materials worth the canvas: leather, wet concrete, glass, printed type. Composition is planned before drawing, so one clear spatial relationship beats a keyword pile.

Hold the seed and change one clause per run

With the seed and every other input held, the draw stays steady, so the difference between two runs is what the changed clause did. Only then sweep aspect_ratio for the crops you need to deliver.

Review before reusing the image downstream

Text-to-image returns one image per request and invents a new face on each seed, so a specific person needs a reference and the image-to-image endpoint. When the output is only going to a feed or a thumbnail, Wan 2.7 does the same job on a smaller canvas.

API quick start

Call the Wan 2.7 Pro API in three steps

  1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
  2. Send the request. POST /jobs/createTask with model alibaba/wan-2.7-pro/text-to-image and an input object that follows the parameter table. The response returns a task ID straight away.
  3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "alibaba/wan-2.7-pro/text-to-image",
  "input": {
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "aspect_ratio": "1:1",
    "resolution": "2k"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

Wan 2.7 Pro API questions

How much does the Wan 2.7 Pro API cost?

Wan 2.7 Pro starts at 12 credits ($0.12) per image with Create Image, its cheapest task. Credits are the same as on the website (1 credit = $0.01), new accounts get 30 free credits, and failed tasks are refunded.

What is the model name for Wan 2.7 Pro in the API?

Put alibaba/wan-2.7-pro/text-to-image for Create Image; alibaba/wan-2.7-pro/edit for Edit Image in the model field of POST /jobs/createTask.

How much bigger is Wan 2.7 Pro?

On text-to-image, Pro defaults to 2k, about 4 megapixels and roughly four times Wan 2.7's 1k default, and adds a 4k tier of about 16 megapixels that the standard family does not offer. On image-to-image Pro works at 2k, about 4 megapixels, where Wan 2.7 edits at 1k unless you ask for 2k; its advantage there is holding longer, multi-part edit instructions.

How many reference images does the edit endpoint take?

One to nine, in a single call. Refer to them by position in the prompt — image 1, image 2 — so the model knows which is the subject, which is the surface and which is the colour reference.

Which aspect ratios are available?

1:1, 4:3, 3:4, 16:9, 9:16, 3:2 and 2:3. Text-to-image defaults to 1:1; image-to-image has no default and follows the last reference when you omit it. The pixel budget is the same for every ratio.

Does one request return more than one image?

No. One image per request on both endpoints. Build variant sets by looping seeds with everything else fixed.

What are the limits of the Wan 2.7 Pro API?

Resolutions: 2K · 4K; Aspect ratios: 1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 3:2 · 2:3; Prompt length (characters): 5,000. Requests outside these limits are rejected before anything is charged.

Can I try Wan 2.7 Pro without writing code?

Yes. The Playground runs Wan 2.7 Pro on your PopNow credits, needs no API key, and shows the matching code for every run.

All Wan models

Wan 2.7 renders at about 1 megapixel by default for less and returns up to four images per run; Pro is for the big canvas.

More about Wan 2.7 Pro