Alibaba
Wan 2.7 Image
Generate a scene from text and specify how much of each color should appear. A weighted palette helps carry a campaign’s visual identity into a new 1K or 2K image.
alibaba/wan-2-7-imageBest for
- Create campaign artwork in specified color proportions
- Explore colorways for a packaging illustration
Technical details
Read the model documentation- API model ID
alibaba/wan-2-7-image- Provider
- Alibaba
- Modality
- Image
- Input
- Text prompt
- Output
- Image
- Endpoint
POST /v2/jobs- Workflow
- Text to image
Request parameters
promptstring · RequiredThe text prompt: what to generate, in plain language.
At least 1 character
sizeChoose a 1K or 2K square, or enter custom dimensions such as 1600*900. The default is 2K.
- 1K
- 2K
- Custom sizes need 589,824 to 4,194,304 pixels in total and an aspect ratio between 1:8 and 8:1.
color_palettearrayA color theme for the picture: 3 to 10 objects like {"hex": "#C2D1E6", "ratio": "23.51%"}, with each ratio written to two decimals and the ratios adding up to 100.00%.
3–10 items
enable_sequentialImage-set mode is not available here, so only false is accepted; output.count sets the number of pictures.
- false
seedintegerRandom seed, a whole number from 0 to 2147483647. The same seed with the same prompt and size gives a similar picture; left out, a random one is used.
0–2147483647
thinking_modeboolean · Default: trueWhether the model reasons before drawing, which improves the picture and lengthens the wait. On by default.
watermarkboolean · Default: falseWhether to add an "AI Generated" label in the bottom-right corner. Off unless you send true.
Pricing
| Billable unit and options | Rate (USD) |
|---|---|
| Per image | $0.03 |
Catalogue rates on 21 Nov 2026. Prices exclude VAT.
View in pricing catalogue