Wan2.7 Image
wan / 2-7-image

Wan2.7-Image 是阿里巴巴推出的集生成与编辑于一体的图像模型系列,全面支持文生图、图像编辑、高级文本渲染及多图工作流。其标准版支持 2K 图像输出,Pro 版则支持高达 4K 的文生图功能。

Model Type:
Pricing: WAN-2.7 Image Pro costs 12 credits per image (≈ $0.06), while WAN-2.7 Image costs 4.8 credits per image (≈ $0.024). High-tier top-ups include +10% bonus credits. Effective pricing is approximately 10% lower than the above rates.
Input

Text prompts for image generation. Supports both Chinese and English, with a minimum of 1 characters and a maximum of 5,000 characters.

0/5000

Click to upload or drag and drop

Supported formats: JPEG, PNG, WEBP, JPG Maximum file size: 10MB; Maximum files: 9

Upload an image file to use as input for the API. Image dimensions must be at least 240 pixels in length and width.

Draw edit regions on each image. Coordinates are saved as [x1, y1, x2, y2] using the original image pixel coordinates. Each image supports up to 2 boxes.

0 boxes selected
Upload image(s) first, then add boxes for each image.

Enable Gallery Mode

Enhances reasoning for higher-quality outputs. Only available when Gallery Mode is off and no images are uploaded. May increase generation time.

When the gallery mode is turned off, n represents the number of generated images (1-4); when it is turned on, n represents the maximum number of images (1-12), and the actual value is determined by the model.

color_palette

Optional custom theme with 3 to 10 colors. Recommended: 8.

0 colors / 0.00%
Add 3 to 10 colors. Ratios must sum to 100.00%.

Resolution of the generated image. Higher resolutions take longer to generate.(4K generation is available only for text-to-image in Standard Mode)

Aspect ratio of the generated image

Whether to add a watermark identifier

Using the same seeds and the same prompts for the same version of the model can keep the generated content relatively stable.

A configurable parameter. Defaults to true in the Playground.

There is no guarantee that everything can be filtered out; if you are not satisfied with the results, you will need to make your own arrangements.
Output
output typeimage
Generated output
Examples

Explore different use cases and parameter configurations

README

Complete guide to using Wan2.7 Image

Kie.ai 上的高性价比 Wan2.7 图像 API

Original image
借助 Wan2.7-Image API 实现一站式的图像生成与编辑
Wan2.7 图像 API:个性化人像定制与逼真面部控制
Wan2.7 图像 Pro API:精准的调色板控制
Alibaba Wan2.7 图像 API 的高级文本渲染功能
通过 Alibaba Wan2.7 图像 API 实现多图编辑与交互控制
Alibaba Wan2.7 图像 API:灵活的 2K 和 4K 输出及 12 图一致性生成
参数Wan2.7 图像 APIWan2.7 图像 Pro API
Input imagesUp to 9 input imagesUp to 9 input images
Output size1K, 2K, and supported custom dimensions1K, 2K, 4K for text-to-image, and supported custom dimensions
Number of outputs1–4 outputs, or up to 12 when image set mode is enabled1–4 outputs, or up to 12 when image set mode is enabled
Thinking modein eligible text-to-image scenariosin eligible text-to-image scenarios
Interactive editing boxes✔✔
借助 Wan2.7-Image,打造更具竞争力的文生图体验
Wan2.7-Image:带来更全面、均衡的通用图像编辑体验

Wan2.7-Image API works well in fast-moving marketing and creative workflows where teams need to turn ideas into visuals without a long design cycle. It can be used for ad concepts, landing page graphics, social media images, promotional banners, and other campaign assets that start from a prompt and often need quick follow-up edits. Because Wan2.7-Image API combines generation and editing in one flow, it is especially practical for teams that want to move from rough visual exploration to more usable creative output without switching across multiple image tools.

Wan 2.7 Image API is a strong choice for portrait-focused products that need faces to feel more intentional and less generic. With more detailed control over bone structure, eye shape, contour, makeup, hairstyle, and accessories, Wan 2.7 Image API is well suited to avatar tools, profile image generation, beauty-related imaging experiences, and other portrait workflows where facial customization matters. This gives developers a better foundation for face-centered products that depend on more realistic, more varied, and more identity-sensitive visual output.

Wan2.7 Image Pro API is better aligned with visual workflows where output quality carries more weight than raw iteration speed. It is a stronger fit for premium campaign creatives, product marketing assets, branded illustrations, presentation visuals, and other design-heavy content that benefits from more polished text-to-image generation. Since Wan2.7 Image Pro API supports up to 4K in supported text-to-image scenarios, it is especially useful when the final visual needs to feel more refined for production-facing delivery rather than quick internal concepting.

Wan2.7 Image API is especially useful for workflows that depend on consistency across multiple outputs rather than one-off image generation. It can support storyboards, product catalogs, children’s books, wedding series, slide visuals, and other sequential content where the subject, styling, or scene logic needs to stay more coherent from image to image. With support for up to 12 consistent images in one generation and up to 9 reference images for more guided outputs, Wan2.7 Image API is a strong match for teams building visual storytelling tools and multi-image production workflows.

5.0/ 5
44,908 ratings
Tap a star to rate

Wan2.7 图像 API 是由阿里巴巴推出的图像模型系列,全面支持图像生成与图像编辑工作流。它可用于文生图创作、多图编辑、交互式编辑、高级文字渲染以及一致性多图生成,能够满足广泛的创意与生产场景需求。

主要区别在于输出质量与创作侧重点。Wan2.7 Image API 是标准版,专为更高效的日常图像生成与编辑而设计;而 Wan2.7 Image Pro API 则是进阶版,专注于提供更高质量的输出。在文生图方面,Pro 模型最高支持 4K 分辨率,标准版最高支持 2K。两款模型均支持图像编辑、适用场景下的思考模式(Thinking mode)以及多图工作流。

是的。Wan2.7-Image API 在同一模型系列下同时支持文生图和图像编辑功能。开发者不仅能通过提示词生成图像,还可以使用自然语言指令编辑现有图片,或引入参考图来实现更精准的视觉输出控制。相比纯生成类模型,这能让工作流更加灵活。

Wan2.7 Image API 与 Wan2.7 Image Pro API 均最多支持输入 9 张图片。在多图编辑、风格迁移、参考图融合等复杂工作流中,仅靠单一提示词往往无法精准把控最终效果,而该多图输入功能便非常实用。

是的。Wan2.7 图像生成 API 支持基于区域框选的交互式编辑,允许开发者在上传的图像上划定目标区域,并结合自然语言指令进行更精准的编辑。这非常适合物体替换、文字修改、排版调整及更多局部视觉编辑等工作流。

是的。开启图像集(Image Set)模式后,Wan2.7 图像生成 API 单次请求最多可生成 12 张图像。这非常适合分镜、产品目录、儿童绘本、幻灯片配图等对连续输出视觉一致性要求较高的工作流。

是的。在 Kie.ai 平台上,Wan2.7 图像生成 API 的定位不仅是提供模型调用接口,更是一套更实用的开发者解决方案。该方案包含了详尽的 Wan2.7 图像生成 API 开发文档,并为测试、集成和部署等工作流提供持续支持。这对于希望从 Playground 验证阶段更顺畅地过渡到实际生产环境中的团队来说尤其有用。