Seedance 2.0 is here - create consistent, multimodal AI videos faster with images, videos, and audio in one prompt.

Try Now
Skip to main content
Available now on ModelsLab · Image Generation

Wan 2.7 Text To ImageImages From Text Prompts

Try Wan 2.7 Text To ImageAPI Documentation
Wan 2.7 Text To Image

Generate With Precision

Bilingual Prompts

English Chinese Support

Use English or Chinese prompts for Wan 2.7 Text To Image generation.

Batch Outputs

Up To Five Images

Request 1-5 variations per Wan 2.7 Text To Image API call for exploration.

Size Presets

HD Square Portrait

Select square_hd, portrait, landscape via image_size in Wan 2.7 Text To Image model.

Examples

See what Wan 2.7 Text To Image can create

Copy any prompt below and try it yourself in the playground.

City Skyline

“Futuristic city skyline at dusk, neon lights reflecting on glass towers, wide angle landscape, high detail, cinematic lighting”

Mountain Lake

“Serene mountain lake with clear water, surrounded by pine forests and snow-capped peaks, golden hour sunlight, photorealistic”

Abstract Geometry

“Geometric abstract art with interlocking shapes in blue and gold tones, minimalist composition, high contrast, square format”

Tech Product

“Sleek wireless earbuds on marble surface, studio lighting, product photography style, sharp focus, neutral background”

For Developers

A few lines of code.
Images. One API Call.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per image, no minimums
  • Python and JavaScript SDKs, plus REST API
API Documentation 
import requests


response = requests.post(
    "https://modelslab.com/api/v7/images/text-to-image",
    json={
  "key": "YOUR_API_KEY",
  "prompt": "A spooky Halloween-themed burger designed with a carved jack-o’-lantern pumpkin as the bun, glowing with fiery light inside. The burger contains multiple juicy beef patties, melted glowing cheese resembling fire, and fresh lettuce. Dark moody background with glowing orange bokeh lights, a wine glass, and a bottle adding to the eerie Halloween atmosphere. Highly detailed, cinematic, dramatic lighting, photorealistic style."
}
)
print(response.json())

FAQ

Common questions about Wan 2.7 Text To Image

Read the docs

Wan 2.7 Text To Image model generates high-quality stills from text prompts. Supports bilingual English-Chinese input with strong adherence. Ideal for marketing and concept art.

Send prompt, negative_prompt, image_size, max_images, seed via Wan 2.7 Text To Image API. Outputs up to five images with safety checker. Reproducible via seed.

Presets include square_hd, square, 4:3 portrait, 16:9 landscape. Custom width-height possible in some integrations. Up to 4K in pro variants.

Wan 2.7 Text To Image excels in prompt fidelity and bilingual support. Use as alternative for production stills over general models. Strong for text rendering too.

Negative prompts up to 500 characters steer unwanted elements. Enabled alongside main prompt in Wan 2.7 Text To Image API. Improves output control.

Set max_images 1-5 for variations in one request. Supports seed for reproducibility. Safety checker runs by default.

Ready to create?

Start generating with Wan 2.7 Text To Image on ModelsLab.

Try Wan 2.7 Text To ImageAPI Documentation