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

⭐ Official ▶️ 365.1K runs 📅 Nov 2024 ⚙️ Cog 0.16.7 ⚖️ License
image-editing image-style-transfer image-to-image sketch-to-image

About

Professional edge-guided image generation. Control structure and composition using Canny edge detection

Example Output

Prompt:

"a photo of a car on a city street"

Output

Example output

Performance Metrics

16.04s Prediction Time
16.04s Total Time
1 Images
All Input Parameters
{
  "steps": 28,
  "prompt": "a photo of a car on a city street",
  "guidance": 25,
  "control_image": "https://replicate.delivery/pbxt/M0j11UQhwUWoxUQ9hJCOaALsAHTeoPZcGGtUf6n3BJxtKHul/output-14.webp",
  "output_format": "jpg",
  "safety_tolerance": 2,
  "prompt_upsampling": false
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation
steps Type: integerDefault: 50Range: 15 - 50
Number of diffusion steps. Higher values yield finer details but increase processing time.
prompt (required) Type: string
Text prompt for image generation
guidance Type: numberDefault: 30Range: 1 - 100
Controls the balance between adherence to the text as well as image prompt and image quality/diversity. Higher values make the output more closely match the prompt but may reduce overall image quality. Lower values allow for more creative freedom but might produce results less relevant to the prompt.
control_image (required) Type: string
Image to use as control input. Must be jpeg, png, gif, or webp.
output_format Default: jpg
Format of the output images.
safety_tolerance Type: integerDefault: 2Range: 1 - 6
Safety tolerance, 1 is most strict and 6 is most permissive
prompt_upsampling Type: booleanDefault: false
Automatically modify the prompt for more creative generation
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
Using seed: 53733
Running prediction... 
Generating image...
Generated image in 14.5sec
Downloaded image in 1.40sec
Version Details
Version ID
d042532044840da9fdd8761d2a9e829ebec76662818d0929a035cc3cf14e2661
Version Created
September 12, 2025
Run on Replicate →