black-forest-labs/flux-kontext-dev 🔢📝🖼️❓✓ → 🖼️
About
Open-weight version of FLUX.1 Kontext

Example Output
Prompt:
"Change the car color to red, turn the headlights on"
Output

Performance Metrics
4.17s
Prediction Time
6.11s
Total Time
1
Images
All Input Parameters
{ "prompt": "Change the car color to red, turn the headlights on", "go_fast": true, "guidance": 2.5, "input_image": "https://replicate.delivery/pbxt/N5YURZv4ifaW2bMwU7hmrwzgtxf99DTQXpBeobLt1O7dEc3h/pexels-jmark-253096.jpg", "aspect_ratio": "match_input_image", "output_format": "jpg", "output_quality": 80, "num_inference_steps": 30 }
Input Parameters
- seed
- Random seed for reproducible generation. Leave blank for random.
- prompt (required)
- Text description of what you want to generate, or the instruction on how to edit the given image.
- guidance
- Guidance scale for generation
- input_image (required)
- Image to use as reference. Must be jpeg, png, gif, or webp.
- aspect_ratio
- Aspect ratio of the generated image. Use 'match_input_image' to match the aspect ratio of the input image.
- output_format
- Output image format
- output_quality
- Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
- num_inference_steps
- Number of inference steps
- disable_safety_checker
- Disable NSFW safety checker
Output Schema
Output
Example Execution Logs
Starting generate image Using seed: 16326 Total safe images: 1 out of 1 generate image took 4.09 seconds
Version Details
- Version ID
85723d503c17da3f9fd9cecfb9987a8bf60ef747fd8f68a25d7636f88260eb59
- Version Created
- June 26, 2025