Wan2.7 Image

Wan2.7 image generation and editing model via Alibaba via Anyfast API.

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 ID	Description
wan2.7-image-pro	Professional variant. Supports 4K output for text-to-image.
wan2.7-image	Standard 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

Text-to-image

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

Parameter	Type	Required	Description
model	string	Yes	wan2.7-image-pro or wan2.7-image
prompt	string	Yes	Text description. Max 5000 characters.
image	string	No	Input image URL or Base64 data URI for editing. Supports JPEG, JPG, PNG, BMP, WEBP. Max 20 MB. Up to 9 images.
n	integer	No	Number of images. Sequential mode off: 1–4, default 1. Sequential mode on: 1–12, default 12.
size	string	No	1K, 2K (default), or 4K (wan2.7-image-pro text-to-image only). Also accepts custom {W}x{H} pixels.
enable_sequential	boolean	No	Enable group image output mode. Default: false.
thinking_mode	boolean	No	Enhanced reasoning for higher quality. Default: true. Only for text-to-image (no image input, sequential off).
watermark	boolean	No	Add watermark to output. Default: false.
seed	integer	No	Random seed [0, 2147483647] for reproducible results.
response_format	string	No	url (default) or b64_json.

Size reference

Size	Pixels
1K	1024×1024
2K	2048×2048
4K	4096×4096 (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

Field	Description
data[].url	Generated image URL (PNG, valid 24 hours)
data[].b64_json	Base64 image (only when response_format=b64_json)
data[].revised_prompt	AI-expanded prompt actually used
created	Unix timestamp

API Reference

View the interactive API playground for Wan2.7 Image.