black-forest-labs/flux-kontext-pro 🔢📝🖼️❓✓ → 🖼️

⭐ Official ▶️ 43.0M runs 📅 May 2025 ⚙️ Cog 0.16.8
image-consistent-character-generation image-editing image-style-transfer image-to-image text-to-image

About

A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language

Example Output

Prompt:

"Make this a 90s cartoon"

Output

Example output

Performance Metrics

4.37s Prediction Time
4.40s Total Time
1 Images
All Input Parameters 
{
  "prompt": "Make this a 90s cartoon",
  "input_image": "https://replicate.delivery/pbxt/N55l5TWGh8mSlNzW8usReoaNhGbFwvLeZR3TX1NL4pd2Wtfv/replicate-prediction-f2d25rg6gnrma0cq257vdw2n4c.png",
  "aspect_ratio": "match_input_image",
  "output_format": "jpg",
  "safety_tolerance": 2
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation
prompt (required) Type: string
Text description of what you want to generate, or the instruction on how to edit the given image.
input_image Type: string
Image to use as reference. Must be jpeg, png, gif, or webp.
aspect_ratio Default: match_input_image
Aspect ratio of the generated image. Use 'match_input_image' to match the aspect ratio of the input image.
output_format Default: png
Output format for the generated image
safety_tolerance Type: integerDefault: 2Range: 0 - 6
Safety tolerance, 0 is most strict and 6 is most permissive. 2 is currently the maximum allowed when input images are used.
prompt_upsampling Type: booleanDefault: false
Automatic prompt improvement
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Using seed: 1944901477
Generating...
Generated image in 4.2sec
Downloading 207029 bytes
Downloaded 0.20MB in 0.14sec
Version Details
Version ID
897a70f5a7dbd8a0611413b3b98cf417b45f266bd595c571a22947619d9ae462
Version Created
November 12, 2025
Run on Replicate →