google/nano-banana-pro 📝❓🖼️✓ → 🖼️

⭐ Official ▶️ 21.7M runs 📅 Nov 2025 ⚙️ Cog 0.16.12
image-editing image-to-image text-to-image

About

Google's state of the art image generation and editing model 🍌🍌

Example Output

Prompt:

"How engineers see the San Francisco Bridge"

Output

Example output

Performance Metrics

113.22s Prediction Time
113.28s Total Time
All Input Parameters 
{
  "prompt": "How engineers see the San Francisco Bridge",
  "resolution": "2K",
  "image_input": [],
  "aspect_ratio": "4:3",
  "output_format": "png",
  "safety_filter_level": "block_only_high"
}
Input Parameters
prompt (required) Type: string
A text description of the image you want to generate
resolution Default: 2K
Resolution of the generated image
image_input Type: arrayDefault:
Input images to transform or use as reference (supports up to 14 images)
aspect_ratio Default: match_input_image
Aspect ratio of the generated image
output_format Default: jpg
Format of the output image
safety_filter_level Default: block_only_high
block_low_and_above is strictest, block_medium_and_above blocks some prompts, block_only_high is most permissive but some prompts will still be blocked
allow_fallback_model Type: booleanDefault: false
Fallback to another model (currently bytedance/seedream-5) if Nano Banana Pro is at capacity.
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Generating image...
Generated image in 112.22 seconds
Version Details
Version ID
712e06a8e122fb7c8dae55dcf7ad6a8e717afb7b1c41c889fc8c5132fd42f374
Version Created
February 25, 2026
Run on Replicate →