Official

black-forest-labs / flux-canny-dev

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

Warm

Public
102K runs
$0.025 per image
Commercial use
Weights
License

Iterate in playground

Run with an API

Playground API Examples README

Input

prompt

*string

Shift + Return to add a new line

A red vintage convertible driving through an old townA red vintage convertible driving through an old town

Prompt for generated image

control_image

*file

Image used to control the generation. The canny edge detection will be automatically generated.

num_outputs

integer

(minimum: 1, maximum: 4)

Number of outputs to generate

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 50)

Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.

Default: 28

guidance

number

(minimum: 0, maximum: 100)

Guidance for generated image

Default: 30

seed

integer

Random seed. Set for reproducible generation

output_format

string

Format of the output images

Default: "webp"

output_quality

integer

(minimum: 0, maximum: 100)

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Default: 80

disable_safety_checker

boolean

Disable safety checker for generated images.

Default: false

megapixels

string

Approximate number of megapixels for generated image. Use match_input to match the size of the input (with an upper limit of 1440x1440 pixels)

Default: "1"

Run this model in Node.js with one line of code:

npx create-replicate --model=black-forest-labs/flux-canny-dev

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run black-forest-labs/flux-canny-dev using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  prompt: "A red vintage convertible driving through an old town",
  guidance: 30,
  megapixels: "1",
  num_outputs: 1,
  control_image: "https://replicate.delivery/pbxt/M0mUcvKOwNSS4axvv7LAngBAR5Iuv2GsIcnSKdpQRJA62f8G/Screenshot%202024-11-21%20at%2016.08.20.png",
  output_format: "webp",
  output_quality: 80,
  num_inference_steps: 28
};

const output = await replicate.run("black-forest-labs/flux-canny-dev", { input });

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run black-forest-labs/flux-canny-dev using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "black-forest-labs/flux-canny-dev",
    input={
        "prompt": "A red vintage convertible driving through an old town",
        "guidance": 30,
        "megapixels": "1",
        "num_outputs": 1,
        "control_image": "https://replicate.delivery/pbxt/M0mUcvKOwNSS4axvv7LAngBAR5Iuv2GsIcnSKdpQRJA62f8G/Screenshot%202024-11-21%20at%2016.08.20.png",
        "output_format": "webp",
        "output_quality": 80,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run black-forest-labs/flux-canny-dev using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "prompt": "A red vintage convertible driving through an old town",
      "guidance": 30,
      "megapixels": "1",
      "num_outputs": 1,
      "control_image": "https://replicate.delivery/pbxt/M0mUcvKOwNSS4axvv7LAngBAR5Iuv2GsIcnSKdpQRJA62f8G/Screenshot%202024-11-21%20at%2016.08.20.png",
      "output_format": "webp",
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/models/black-forest-labs/flux-canny-dev/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-11-21T15:12:27.593277Z",
  "created_at": "2024-11-21T15:12:20.974000Z",
  "data_removed": false,
  "error": null,
  "id": "d9v5nwg7xsrma0ck9x4a8z0g18",
  "input": {
    "prompt": "A red vintage convertible driving through an old town",
    "guidance": 30,
    "megapixels": "1",
    "num_outputs": 1,
    "control_image": "https://replicate.delivery/pbxt/M0mUcvKOwNSS4axvv7LAngBAR5Iuv2GsIcnSKdpQRJA62f8G/Screenshot%202024-11-21%20at%2016.08.20.png",
    "output_format": "webp",
    "output_quality": 80,
    "num_inference_steps": 28
  },
  "logs": "running bf16 model, fp8 disabled\nUsing seed: 25823\n0it [00:00, ?it/s]\n1it [00:00,  8.11it/s]\n2it [00:00,  5.66it/s]\n3it [00:00,  5.15it/s]\n4it [00:00,  4.94it/s]\n5it [00:00,  4.74it/s]\n6it [00:01,  4.69it/s]\n7it [00:01,  4.66it/s]\n8it [00:01,  4.65it/s]\n9it [00:01,  4.64it/s]\n10it [00:02,  4.61it/s]\n11it [00:02,  4.61it/s]\n12it [00:02,  4.61it/s]\n13it [00:02,  4.61it/s]\n14it [00:02,  4.59it/s]\n15it [00:03,  4.59it/s]\n16it [00:03,  4.59it/s]\n17it [00:03,  4.60it/s]\n18it [00:03,  4.60it/s]\n19it [00:04,  4.58it/s]\n20it [00:04,  4.58it/s]\n21it [00:04,  4.59it/s]\n22it [00:04,  4.60it/s]\n23it [00:04,  4.61it/s]\n24it [00:05,  4.59it/s]\n25it [00:05,  4.59it/s]\n26it [00:05,  4.59it/s]\n27it [00:05,  4.60it/s]\n28it [00:06,  4.59it/s]\n28it [00:06,  4.67it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "image_count": 1,
    "predict_time": 6.611810817,
    "total_time": 6.619277
  },
  "output": [
    "https://replicate.delivery/xezq/4bt5HoegzYR9EKqv70zsBoHnhFkcaB9Yk1naaQJai6rtfPzTA/out-0.webp"
  ],
  "started_at": "2024-11-21T15:12:20.981466Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-rxxzhmhyoia3wetm2bu2vgsqfgoy3q7d2nhua3spprualor3nk4q",
    "get": "https://api.replicate.com/v1/predictions/d9v5nwg7xsrma0ck9x4a8z0g18",
    "cancel": "https://api.replicate.com/v1/predictions/d9v5nwg7xsrma0ck9x4a8z0g18/cancel"
  },
  "version": "hidden"
}

Generated in

6.6 seconds

Tweak itReport

Examples

View more examples

Pricing

Model pricing for black-forest-labs/flux-canny-dev. Can’t find what you're looking for? Reach out to support.

Official models are always on, maintained, and have predictable pricing. Learn more.

$0.025

per output image

or around 40 images for $1

This model is priced per output image.

Check out our docs for more information about how pricing works on Replicate.

Readme

FLUX.1 Canny [dev]

FLUX.1 Canny [dev] gives developers the same edge-guided generation that powers Canny [pro]. Feed it a sketch or edge map plus a description, and it creates images that follow your structural guidance while adding rich detail and style.

Perfect for building creative tools that need precise control over image composition.