Skip to content
Docs menu

Image models

Wan2.7 Image

On this page

Wan2.7 Image — fast, high-fidelity AI image generation & editing.

modelIdwan-2-7-image, wan-2-7-image-pro
Modalityimage
PricingSee this model on the Pricing page for the current per-call price (with your markup).

Operations

OperationmodelIdEndpointRequired input
Imagewan-2-7-imagePOST /api/v1/generateprompt
Image Prowan-2-7-image-proPOST /api/v1/generateprompt
Poll taskGET /api/v1/task/{id}?model=wan-2-7-image

Image — wan-2-7-image

FieldTypeRequiredValues / example
promptstringYesText prompts for image generation. Supports both Chinese and English, with a minimum of 1 characters and a maximum of 5,000 characters. Max 5000 characters. (example: Create a scroll-stopping 3:4 vertical fashion advertising image for a fictional 2026 youth-culture campaign. MAIN CONCEPT: “LIQUID FUTURE” A striking Gen Z… — full value in the request example)
input_urlsstring[]NoUpload an image file to use as input for the API (image URL)
bbox_liststringNoDraw 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.
enable_sequentialbooleanNoEnable Gallery Mode (true/false) (default: false)
color_paletteobject[]NoOptional custom theme, 3-10 colours (8 recommended). Ratios must sum to 100.00%. Only available with Sequential Mode off. (array of { hex, ratio })
nnumberConditionalwhen `enable_sequential` is `false`: When the group image 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. (range 1-4) · when `enable_sequential` is `true`: When the group image 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. (range 1-12)
resolutionstringNoResolution of the generated image. Higher resolutions take longer to generate. (options: 1K | 2K) (default: 2K)
thinking_modebooleanNoEnhances reasoning for higher-quality outputs. Only available when Gallery Mode is off and no images are uploaded. May increase generation time. (true/false) (default: true)
aspect_ratiostringNoAspect ratio of the generated image (options: 1:1 | 3:4 | 4:3 | 1:8 | 8:1 | 9:16 | 16:9 | 21:9) (default: 1:1)
watermarkbooleanNoWhether to add a watermark identifier (true/false) (default: false)
seednumberNoUsing the same seeds and the same prompts for the same version of the model can keep the generated content relatively stable. (default: 0)
nsfw_checkerbooleanNoA configurable parameter. Defaults to true in the Playground. (true/false) (default: true)
bash
curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"wan-2-7-image","input":{"prompt":"Create a scroll-stopping 3:4 vertical fashion advertising image for a fictional 2026 youth-culture campaign.\n\nMAIN CONCEPT:\n“LIQUID FUTURE”\n\nA striking Gen Z fashion model fills most of the frame, photographed in an extreme high-fashion editorial style.\n\nThe model has realistic natural skin, subtle pores, slightly wet hair and a calm but intimidating expression, looking directly into the camera.\n\nShe wears a sculptural liquid-chrome fashion piece wrapping organically around the shoulders and upper body, combining polished mirror metal with transparent jelly-like material.\n\nBehind her, a gigantic translucent electric-lime gel form bends through the scene like a frozen liquid wave.\n\nSeveral chrome droplets float extremely close to the lens, creating dramatic depth and distorted reflections.\n\nThe image should immediately feel expensive, strange and unforgettable.\n\nCOMPOSITION:\nVery strong central hero image.\nClose-up fashion portrait.\nFace large enough to remain powerful as a small thumbnail.\nSlight ultra-wide lens distortion around the outer edges.\nForeground chrome object partially enters the frame.\nLarge clean negative space in the upper-left area for typography.\nControlled asymmetry.\nNo clutter.\n\nTYPOGRAPHY:\nRender only these exact words:\n\n“LIQUID\nFUTURE”\n\nLarge condensed black editorial typography in the upper-left corner.\n\nSmall text underneath:\n“2026 / MATERIAL STUDY”\n\nKeep all text perfectly spelled, sharp and clearly readable.\n\nCOLOR SYSTEM:\nelectric acid lime\nmirror chrome silver\ndeep black\nclean white\nnatural skin tones\n\nAvoid rainbow colors.\n\nLIGHTING:\nhard direct fashion flash combined with a large soft key light,\nbright specular highlights on chrome,\nrealistic translucent gel refraction,\nsharp catchlights in the eyes,\ndeep but clean shadows,\nsubtle analog film grain.\n\nMATERIAL QUALITY:\nextremely realistic polished chrome,\ntransparent soft gel,\nwet glass,\nsubtle skin moisture,\nhigh-end textile details,\nphysically believable reflections and refractions.\n\nART DIRECTION:\n2026 experimental fashion campaign,\nluxury advertising meets underground Gen Z culture,\nbold but minimal,\nsurreal without becoming fantasy,\nphysical and tactile rather than generic digital CGI,\nstrange enough to stop scrolling but sophisticated enough for a global fashion campaign.\n\nThe final image must work instantly as a thumbnail.\nThe face and liquid-chrome material are the main visual hook.\nTypography is secondary.\nOne unforgettable visual idea, not many competing ideas.\n\nPremium commercial photography.\nAward-level fashion art direction.\nPhotorealistic.\nExtremely polished.\nHigh visual tension.\n\nDo not add logos.\nDo not add extra text.\nDo not add random letters.\nNo cyberpunk city.\nNo generic neon background.\nNo excessive objects.\nNo cartoon look.\nNo distorted hands.\nNo plastic skin.\nNo cheap AI aesthetic.","input_urls":["https://you.bot/examples/grok-imagine-text-to-image.jpg"],"bbox_list":"example","enable_sequential":false,"color_palette":[{"hex":"example","ratio":"example"},{"hex":"example","ratio":"example"},{"hex":"example","ratio":"example"}],"n":4,"resolution":"2K","thinking_mode":true,"aspect_ratio":"1:1","watermark":false,"seed":0,"nsfw_checker":true}}'

Image Pro — wan-2-7-image-pro

FieldTypeRequiredValues / example
promptstringYesText prompts for image generation. Supports both Chinese and English, with a minimum of 1 characters and a maximum of 5,000 characters. Max 5000 characters. (example: Restyle into a warm hand-tinted vintage photograph, a sepia base with delicate hand-painted color on the artisan's hands and worn tools, soft film grain and a… — full value in the request example)
input_urlsstring[]NoUpload an image file to use as input for the API (image URL)
bbox_liststringNoDraw 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.
enable_sequentialbooleanNoEnable Gallery Mode (true/false) (default: false)
color_paletteobject[]NoOptional custom theme, 3-10 colours (8 recommended). Ratios must sum to 100.00%. Only available with Sequential Mode off. (array of { hex, ratio })
nnumberConditionalwhen `enable_sequential` is `false`: When the group image 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. (range 1-4) · when `enable_sequential` is `true`: When the group image 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. (range 1-12)
resolutionstringNoResolution of the generated image. Higher resolutions take longer to generate.(4K generation is available only for text-to-image in Standard Mode) (options: 1K | 2K | 4K) (default: 2K)
thinking_modebooleanNoEnhances reasoning for higher-quality outputs. Only available when Gallery Mode is off and no images are uploaded. May increase generation time. (true/false) (default: false)
aspect_ratiostringNoAspect ratio of the generated image (options: 1:1 | 3:4 | 4:3 | 1:8 | 8:1 | 9:16 | 16:9 | 21:9) (default: 1:1)
watermarkbooleanNoWhether to add a watermark identifier (true/false) (default: false)
seednumberNoUsing the same seeds and the same prompts for the same version of the model can keep the generated content relatively stable. (default: 0)
nsfw_checkerbooleanNoA configurable parameter. Defaults to true in the Playground. (true/false) (default: true)
bash
curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"wan-2-7-image-pro","input":{"prompt":"Restyle into a warm hand-tinted vintage photograph, a sepia base with delicate hand-painted color on the artisan's hands and worn tools, soft film grain and a gentle vignette.","input_urls":["https://you.bot/examples/grok-imagine-text-to-image.jpg"],"bbox_list":"example","enable_sequential":false,"color_palette":[{"hex":"example","ratio":"example"},{"hex":"example","ratio":"example"},{"hex":"example","ratio":"example"}],"n":0,"resolution":"2K","thinking_mode":false,"aspect_ratio":"1:1","watermark":false,"seed":0,"nsfw_checker":true}}'