lucataco/multi-image-qwen-edit 🔢🖼️📝✓❓ → 🖼️

▶️ 2.5K runs 📅 Aug 2025 ⚙️ Cog 0.14.0
fast-predictions image-editing image-merging multi-image text-to-image

About

Experimental model with multiple image support for Qwen-Image-Edit

Example Output

Prompt:

"have her hold the doll"

Output

Example output

Performance Metrics

18.65s Prediction Time
19.12s Total Time
All Input Parameters 
{
  "images": [
    "https://replicate.delivery/pbxt/NZlAtMEqfwdlmpvHPcXOq7Ack9VB4V3LcMMOUfv8ywa5AYOy/woman.png",
    "https://replicate.delivery/pbxt/NZlAtNbDRZO8f5bYrqAnkpZwPteg3YuMerVAaIytnGWtfDx8/labubu.png"
  ],
  "prompt": "have her hold the doll",
  "go_fast": true,
  "aspect_ratio": "match_input_image"
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation
images (required) Type: array
List of images to merge and then edit
prompt (required) Type: string
Text instruction on how to edit the merged image
go_fast Type: booleanDefault: true
Run faster predictions with additional optimizations
aspect_ratio Default: match_input_image
Aspect ratio for the generated image
Output Schema

Output

Type: string • Format: uri

Version Details
Version ID
5c53bc0c70836c15968705cdb47f154948cd11440e185914b49c4f93cb4c3643
Version Created
August 21, 2025
Run on Replicate →