Wan 2.7 Image Text to Image API

alibaba/wan-2.7/text-to-image

6 preset sizes / custom size · 1–4 images

Wan 2.7 Image Text to Image transforms natural language prompts into high-fidelity 1K and 2K images, with Thinking Mode spatial reasoning, bilingual typography rendering, and palette-guided color control. It strictly adheres to prompt physical laws and spatial layouts while rendering authentic lighting textures and rich details.

Get API Key

Input

Prompt

716/5000

Size

Output count

Seed

OutputReady

Continue with

Wan 2.7 Image Edit Wan 2.7 Image Pro Text to Image Wan 2.7 Text to Video

Examples

Photorealistic quiet old railway waiting room, warm late-afternoon sunlight, worn wooden benches and cream plaster. A large dark green timetable board is the main focal point, nearly front-facing and occupies half the frame. Render ONLY these five lines of crisp, large, correctly spelled lettering on the board: "列车时刻 / TIMETABLE", "松林 / PINES 08:20", "湖畔 / LAKESIDE 10:45", "山谷 / VALLEY 16:30", "一路平安 / SAFE JOURNEY". Carefully aligned rows with consistent spacing, all lettering readable. Authentic painted enamel, subtle scratches, dust in the light, cinematic but restrained composition. No other visible text, people, promotional graphics or extra boards. No advertising, brands, logos, watermark, or foxes.

Natural wildlife photograph at eye level of one roseate spoonbill foraging in a salt marsh. Its long flattened spoon-shaped bill touches the shallow water; anatomically correct slender legs and layered pale pink feathers, subtle crimson shoulder patch. One bird only, no duplicates. Pale salt grasses, small ripples and a coherent reflection, layered muted blue-green estuary in the distance. Soft overcast morning light and delicate feather detail, unposed natural behavior. No writing. No advertising, brands, logos, watermark, or foxes.

Candid documentary portrait of a silver-haired woman in her seventies considering a chess move at an outdoor stone chess table in a leafy neighborhood square. Distinctive deep smile lines, short wavy white hair, ochre cardigan, natural skin texture. Her right hand gently holds one wooden knight between thumb and index finger above the board; her left rests on the edge of the table. Believable fingers and wrists, restrained thoughtful expression. Green plane-tree shade with soft sunlight, intimate waist-up composition, no other people or text. No advertising, brands, logos, watermark, or foxes.

REST API

Quick Start

This flow submits one valid Wan 2.7 Image Text to Image request, captures its task_id, and reads image URLs after the asynchronous task ends.

Connect to the Vidgo API

Create an API key, keep it on the server, and send it as Authorization: Bearer VIDGO_API_KEY.

Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authentication: Authorization: Bearer VIDGO_API_KEY

Submit one image task

Send the current model ID, prompt to the unified submit endpoint. The example keeps only first-call fields.

Submit request

curl --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "alibaba/wan-2.7/text-to-image",
  "input": {
    "prompt": "Photorealistic quiet old railway waiting room, warm late-afternoon sunlight, worn wooden benches and cream plaster. A large dark green timetable board is the main focal point, nearly front-facing and occupies half the frame. Render ONLY these five lines of crisp, large, correctly spelled lettering on the board: \"列车时刻 / TIMETABLE\", \"松林 / PINES  08:20\", \"湖畔 / LAKESIDE  10:45\", \"山谷 / VALLEY  16:30\", \"一路平安 / SAFE JOURNEY\". Carefully aligned rows with consistent spacing, all lettering readable. Authentic painted enamel, subtle scratches, dust in the light, cinematic but restrained composition. No other visible text, people, promotional graphics or extra boards. No advertising, brands, logos, watermark, or foxes.",
    "size": "1024x768",
    "n": 1,
    "seed": 270901
  }
}'

Wait for the image result

Read data.task_id and poll only while status is not_started or running. Stop on both finished and failed.

Track status

GET https://api.vidgo.ai/api/generate/status/{task_id}

Poll every 2–5 seconds and back off on 429/5xx. Or provide top-level callback_url to receive a terminal-state callback.

not_startedrunningfinishedfailed

Submit response

{
  "code": 200,
  "data": {
    "task_id": "V28RKQPZTHYDE4G9",
    "status": "running",
    "created_time": "2026-09-24T15:49:49"
  }
}

Finished response

{
  "code": 200,
  "data": {
    "task_id": "V28RKQPZTHYDE4G9",
    "status": "finished",
    "files": [
      {
        "file_type": "image",
        "file_url": "https://cdn.vidgo.ai/apis/models/alibaba/wan-2.7/text-to-image/v1/01/output.jpg"
      }
    ],
    "created_time": "2026-09-24T15:49:49",
    "error_message": null,
    "progress": 100
  }
}

Complete runnable polling example

Expand for the same payload end to end, including business-code, missing-task-ID, failed-state, unexpected-state, and network-error handling.

Complete runnable polling example

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "alibaba/wan-2.7/text-to-image",
  "input": {
    "prompt": "Photorealistic quiet old railway waiting room, warm late-afternoon sunlight, worn wooden benches and cream plaster. A large dark green timetable board is the main focal point, nearly front-facing and occupies half the frame. Render ONLY these five lines of crisp, large, correctly spelled lettering on the board: \"列车时刻 / TIMETABLE\", \"松林 / PINES  08:20\", \"湖畔 / LAKESIDE  10:45\", \"山谷 / VALLEY  16:30\", \"一路平安 / SAFE JOURNEY\". Carefully aligned rows with consistent spacing, all lettering readable. Authentic painted enamel, subtle scratches, dust in the light, cinematic but restrained composition. No other visible text, people, promotional graphics or extra boards. No advertising, brands, logos, watermark, or foxes.",
    "size": "1024x768",
    "n": 1,
    "seed": 270901
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

while true; do
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep 2
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Request Parameters

This table lists only public fields inside input. See Quick Start for top-level model and optional callback_url usage.

Field	Type	Required	Default	Description
input.prompt	string	Yes	–	String, 1–5,000 characters after trimming.
input.size	string \| object	No	1024x1024	Six preset sizes, or an object such as {"width":1280,"height":720}. Width and height must be positive integers.
input.n	integer	No	1	Output image count, integer 1–4. Credits = per-image rate × n.
input.seed	integer	No	–	Optional integer, omitted when unset. The upstream documentation specifies no numeric range.

Response Fields

The submit response identifies the task. The status response supplies image files or failure details at a terminal state.

Field	Type	Description
code	integer	Business response code; 0 or 200 indicates success.
message	string	Optional human-readable response message.
data.task_id	string	Unique task ID used for status queries after submission.
data.status	string	not_started, running, finished, or failed.
data.created_time	string	Task creation timestamp.
data.progress	integer	Progress from 0–100 in status responses.
data.files[]	array	Generated files in returned order when finished.
data.files[].file_url	string	Direct generated-image URL.
data.files[].file_type	string	Image results are identified as image.
data.files[].watermark_url	string \| null	Optional watermarked-file URL when present.
data.error_message	string \| null	Readable failure reason for failed tasks.

Task Lifecycle

Only the first two states may be polled again. finished and failed are terminal.

not_started
Accepted and queued; wait before checking again.
running
Image generation is in progress; continue polling.
finished
Successful terminal state; validate files and read image URLs.
failed
Failure terminal state; read error_message and stop.

Polling and Errors

Authentication401 means the key is missing or invalid. Fix authentication before resubmitting and never expose the key in browser code.
Validation400 indicates an invalid model ID, field, enum, length, or image count.
Polling intervalStart at 2–5 seconds, use exponential backoff for 429/5xx, and enforce an overall timeout.
Terminal statesStop after finished or failed. Treat finished without a valid image as a separate error.
Callback optionProvide a public top-level callback_url to receive a flat task object after finished or failed.
Network errorsDistinguish request timeout, network failure, and task failure. Retry the same query only when safe.

Model Specifications

Specification	Value	Details
Input mode	Prompt	Edit preserves the reference-image order.
Size	512x512, 1024x1024, 768x1024, 1024x768, 576x1024, 1024x576	Default: 1024x1024; custom positive integer width and height are supported.
Output count	1–4	Integer; default: 1.
Seed	integer	Optional; the upstream specifies no numeric range.
Billing	4.2 credits per output image ($0.021). Total credits = 4.2 × n. Size and reference images add no charges. 1 credit = $0.005.	1 credit = $0.005.

Wan 2.7 Image Text to Image API documentation

Wan 2.7 Image Text to Image Overview

Wan 2.7 Image Text to Image is a high-performance text-to-image model developed by Alibaba Tongyi Lab. Built on a unified multimodal planner and diffusion transformer (DiT) architecture, it analyzes multi-object layout and prompt nuances through an integrated chain-of-thought phase prior to synthesis. The model supports 6 preset aspect ratios as well as custom pixel dimensions, excelling in multi-line typography, brand color accuracy, and realistic portrait skin rendering for high-volume concept art, advertising, and marketing assets.

Why Choose

Thinking Mode Spatial ReasoningAnalyzes multi-object relationships, depth layers, and occlusion constraints during a built-in reasoning stage before pixel synthesis, ensuring coherent compositions for complex prompts.
Bilingual In-Image TypographyEliminates distorted AI lettering by directly rendering sharp, legible Chinese and English text, paragraphs, and slogans with crisp typographic outlines.
Palette-Guided Color & Extreme Aspect RatiosAccepts hex color arrays for precise brand palette adherence and natively accommodates extreme 1:8 to 8:1 aspect ratios for panoramic banners and vertical scrolls.

Parameters

Parameter	Requirement	Description
prompt	Required	String, 1–5,000 characters after trimming.
size	Optional	Six preset sizes, or an object such as {"width":1280,"height":720}. Width and height must be positive integers. Default`1024x1024512x512768x10241024x768576x10241024x576`
n	Optional	Output image count, integer 1–4. Credits = per-image rate × n. Default`1`
seed	Optional	Optional integer, omitted when unset. The upstream documentation specifies no numeric range.

How to Use

Compose Prompt and Typography TextDescribe visual subjects and lighting in detail, enclosing any desired banner text in quotation marks and specifying color preferences.
Select Dimensions and CountChoose a preset aspect ratio or enter custom dimensions, then specify output count from 1 to 4.
Submit Task and Fetch OutputsSubmit request to the unified API endpoint, track task_id status asynchronously, and retrieve final image URLs.

Pricing

4.2 credits per output image ($0.021). Total credits = 4.2 × n. Size and reference images add no charges. 1 credit = $0.005.

Usage	Rate	Details
Standard	4.2 credits/image · $0.021	Multiply by output count n; credits are refunded for failed tasks.

Use Cases

Commercial Ads & Social Media BannersRender crisp promotional text and brand palettes directly inside high-resolution marketing visuals.
E-Commerce Concept Sets & StagingPlan spatial placement and realistic light reflections for believable merchandise settings and editorial lookbooks.
Panoramic Layouts & Digital ArtLeverage extreme 1:8 to 8:1 ratios to design website hero headers, long infographic scrolls, and visual storytelling boards.

Tips

Optimize Typography Rendering: Place text phrases inside quotation marks (e.g., a billboard reading "SUMMER SALE") and state font style and placement clearly.
Activate Spatial Reasoning: Specify spatial positions like "in the foreground left" or "behind the counter" to help the reasoning planner allocate scene composition.
Maintain Visual Series Consistency: Fix the seed number across prompts with matching lighting terms to generate cohesive visual asset packs.

Notes

Text-Only Input: This endpoint accepts text prompts only; use Wan 2.7 Image Edit when reference images are needed.
Character Count Boundary: Prompts must contain between 1 and 5,000 characters after whitespace trimming.
Output Quantity Range: Parameter n accepts integers 1 to 4, with billing scaling linearly per generated image.

Related Models

Qwen Image 3.0 Text-to-ImageAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Qwen Image 3.0 Image EditAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Qwen Image 3.0 Pro Text-to-Image preview

Qwen Image 3.0 Pro Text-to-ImageAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Qwen Image 3.0 Pro Image EditAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Seedream 5.0 Pro Text-to-ImageThe ByteDance Seedream 5.0 Pro API generates 1K or 2K JPEG/PNG images from prompts and edits one to ten ordered HTTP(S) image inputs.

Seedream 5.0 Pro Image EditThe ByteDance Seedream 5.0 Pro API generates 1K or 2K JPEG/PNG images from prompts and edits one to ten ordered HTTP(S) image inputs.

GPT Image 2 Text-to-ImageOpenAI image generation and editing with quality tiers, flexible size controls, and single-image outputs up to 4K.

GPT Image 2 Image EditOpenAI image generation and editing with quality tiers, flexible size controls, and single-image outputs up to 4K.

Nano Banana 2 Text-to-ImageGoogle's next-gen image model powered by Gemini 3.1 Flash with native 2K/4K resolution, chain-of-thought reasoning, precise multi-language text rendering, and up to 14 reference images.

Nano Banana 2 Image EditGoogle's next-gen image model powered by Gemini 3.1 Flash with native 2K/4K resolution, chain-of-thought reasoning, precise multi-language text rendering, and up to 14 reference images.

Nano Banana Pro Text-to-ImageGoogle's Nano Banana Pro image model powered by Gemini 3 Pro for 4K generation, strong text rendering, multi-image blending, and production-ready image editing.

Nano Banana Pro Image EditGoogle's Nano Banana Pro image model powered by Gemini 3 Pro for 4K generation, strong text rendering, multi-image blending, and production-ready image editing.

GPT Image 1.5OpenAI's latest image model with 4x speed, precision editing, and superior text rendering.

Z-ImageAlibaba's efficient 6B-parameter image model with sub-second generation and exceptional Chinese-English bilingual text rendering capabilities.

Seedream 4.5ByteDance's unified 4K image generation and editing model with professional-grade text rendering and commercial photography quality.

Seedream 5.0 LiteByteDance Seedream 5.0 Lite family on Vidgo API: seedream-5.0-lite for text-to-image and seedream-5.0-lite-edit for image-to-image editing, with 2K/3K presets, custom sizes, and up to 10 reference images.

Wan 2.7 Image Text to Image API FAQ

What is the Wan 2.7 Image Text to Image API?

Wan 2.7 Image Text to Image is an Alibaba Tongyi Lab model for high-fidelity image generation from text prompts. It produces sharp 1K and 2K visuals with Thinking Mode spatial reasoning, bilingual typography rendering, and palette-guided color control. Built on a unified multimodal planner and DiT architecture, it preserves coherent physical laws and spatial arrangements while delivering authentic lighting textures. You can call it programmatically or try it from the playground above.

Can Wan 2.7 Image Text to Image generate multiple images in one request?

Yes. Setting parameter n between 1 and 4 outputs up to four distinct visual variants simultaneously. Each image maintains full quality and resolution, billed at 4.2 credits per output image.

Does Wan 2.7 Image Text to Image render legible text in images?

Yes. The model incorporates specialized multilingual glyph comprehension, rendering sharp Chinese and English words, titles, and signage directly inside the scene when enclosed in quotation marks.

How do I customize aspect ratio and resolution in Wan 2.7 Image Text to Image?

You can select from 6 preset options (including 1:1, 16:9, 9:16, 4:3, and 3:4) or pass a custom {width, height} object with positive integer pixel values, spanning ratios from 1:8 to 8:1.

How does Thinking Mode work in Wan 2.7 Image Text to Image?

When processing dense or multi-subject prompts, an internal reasoning stage analyzes spatial arrangements, perspective depth, and object interactions before diffusion begins to guarantee composition balance.

Can I use a fixed seed to reproduce images with Wan 2.7 Image Text to Image?

Yes. Providing an integer in the optional seed parameter preserves the initial latent noise layout, allowing you to fine-tune prompts while maintaining consistent composition structures.

How does billing work if a generation task fails?

Vidgo provides an automatic credit refund guarantee. If a task fails due to validation errors, network interruption, or processing timeout, all deducted credits are immediately returned to your account balance.