wan-video/wan-2.7-image-pro 🔢❓🖼️📝✓ → 🖼️

⭐ Official ▶️ 79.0K runs 📅 Apr 2026 ⚙️ Cog 0.17.2
image-editing image-to-image text-to-image

About

Generate and edit high-quality images with Alibaba's Wan 2.7 Pro with 4K output, thinking mode, text-to-image, multi-image editing, and image set generation

Example Output

Prompt:

"An extreme close-up macro photograph of a honeybee collecting pollen from a lavender flower, every hair and wing vein sharply detailed, soft bokeh background with morning dew drops glistening on purple petals, natural golden hour lighting, shot on Hasselblad with 100mm macro lens"

Output

Example output

Performance Metrics

51.04s Prediction Time
51.07s Total Time
All Input Parameters
{
  "seed": 3333,
  "size": "2K",
  "prompt": "An extreme close-up macro photograph of a honeybee collecting pollen from a lavender flower, every hair and wing vein sharply detailed, soft bokeh background with morning dew drops glistening on purple petals, natural golden hour lighting, shot on Hasselblad with 100mm macro lens",
  "thinking_mode": true
}
Input Parameters
seed Type: integer
Random seed for reproducible generation. Range: 0-2147483647
size Default: 2K
Output image resolution. '1K', '2K', and '4K' auto-size based on input images. 4K is only available for text-to-image.
images Type: arrayDefault:
Input images for editing, style transfer, or multi-reference generation (up to 9 images, jpg/png/bmp/webp). When provided, the model operates in image editing mode.
prompt (required) Type: string
Text prompt for image generation or editing
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of images to generate (1-4 for standard mode, 1-12 for image set mode)
thinking_mode Type: booleanDefault: true
Enable enhanced reasoning for improved image quality. Only applies to text-to-image (no input images, no image set mode). Increases generation time.
image_set_mode Type: booleanDefault: false
Generate a coherent set of related images from a single prompt (e.g. a character across seasons). When enabled, num_outputs can be up to 12.
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 3333
Generating image with Wan 2.7 Image (wan2.7-image-pro) (text-to-image)...
Creating Wan 2.7 Image (wan2.7-image-pro) task...
Created task 8d61e073-7199-4975-aeca-f1e17acd6e8b, polling for result...
Task status: RUNNING
Task status: RUNNING
Task status: RUNNING
Task status: RUNNING
Task status: RUNNING
Task status: RUNNING
Task status: RUNNING
Task status: SUCCEEDED
Generated 1 image(s) in 48.6sec
Downloading 7503486 bytes
Downloaded 7.16MB in 1.79sec
Version Details
Version ID
d880bad3fb109170221d7c233c4665bab6ba83d01936f3c9b1389de6ed2a82ed
Version Created
April 2, 2026
Run on Replicate →