popnow
Sign inStart creating

alibaba/wan-2.7/editFrom 5 credits per image· Edit Image

Wan 2.7 image-to-image from Alibaba merges or edits one to nine reference images into a new image under a single instruction.

Call it with the model name alibaba/wan-2.7/edit on POST /jobs/createTask, from 5 credits per image ($0.05). New accounts get 30 free credits to try it in the Playground first.

  • Create Image
  • Edit Image
  • Up to 2K
  • Up to 9 reference images
  • 7 aspect ratios
  • Up to 4 per run
by AlibabaGet API keyWan 2.7 examples and prompts →

Introduction

Wan 2.7 Image to image reworks supplied imagery with a directed change. Use it when the source image contains details that must remain recognizable while a local or stylistic decision changes.

Choose a Wan 2.7 mode by starting material

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

Key features

The 9-image edit draws what you wrote

Give image-to-image a reference and it draws the brief you sent, wardrobe and framing included. On text-to-image it answers a restricted prompt with a more conservative frame instead. The cafe scene for this endpoint is text-to-image, an oversized white shirt with rain on the window, and that is roughly where the text endpoint stops.

Combine up to nine images without painting a mask

Image-to-image takes one to nine source images in a single request, so a garment, a face, a room and a colour reference can all enter the same edit. Say what each source is for in the prompt — an unlabelled stack gets averaged, which is the most common reason a nine-image edit comes back muddy.

It plans the layout before it draws

Wan 2.7 plans the frame before it draws it, which shows up in things that need a spatial decision: who is in the foreground, what the hand is holding, where the light source sits. Long descriptive prompts with a clear subject and one clear relationship beat keyword piles here.

Request parameters

ParameterRequiredDescription
aspect_ratioNoThe shape of the frame: wide, square or tall. 1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 3:2 · 2:3
bounding_boxesNoRectangles marking the areas to edit, in pixels from the top-left corner of the reference image each one belongs to. Up to 2 per image.
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.
image_urlsYesPhotos to edit or combine. Say in the prompt what each one adds.
num_outputsNoHow many results to make in one go. ≥ 1 · ≤ 4 · Default: 1
promptYesDescribe the image to produce from the source: subject, composition, style, and lighting.
resolutionNoOutput size. Bigger sizes look sharper and cost more. 1k · 2k · Default: 1k
seedNoReuse the same number to get a repeatable result. ≥ 0 · ≤ 2147483647

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
Standard4.5$0.045

Each task is rounded up to whole credits, so one run at the lowest tier costs 5 credits per image ($0.05).

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

Use cases

Adapt an approved image for a new campaign context

Send the approved image as the reference and name the one element that changes — the setting, the colour treatment, a prop — and everything that must not. Leave aspect_ratio out and the result follows the last reference's proportions.

Explore a controlled art-direction change

Send the packshot and a colour reference and ask for the glaze, fabric or finish to change while the linen, the props and the window light stay untouched. One call, no mask, and a fixed seed so the variant set stays comparable.

Prepare a consistent set of variations

Image-to-image takes one to nine references in a single call, so a garment, a face, a room and a colour reference can enter the same edit. Fix seed across the set so the only difference between two edits is the clause you changed.

Prompt guide & pro tips

State what must stay and what may change

Refer to the sources by position — image 1, image 2 — so the model knows which is the subject and which is the surface. Name what must stay identical first, then the change; an unlabelled stack of references gets averaged.

Keep the revision locally testable

Ask for one focused adjustment and compare it with the source.

Validate the source-dependent result

Each reference must be JPEG, PNG without transparency, BMP or WEBP, 240 to 8,000 pixels on each side, between 1:8 and 8:1 in shape and no larger than 20 MB. At the 1k default the edit is about one megapixel; set resolution to 2k for four times that.

API quick start

Call the Wan 2.7 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/edit 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/edit",
  "input": {
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "image_urls": [
      "https://media.popnow.ai/influencer/examples/marco.webp"
    ],
    "num_outputs": 1,
    "resolution": "1k"
  }
}'

# 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 API questions

How much does the Wan 2.7 API cost?

Wan 2.7 starts at 5 credits ($0.05) per image with Edit 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 in the API?

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

How many reference images can Wan 2.7 take?

Image-to-image accepts one to nine images in a single call, combined under one prompt. Text-to-image accepts none — it is a separate contract with no image_urls field.

How big is a Wan 2.7 image?

About 1.01 to 1.05 megapixels at the 1k default, and that budget is spread evenly across all seven aspect ratios, so a 16:9 frame is wider but not larger. Setting resolution to 2k gives about four times that. Wan 2.7 Pro starts at 2k and adds a 4k tier on text-to-image. On image-to-image, an edit that leaves the ratio out takes the last reference's proportions at the tier you picked.

Which aspect ratios are supported?

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 reference when you leave it out.

Can I get the same image twice?

A fixed seed helps control variation; identical results are not guaranteed.

What is the difference between Wan 2.7 and Wan 2.7 Pro?

Mainly canvas. Pro text-to-image runs at 2k by default, about 4 megapixels, and adds a 4k tier of about 16 megapixels that this family does not have. Pro image-to-image works at 2k, about 4 megapixels, and is tuned for multi-constraint edit prompts; this family edits at 1k unless you ask for 2k.

What are the limits of the Wan 2.7 API?

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

Can I try Wan 2.7 without writing code?

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

All Wan models

Wan 2.7 Pro adds a 4K canvas for text to image and 2K edits that hold longer instructions.

More about Wan 2.7