Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt

Use this file to discover all available pages before exploring further.

Wan2.7 Image is Alibaba’s latest multimodal image model available through Anyfast. It supports text-to-image, image editing, interactive region editing, and group image generation, with up to 4K output resolution.

​
Models

Model IDDescription
wan2.7-image-proProfessional variant. Supports 4K output for text-to-image.
wan2.7-imageStandard variant. Faster generation speed.

​
Key capabilities

  • Text-to-image — Generate images from text prompts
  • Image editing — Edit an existing image guided by a text prompt (0–9 input images)
  • Interactive editing — Edit specific regions using bounding boxes (bbox_list)
  • Group image generation — Generate multiple related images in one request (enable_sequential)
  • Thinking mode — Enhanced reasoning for better quality in text-to-image

​
Quick example

curl https://www.anyfast.ai/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-image-pro",
    "prompt": "A flower shop with exquisite windows and a beautiful wooden door",
    "size": "2K",
    "thinking_mode": true
  }'

​
Parameters

ParameterTypeRequiredDescription
modelstringYeswan2.7-image-pro or wan2.7-image
promptstringYesText description. Max 5000 characters.
imagestringNoInput image URL or Base64 data URI for editing. Supports JPEG, JPG, PNG, BMP, WEBP. Max 20 MB. Up to 9 images.
nintegerNoNumber of images. Sequential mode off: 1–4, default 1. Sequential mode on: 1–12, default 12.
sizestringNo1K, 2K (default), or 4K (wan2.7-image-pro text-to-image only). Also accepts custom {W}x{H} pixels.
enable_sequentialbooleanNoEnable group image output mode. Default: false.
thinking_modebooleanNoEnhanced reasoning for higher quality. Default: true. Only for text-to-image (no image input, sequential off).
watermarkbooleanNoAdd watermark to output. Default: false.
seedintegerNoRandom seed [0, 2147483647] for reproducible results.
response_formatstringNourl (default) or b64_json.

​
Size reference

SizePixels
1K1024×1024
2K2048×2048
4K4096×4096 (wan2.7-image-pro, text-to-image only)
When an input image is provided, the output aspect ratio matches the input and is scaled to the selected resolution.

​
Response

FieldDescription
data[].urlGenerated image URL (PNG, valid 24 hours)
data[].b64_jsonBase64 image (only when response_format=b64_json)
data[].revised_promptAI-expanded prompt actually used
createdUnix timestamp

API Reference

View the interactive API playground for Wan2.7 Image.