Prediction

ID

wrrehq9jthrm80cm8sks373yh8

Status

Succeeded

Source

Web

Hardware

H100

Total duration

26.7s

Created

5 months ago

Input

seed: 42
redux
width: 1024
height: 1024
prompt: A woman with pink hair at the beach
num_outputs: 1
output_format: webp
guidance_scale: 3.5
output_quality: 80
redux_strength: 0.05
num_inference_steps: 28

{
  "seed": 42,
  "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
  "width": 1024,
  "height": 1024,
  "prompt": "A woman with pink hair at the beach",
  "num_outputs": 1,
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "redux_strength": 0.05,
  "num_inference_steps": 28
}

npm install replicate

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 jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
  {
    input: {
      seed: 42,
      redux: "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
      width: 1024,
      height: 1024,
      prompt: "A woman with pink hair at the beach",
      num_outputs: 1,
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      redux_strength: 0.05,
      num_inference_steps: 28
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

Run jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
    input={
        "seed": 42,
        "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
        "width": 1024,
        "height": 1024,
        "prompt": "A woman with pink hair at the beach",
        "num_outputs": 1,
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "redux_strength": 0.05,
        "num_inference_steps": 28
    }
)
print(output)

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

Run jhorovitz/flux-dev-redux-control 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 $'{
    "version": "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
    "input": {
      "seed": 42,
      "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
      "width": 1024,
      "height": 1024,
      "prompt": "A woman with pink hair at the beach",
      "num_outputs": 1,
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.05,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/jhorovitz/flux-dev-redux-control@sha256:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430 \
  -i 'seed=42' \
  -i 'redux="https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg"' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="A woman with pink hair at the beach"' \
  -i 'num_outputs=1' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=3.5' \
  -i 'output_quality=80' \
  -i 'redux_strength=0.05' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/jhorovitz/flux-dev-redux-control@sha256:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 42,
      "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
      "width": 1024,
      "height": 1024,
      "prompt": "A woman with pink hair at the beach",
      "num_outputs": 1,
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.05,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2025-01-08T14:53:02.630618Z",
  "created_at": "2025-01-08T14:52:35.924000Z",
  "data_removed": false,
  "error": null,
  "id": "wrrehq9jthrm80cm8sks373yh8",
  "input": {
    "seed": 42,
    "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
    "width": 1024,
    "height": 1024,
    "prompt": "A woman with pink hair at the beach",
    "num_outputs": 1,
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "redux_strength": 0.05,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 42\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:24,  1.11it/s]\n  7%|▋         | 2/28 [00:01<00:19,  1.32it/s]\n 11%|█         | 3/28 [00:02<00:20,  1.21it/s]\n 14%|█▍        | 4/28 [00:03<00:20,  1.17it/s]\n 18%|█▊        | 5/28 [00:04<00:20,  1.15it/s]\n 21%|██▏       | 6/28 [00:05<00:19,  1.13it/s]\n 25%|██▌       | 7/28 [00:06<00:18,  1.12it/s]\n 29%|██▊       | 8/28 [00:06<00:17,  1.12it/s]\n 32%|███▏      | 9/28 [00:07<00:17,  1.12it/s]\n 36%|███▌      | 10/28 [00:08<00:16,  1.11it/s]\n 39%|███▉      | 11/28 [00:09<00:15,  1.11it/s]\n 43%|████▎     | 12/28 [00:10<00:14,  1.11it/s]\n 46%|████▋     | 13/28 [00:11<00:13,  1.11it/s]\n 50%|█████     | 14/28 [00:12<00:12,  1.11it/s]\n 54%|█████▎    | 15/28 [00:13<00:11,  1.11it/s]\n 57%|█████▋    | 16/28 [00:14<00:10,  1.11it/s]\n 61%|██████    | 17/28 [00:15<00:09,  1.11it/s]\n 64%|██████▍   | 18/28 [00:15<00:09,  1.11it/s]\n 68%|██████▊   | 19/28 [00:16<00:08,  1.11it/s]\n 71%|███████▏  | 20/28 [00:17<00:07,  1.11it/s]\n 75%|███████▌  | 21/28 [00:18<00:06,  1.11it/s]\n 79%|███████▊  | 22/28 [00:19<00:05,  1.11it/s]\n 82%|████████▏ | 23/28 [00:20<00:04,  1.11it/s]\n 86%|████████▌ | 24/28 [00:21<00:03,  1.11it/s]\n 89%|████████▉ | 25/28 [00:22<00:02,  1.11it/s]\n 93%|█████████▎| 26/28 [00:23<00:01,  1.11it/s]\n 96%|█████████▋| 27/28 [00:24<00:00,  1.11it/s]\n100%|██████████| 28/28 [00:25<00:00,  1.11it/s]\n100%|██████████| 28/28 [00:25<00:00,  1.12it/s]",
  "metrics": {
    "predict_time": 26.699620529,
    "total_time": 26.706618
  },
  "output": [
    "https://replicate.delivery/xezq/gWUkCj3vTy64JNt5uaeGiT8YxWGAeIy3NfffmDHOuRa2phYgC/out-0.webp"
  ],
  "started_at": "2025-01-08T14:52:35.930997Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-usfltpnbkfuyn4fmgtwgg7cj4bpkf4m6hqkwwsakhfltpztdpyxq",
    "get": "https://api.replicate.com/v1/predictions/wrrehq9jthrm80cm8sks373yh8",
    "cancel": "https://api.replicate.com/v1/predictions/wrrehq9jthrm80cm8sks373yh8/cancel"
  },
  "version": "c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430"
}

Generated in

26.7 seconds

jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430

Prediction

Model

ID

6bazd9ewbdrmc0cm8snr75t0sm

Status

Succeeded

Source

Web

Hardware

H100

Total duration

25.6s

Created

5 months ago

Input

seed: 42
redux
width: 1024
height: 1024
prompt: A cartoon drawing of a car.
num_outputs: 1
output_format: webp
guidance_scale: 3.5
output_quality: 80
redux_strength: 0.03
num_inference_steps: 28

{
  "seed": 42,
  "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
  "width": 1024,
  "height": 1024,
  "prompt": "A cartoon drawing of a car.",
  "num_outputs": 1,
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "redux_strength": 0.03,
  "num_inference_steps": 28
}

npm install replicate

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 jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
  {
    input: {
      seed: 42,
      redux: "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
      width: 1024,
      height: 1024,
      prompt: "A cartoon drawing of a car.",
      num_outputs: 1,
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      redux_strength: 0.03,
      num_inference_steps: 28
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

Run jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
    input={
        "seed": 42,
        "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
        "width": 1024,
        "height": 1024,
        "prompt": "A cartoon drawing of a car.",
        "num_outputs": 1,
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "redux_strength": 0.03,
        "num_inference_steps": 28
    }
)
print(output)

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

Run jhorovitz/flux-dev-redux-control 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 $'{
    "version": "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
    "input": {
      "seed": 42,
      "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
      "width": 1024,
      "height": 1024,
      "prompt": "A cartoon drawing of a car.",
      "num_outputs": 1,
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.03,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/jhorovitz/flux-dev-redux-control@sha256:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430 \
  -i 'seed=42' \
  -i 'redux="https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp"' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="A cartoon drawing of a car."' \
  -i 'num_outputs=1' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=3.5' \
  -i 'output_quality=80' \
  -i 'redux_strength=0.03' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/jhorovitz/flux-dev-redux-control@sha256:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 42,
      "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
      "width": 1024,
      "height": 1024,
      "prompt": "A cartoon drawing of a car.",
      "num_outputs": 1,
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.03,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2025-01-08T14:58:07.056386Z",
  "created_at": "2025-01-08T14:57:41.467000Z",
  "data_removed": false,
  "error": null,
  "id": "6bazd9ewbdrmc0cm8snr75t0sm",
  "input": {
    "seed": 42,
    "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
    "width": 1024,
    "height": 1024,
    "prompt": "A cartoon drawing of a car.",
    "num_outputs": 1,
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "redux_strength": 0.03,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 42\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:24,  1.11it/s]\n  7%|▋         | 2/28 [00:01<00:19,  1.32it/s]\n 11%|█         | 3/28 [00:02<00:20,  1.21it/s]\n 14%|█▍        | 4/28 [00:03<00:20,  1.17it/s]\n 18%|█▊        | 5/28 [00:04<00:20,  1.15it/s]\n 21%|██▏       | 6/28 [00:05<00:19,  1.13it/s]\n 25%|██▌       | 7/28 [00:06<00:18,  1.13it/s]\n 29%|██▊       | 8/28 [00:06<00:17,  1.12it/s]\n 32%|███▏      | 9/28 [00:07<00:17,  1.12it/s]\n 36%|███▌      | 10/28 [00:08<00:16,  1.11it/s]\n 39%|███▉      | 11/28 [00:09<00:15,  1.11it/s]\n 43%|████▎     | 12/28 [00:10<00:14,  1.11it/s]\n 46%|████▋     | 13/28 [00:11<00:13,  1.11it/s]\n 50%|█████     | 14/28 [00:12<00:12,  1.11it/s]\n 54%|█████▎    | 15/28 [00:13<00:11,  1.11it/s]\n 57%|█████▋    | 16/28 [00:14<00:10,  1.11it/s]\n 61%|██████    | 17/28 [00:15<00:09,  1.11it/s]\n 64%|██████▍   | 18/28 [00:15<00:09,  1.11it/s]\n 68%|██████▊   | 19/28 [00:16<00:08,  1.11it/s]\n 71%|███████▏  | 20/28 [00:17<00:07,  1.11it/s]\n 75%|███████▌  | 21/28 [00:18<00:06,  1.11it/s]\n 79%|███████▊  | 22/28 [00:19<00:05,  1.11it/s]\n 82%|████████▏ | 23/28 [00:20<00:04,  1.11it/s]\n 86%|████████▌ | 24/28 [00:21<00:03,  1.11it/s]\n 89%|████████▉ | 25/28 [00:22<00:02,  1.11it/s]\n 93%|█████████▎| 26/28 [00:23<00:01,  1.11it/s]\n 96%|█████████▋| 27/28 [00:24<00:00,  1.11it/s]\n100%|██████████| 28/28 [00:25<00:00,  1.11it/s]\n100%|██████████| 28/28 [00:25<00:00,  1.12it/s]",
  "metrics": {
    "predict_time": 25.583090236,
    "total_time": 25.589386
  },
  "output": [
    "https://replicate.delivery/xezq/6ctpbTfjDhwfAk31YuvxGSEYRhibuvG9ifEEnkxj1pueHRMQB/out-0.webp"
  ],
  "started_at": "2025-01-08T14:57:41.473296Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-v5bg4vqnbytcv5a2f5rlpefly4a4kbshdnnrszfrhs5wth2a7uwq",
    "get": "https://api.replicate.com/v1/predictions/6bazd9ewbdrmc0cm8snr75t0sm",
    "cancel": "https://api.replicate.com/v1/predictions/6bazd9ewbdrmc0cm8snr75t0sm/cancel"
  },
  "version": "c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430"
}

Generated in

25.6 seconds

jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430

Prediction

Model

ID

5qc07hk4p9rme0cm8sqt3tvr7r

Status

Succeeded

Source

Web

Hardware

H100

Total duration

38.1s

Created

5 months ago

Input

seed: 42
redux
width: 1024
height: 1024
prompt: A red car driving underwater.
num_outputs: 1
output_format: webp
guidance_scale: 3.5
output_quality: 80
redux_strength: 0.01
num_inference_steps: 28

{
  "seed": 42,
  "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
  "width": 1024,
  "height": 1024,
  "prompt": "A red car driving underwater.",
  "num_outputs": 1,
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "redux_strength": 0.01,
  "num_inference_steps": 28
}

npm install replicate

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 jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
  {
    input: {
      seed: 42,
      redux: "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
      width: 1024,
      height: 1024,
      prompt: "A red car driving underwater.",
      num_outputs: 1,
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      redux_strength: 0.01,
      num_inference_steps: 28
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

Run jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
    input={
        "seed": 42,
        "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
        "width": 1024,
        "height": 1024,
        "prompt": "A red car driving underwater.",
        "num_outputs": 1,
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "redux_strength": 0.01,
        "num_inference_steps": 28
    }
)
print(output)

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

Run jhorovitz/flux-dev-redux-control 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 $'{
    "version": "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
    "input": {
      "seed": 42,
      "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
      "width": 1024,
      "height": 1024,
      "prompt": "A red car driving underwater.",
      "num_outputs": 1,
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.01,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/jhorovitz/flux-dev-redux-control@sha256:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430 \
  -i 'seed=42' \
  -i 'redux="https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp"' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="A red car driving underwater."' \
  -i 'num_outputs=1' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=3.5' \
  -i 'output_quality=80' \
  -i 'redux_strength=0.01' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/jhorovitz/flux-dev-redux-control@sha256:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 42,
      "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
      "width": 1024,
      "height": 1024,
      "prompt": "A red car driving underwater.",
      "num_outputs": 1,
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.01,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2025-01-08T15:02:11.115402Z",
  "created_at": "2025-01-08T15:01:32.978000Z",
  "data_removed": false,
  "error": null,
  "id": "5qc07hk4p9rme0cm8sqt3tvr7r",
  "input": {
    "seed": 42,
    "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
    "width": 1024,
    "height": 1024,
    "prompt": "A red car driving underwater.",
    "num_outputs": 1,
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "redux_strength": 0.01,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 42\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:24,  1.11it/s]\n  7%|▋         | 2/28 [00:01<00:19,  1.32it/s]\n 11%|█         | 3/28 [00:02<00:20,  1.21it/s]\n 14%|█▍        | 4/28 [00:03<00:20,  1.17it/s]\n 18%|█▊        | 5/28 [00:04<00:20,  1.15it/s]\n 21%|██▏       | 6/28 [00:05<00:19,  1.13it/s]\n 25%|██▌       | 7/28 [00:06<00:18,  1.12it/s]\n 29%|██▊       | 8/28 [00:06<00:17,  1.12it/s]\n 32%|███▏      | 9/28 [00:07<00:17,  1.12it/s]\n 36%|███▌      | 10/28 [00:08<00:16,  1.11it/s]\n 39%|███▉      | 11/28 [00:09<00:15,  1.11it/s]\n 43%|████▎     | 12/28 [00:10<00:14,  1.11it/s]\n 46%|████▋     | 13/28 [00:11<00:13,  1.11it/s]\n 50%|█████     | 14/28 [00:12<00:12,  1.11it/s]\n 54%|█████▎    | 15/28 [00:13<00:11,  1.11it/s]\n 57%|█████▋    | 16/28 [00:14<00:10,  1.11it/s]\n 61%|██████    | 17/28 [00:15<00:09,  1.11it/s]\n 64%|██████▍   | 18/28 [00:16<00:09,  1.11it/s]\n 68%|██████▊   | 19/28 [00:16<00:08,  1.11it/s]\n 71%|███████▏  | 20/28 [00:17<00:07,  1.11it/s]\n 75%|███████▌  | 21/28 [00:18<00:06,  1.11it/s]\n 79%|███████▊  | 22/28 [00:19<00:05,  1.11it/s]\n 82%|████████▏ | 23/28 [00:20<00:04,  1.11it/s]\n 86%|████████▌ | 24/28 [00:21<00:03,  1.11it/s]\n 89%|████████▉ | 25/28 [00:22<00:02,  1.11it/s]\n 93%|█████████▎| 26/28 [00:23<00:01,  1.11it/s]\n 96%|█████████▋| 27/28 [00:24<00:00,  1.11it/s]\n100%|██████████| 28/28 [00:25<00:00,  1.11it/s]\n100%|██████████| 28/28 [00:25<00:00,  1.12it/s]",
  "metrics": {
    "predict_time": 25.64457902,
    "total_time": 38.137402
  },
  "output": [
    "https://replicate.delivery/xezq/XSlusWLDzMbeTaIVZb4A195GwHECZut72oO0AhMp8e6zVEDUA/out-0.webp"
  ],
  "started_at": "2025-01-08T15:01:45.470823Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-6d4keee75a74hmj6tesj6schc7kdjq6w3dtjihhvqo3fvzh4s2fq",
    "get": "https://api.replicate.com/v1/predictions/5qc07hk4p9rme0cm8sqt3tvr7r",
    "cancel": "https://api.replicate.com/v1/predictions/5qc07hk4p9rme0cm8sqt3tvr7r/cancel"
  },
  "version": "c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430"
}

Generated in

25.6 seconds

jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430

Prediction

Model

ID

09rx80vaq1rmc0cm8srs9aq518

Status

Succeeded

Source

Web

Hardware

H100

Total duration

25.6s

Created

5 months ago

Input

seed: 42
redux
width: 1024
height: 1024
prompt: A pencil drawing of a car.
num_outputs: 1
output_format: webp
guidance_scale: 3.5
output_quality: 80
redux_strength: 0.02
num_inference_steps: 28

{
  "seed": 42,
  "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
  "width": 1024,
  "height": 1024,
  "prompt": "A pencil drawing of a car.",
  "num_outputs": 1,
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "redux_strength": 0.02,
  "num_inference_steps": 28
}

npm install replicate

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 jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
  {
    input: {
      seed: 42,
      redux: "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
      width: 1024,
      height: 1024,
      prompt: "A pencil drawing of a car.",
      num_outputs: 1,
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      redux_strength: 0.02,
      num_inference_steps: 28
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

Run jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
    input={
        "seed": 42,
        "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
        "width": 1024,
        "height": 1024,
        "prompt": "A pencil drawing of a car.",
        "num_outputs": 1,
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "redux_strength": 0.02,
        "num_inference_steps": 28
    }
)
print(output)

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

Run jhorovitz/flux-dev-redux-control 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 $'{
    "version": "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
    "input": {
      "seed": 42,
      "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
      "width": 1024,
      "height": 1024,
      "prompt": "A pencil drawing of a car.",
      "num_outputs": 1,
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.02,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/jhorovitz/flux-dev-redux-control@sha256:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430 \
  -i 'seed=42' \
  -i 'redux="https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp"' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="A pencil drawing of a car."' \
  -i 'num_outputs=1' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=3.5' \
  -i 'output_quality=80' \
  -i 'redux_strength=0.02' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/jhorovitz/flux-dev-redux-control@sha256:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 42,
      "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
      "width": 1024,
      "height": 1024,
      "prompt": "A pencil drawing of a car.",
      "num_outputs": 1,
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.02,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2025-01-08T15:04:11.189322Z",
  "created_at": "2025-01-08T15:03:45.592000Z",
  "data_removed": false,
  "error": null,
  "id": "09rx80vaq1rmc0cm8srs9aq518",
  "input": {
    "seed": 42,
    "redux": "https://replicate.delivery/pbxt/MHoZIY0XUcZ2G34UPSRRXGOxOarxnMDc96u7UCrGdUsqoC1j/car.webp",
    "width": 1024,
    "height": 1024,
    "prompt": "A pencil drawing of a car.",
    "num_outputs": 1,
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "redux_strength": 0.02,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 42\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:24,  1.11it/s]\n  7%|▋         | 2/28 [00:01<00:19,  1.32it/s]\n 11%|█         | 3/28 [00:02<00:20,  1.21it/s]\n 14%|█▍        | 4/28 [00:03<00:20,  1.17it/s]\n 18%|█▊        | 5/28 [00:04<00:20,  1.15it/s]\n 21%|██▏       | 6/28 [00:05<00:19,  1.13it/s]\n 25%|██▌       | 7/28 [00:06<00:18,  1.12it/s]\n 29%|██▊       | 8/28 [00:06<00:17,  1.12it/s]\n 32%|███▏      | 9/28 [00:07<00:17,  1.12it/s]\n 36%|███▌      | 10/28 [00:08<00:16,  1.11it/s]\n 39%|███▉      | 11/28 [00:09<00:15,  1.11it/s]\n 43%|████▎     | 12/28 [00:10<00:14,  1.11it/s]\n 46%|████▋     | 13/28 [00:11<00:13,  1.11it/s]\n 50%|█████     | 14/28 [00:12<00:12,  1.11it/s]\n 54%|█████▎    | 15/28 [00:13<00:11,  1.11it/s]\n 57%|█████▋    | 16/28 [00:14<00:10,  1.11it/s]\n 61%|██████    | 17/28 [00:15<00:09,  1.11it/s]\n 64%|██████▍   | 18/28 [00:15<00:09,  1.11it/s]\n 68%|██████▊   | 19/28 [00:16<00:08,  1.11it/s]\n 71%|███████▏  | 20/28 [00:17<00:07,  1.11it/s]\n 75%|███████▌  | 21/28 [00:18<00:06,  1.11it/s]\n 79%|███████▊  | 22/28 [00:19<00:05,  1.11it/s]\n 82%|████████▏ | 23/28 [00:20<00:04,  1.11it/s]\n 86%|████████▌ | 24/28 [00:21<00:03,  1.11it/s]\n 89%|████████▉ | 25/28 [00:22<00:02,  1.11it/s]\n 93%|█████████▎| 26/28 [00:23<00:01,  1.11it/s]\n 96%|█████████▋| 27/28 [00:24<00:00,  1.11it/s]\n100%|██████████| 28/28 [00:25<00:00,  1.11it/s]\n100%|██████████| 28/28 [00:25<00:00,  1.12it/s]",
  "metrics": {
    "predict_time": 25.590310202,
    "total_time": 25.597322
  },
  "output": [
    "https://replicate.delivery/xezq/Xw0NNWUnDrreYibUE1WfJT0qSzLaM14iZlFiXn7vbbMrXEDUA/out-0.webp"
  ],
  "started_at": "2025-01-08T15:03:45.599012Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-tfi7i3dqjjksw44agp6kr22oisgjpicsnc6fu2k7kmgeeejfbdna",
    "get": "https://api.replicate.com/v1/predictions/09rx80vaq1rmc0cm8srs9aq518",
    "cancel": "https://api.replicate.com/v1/predictions/09rx80vaq1rmc0cm8srs9aq518/cancel"
  },
  "version": "c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430"
}

Generated in

25.6 seconds

jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430

Prediction

Model

ID

v8k6tbex49rmc0cm8srveweeyw

Status

Succeeded

Source

Web

Hardware

H100

Total duration

48.9s

Created

5 months ago

Input

seed: 42
redux
width: 1024
height: 1024
prompt: anime style
num_outputs: 1
output_format: webp
guidance_scale: 3.5
output_quality: 80
redux_strength: 0.015
num_inference_steps: 28

{
  "seed": 42,
  "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
  "width": 1024,
  "height": 1024,
  "prompt": "anime style",
  "num_outputs": 1,
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "redux_strength": 0.015,
  "num_inference_steps": 28
}

npm install replicate

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 jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
  {
    input: {
      seed: 42,
      redux: "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
      width: 1024,
      height: 1024,
      prompt: "anime style",
      num_outputs: 1,
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      redux_strength: 0.015,
      num_inference_steps: 28
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

Run jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
    input={
        "seed": 42,
        "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
        "width": 1024,
        "height": 1024,
        "prompt": "anime style",
        "num_outputs": 1,
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "redux_strength": 0.015,
        "num_inference_steps": 28
    }
)
print(output)

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

Run jhorovitz/flux-dev-redux-control 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 $'{
    "version": "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
    "input": {
      "seed": 42,
      "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
      "width": 1024,
      "height": 1024,
      "prompt": "anime style",
      "num_outputs": 1,
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.015,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/jhorovitz/flux-dev-redux-control@sha256:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430 \
  -i 'seed=42' \
  -i 'redux="https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg"' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="anime style"' \
  -i 'num_outputs=1' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=3.5' \
  -i 'output_quality=80' \
  -i 'redux_strength=0.015' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/jhorovitz/flux-dev-redux-control@sha256:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 42,
      "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
      "width": 1024,
      "height": 1024,
      "prompt": "anime style",
      "num_outputs": 1,
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.015,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2025-01-08T15:05:03.775013Z",
  "created_at": "2025-01-08T15:04:14.882000Z",
  "data_removed": false,
  "error": null,
  "id": "v8k6tbex49rmc0cm8srveweeyw",
  "input": {
    "seed": 42,
    "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
    "width": 1024,
    "height": 1024,
    "prompt": "anime style",
    "num_outputs": 1,
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "redux_strength": 0.015,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 42\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:24,  1.11it/s]\n  7%|▋         | 2/28 [00:01<00:19,  1.32it/s]\n 11%|█         | 3/28 [00:02<00:20,  1.21it/s]\n 14%|█▍        | 4/28 [00:03<00:20,  1.17it/s]\n 18%|█▊        | 5/28 [00:04<00:20,  1.15it/s]\n 21%|██▏       | 6/28 [00:05<00:19,  1.13it/s]\n 25%|██▌       | 7/28 [00:06<00:18,  1.12it/s]\n 29%|██▊       | 8/28 [00:06<00:17,  1.12it/s]\n 32%|███▏      | 9/28 [00:07<00:17,  1.12it/s]\n 36%|███▌      | 10/28 [00:08<00:16,  1.11it/s]\n 39%|███▉      | 11/28 [00:09<00:15,  1.11it/s]\n 43%|████▎     | 12/28 [00:10<00:14,  1.11it/s]\n 46%|████▋     | 13/28 [00:11<00:13,  1.11it/s]\n 50%|█████     | 14/28 [00:12<00:12,  1.11it/s]\n 54%|█████▎    | 15/28 [00:13<00:11,  1.11it/s]\n 57%|█████▋    | 16/28 [00:14<00:10,  1.11it/s]\n 61%|██████    | 17/28 [00:15<00:09,  1.11it/s]\n 64%|██████▍   | 18/28 [00:16<00:09,  1.11it/s]\n 68%|██████▊   | 19/28 [00:16<00:08,  1.11it/s]\n 71%|███████▏  | 20/28 [00:17<00:07,  1.11it/s]\n 75%|███████▌  | 21/28 [00:18<00:06,  1.11it/s]\n 79%|███████▊  | 22/28 [00:19<00:05,  1.11it/s]\n 82%|████████▏ | 23/28 [00:20<00:04,  1.11it/s]\n 86%|████████▌ | 24/28 [00:21<00:03,  1.11it/s]\n 89%|████████▉ | 25/28 [00:22<00:02,  1.11it/s]\n 93%|█████████▎| 26/28 [00:23<00:01,  1.11it/s]\n 96%|█████████▋| 27/28 [00:24<00:00,  1.11it/s]\n100%|██████████| 28/28 [00:25<00:00,  1.11it/s]\n100%|██████████| 28/28 [00:25<00:00,  1.12it/s]",
  "metrics": {
    "predict_time": 26.861600474,
    "total_time": 48.893013
  },
  "output": [
    "https://replicate.delivery/xezq/kjl8tmeia33jUa8lv2ZsmeSNLTr5sqD16QPCEF2v6FWfwIGoA/out-0.webp"
  ],
  "started_at": "2025-01-08T15:04:36.913412Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-pghtp2bcls3plpj5zmhczwrdetxwyk53zorij6dhlwmbsauehejq",
    "get": "https://api.replicate.com/v1/predictions/v8k6tbex49rmc0cm8srveweeyw",
    "cancel": "https://api.replicate.com/v1/predictions/v8k6tbex49rmc0cm8srveweeyw/cancel"
  },
  "version": "c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430"
}

Generated in

26.9 seconds

jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430

Prediction

Model

ID

z9twg61n19rmc0cm8svt2g1ghw

Status

Succeeded

Source

Web

Hardware

H100

Total duration

28.3s

Created

5 months ago

Input

seed: 43
redux
width: 1024
height: 1024
prompt: A woman riding a jet ski.
num_outputs: 1
output_format: webp
guidance_scale: 3.5
output_quality: 80
redux_strength: 0.035
num_inference_steps: 28

{
  "seed": 43,
  "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
  "width": 1024,
  "height": 1024,
  "prompt": "A woman riding a jet ski.",
  "num_outputs": 1,
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "redux_strength": 0.035,
  "num_inference_steps": 28
}

npm install replicate

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 jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
  {
    input: {
      seed: 43,
      redux: "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
      width: 1024,
      height: 1024,
      prompt: "A woman riding a jet ski.",
      num_outputs: 1,
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      redux_strength: 0.035,
      num_inference_steps: 28
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

Run jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
    input={
        "seed": 43,
        "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
        "width": 1024,
        "height": 1024,
        "prompt": "A woman riding a jet ski.",
        "num_outputs": 1,
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "redux_strength": 0.035,
        "num_inference_steps": 28
    }
)
print(output)

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

Run jhorovitz/flux-dev-redux-control 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 $'{
    "version": "jhorovitz/flux-dev-redux-control:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430",
    "input": {
      "seed": 43,
      "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
      "width": 1024,
      "height": 1024,
      "prompt": "A woman riding a jet ski.",
      "num_outputs": 1,
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.035,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/jhorovitz/flux-dev-redux-control@sha256:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430 \
  -i 'seed=43' \
  -i 'redux="https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg"' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="A woman riding a jet ski."' \
  -i 'num_outputs=1' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=3.5' \
  -i 'output_quality=80' \
  -i 'redux_strength=0.035' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/jhorovitz/flux-dev-redux-control@sha256:c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 43,
      "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
      "width": 1024,
      "height": 1024,
      "prompt": "A woman riding a jet ski.",
      "num_outputs": 1,
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.035,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2025-01-08T15:10:33.398648Z",
  "created_at": "2025-01-08T15:10:05.066000Z",
  "data_removed": false,
  "error": null,
  "id": "z9twg61n19rmc0cm8svt2g1ghw",
  "input": {
    "seed": 43,
    "redux": "https://replicate.delivery/pbxt/MHoUlzZXnN03yJc6X1OytUzhTfj6Xu4DxTIXr30fTq5ApTRN/lisa.jpg",
    "width": 1024,
    "height": 1024,
    "prompt": "A woman riding a jet ski.",
    "num_outputs": 1,
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "redux_strength": 0.035,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 43\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:24,  1.11it/s]\n  7%|▋         | 2/28 [00:01<00:19,  1.32it/s]\n 11%|█         | 3/28 [00:02<00:20,  1.21it/s]\n 14%|█▍        | 4/28 [00:03<00:20,  1.17it/s]\n 18%|█▊        | 5/28 [00:04<00:20,  1.15it/s]\n 21%|██▏       | 6/28 [00:05<00:19,  1.13it/s]\n 25%|██▌       | 7/28 [00:06<00:18,  1.12it/s]\n 29%|██▊       | 8/28 [00:06<00:17,  1.12it/s]\n 32%|███▏      | 9/28 [00:07<00:17,  1.12it/s]\n 36%|███▌      | 10/28 [00:08<00:16,  1.11it/s]\n 39%|███▉      | 11/28 [00:09<00:15,  1.11it/s]\n 43%|████▎     | 12/28 [00:10<00:14,  1.11it/s]\n 46%|████▋     | 13/28 [00:11<00:13,  1.11it/s]\n 50%|█████     | 14/28 [00:12<00:12,  1.11it/s]\n 54%|█████▎    | 15/28 [00:13<00:11,  1.11it/s]\n 57%|█████▋    | 16/28 [00:14<00:10,  1.11it/s]\n 61%|██████    | 17/28 [00:15<00:09,  1.11it/s]\n 64%|██████▍   | 18/28 [00:15<00:09,  1.11it/s]\n 68%|██████▊   | 19/28 [00:16<00:08,  1.11it/s]\n 71%|███████▏  | 20/28 [00:17<00:07,  1.11it/s]\n 75%|███████▌  | 21/28 [00:18<00:06,  1.11it/s]\n 79%|███████▊  | 22/28 [00:19<00:05,  1.11it/s]\n 82%|████████▏ | 23/28 [00:20<00:04,  1.11it/s]\n 86%|████████▌ | 24/28 [00:21<00:03,  1.11it/s]\n 89%|████████▉ | 25/28 [00:22<00:02,  1.11it/s]\n 93%|█████████▎| 26/28 [00:23<00:01,  1.11it/s]\n 96%|█████████▋| 27/28 [00:24<00:00,  1.11it/s]\n100%|██████████| 28/28 [00:25<00:00,  1.11it/s]\n100%|██████████| 28/28 [00:25<00:00,  1.12it/s]",
  "metrics": {
    "predict_time": 28.325948334,
    "total_time": 28.332648
  },
  "output": [
    "https://replicate.delivery/xezq/pfzVeWzvwKnn9UqcXCf0kA4Ppj4hhj1qvePWJUKRxwtk2RMQB/out-0.webp"
  ],
  "started_at": "2025-01-08T15:10:05.072699Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-zmxwej2b36ttg4lxxa4pg2qrre36hfhgvmdlc5pclioypyffeiga",
    "get": "https://api.replicate.com/v1/predictions/z9twg61n19rmc0cm8svt2g1ghw",
    "cancel": "https://api.replicate.com/v1/predictions/z9twg61n19rmc0cm8svt2g1ghw/cancel"
  },
  "version": "c7e5394e7fc2b92760d37d607e07af5368ef4a61e59c40049aaa71e76c714430"
}

Generated in

28.3 seconds

jhorovitz/flux-dev-redux-control:2d77f82dce2466dee3646296420ef620bf8ab28580ef4cd7c60d22d8900e5337

Prediction

Model

jhorovitz/flux-dev-redux-control:2d77f82d

ID

1vybxphzg1rmc0cmerrt8qjnqw

Status

Succeeded

Source

Web

Hardware

H100

Total duration

2m 35s

Created

5 months ago

Input

redux
width: 1024
height: 1024
prompt: a man riding a skateboard
num_outputs: 1
control_image
output_format: webp
guidance_scale: 3.5
output_quality: 80
redux_strength: 0.02
num_inference_steps: 28

{
  "redux": "https://replicate.delivery/pbxt/ML6lOgKvDAmP2ByQnHlV3D7y0Xuerf3lDJGksDs2ixd1fzdz/yoni2.jpg",
  "width": 1024,
  "height": 1024,
  "prompt": "a man riding a skateboard",
  "num_outputs": 1,
  "control_image": "https://replicate.delivery/pbxt/ML6lOSgpOfStaqp64xbmJMRLwdLHYGZqsAoQAOdPjKfAE0fk/man_on_skateboard.webp",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "redux_strength": 0.02,
  "num_inference_steps": 28
}

npm install replicate

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 jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jhorovitz/flux-dev-redux-control:2d77f82dce2466dee3646296420ef620bf8ab28580ef4cd7c60d22d8900e5337",
  {
    input: {
      redux: "https://replicate.delivery/pbxt/ML6lOgKvDAmP2ByQnHlV3D7y0Xuerf3lDJGksDs2ixd1fzdz/yoni2.jpg",
      width: 1024,
      height: 1024,
      prompt: "a man riding a skateboard",
      num_outputs: 1,
      control_image: "https://replicate.delivery/pbxt/ML6lOSgpOfStaqp64xbmJMRLwdLHYGZqsAoQAOdPjKfAE0fk/man_on_skateboard.webp",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      redux_strength: 0.02,
      num_inference_steps: 28
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

Run jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jhorovitz/flux-dev-redux-control:2d77f82dce2466dee3646296420ef620bf8ab28580ef4cd7c60d22d8900e5337",
    input={
        "redux": "https://replicate.delivery/pbxt/ML6lOgKvDAmP2ByQnHlV3D7y0Xuerf3lDJGksDs2ixd1fzdz/yoni2.jpg",
        "width": 1024,
        "height": 1024,
        "prompt": "a man riding a skateboard",
        "num_outputs": 1,
        "control_image": "https://replicate.delivery/pbxt/ML6lOSgpOfStaqp64xbmJMRLwdLHYGZqsAoQAOdPjKfAE0fk/man_on_skateboard.webp",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "redux_strength": 0.02,
        "num_inference_steps": 28
    }
)
print(output)

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

Run jhorovitz/flux-dev-redux-control 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 $'{
    "version": "jhorovitz/flux-dev-redux-control:2d77f82dce2466dee3646296420ef620bf8ab28580ef4cd7c60d22d8900e5337",
    "input": {
      "redux": "https://replicate.delivery/pbxt/ML6lOgKvDAmP2ByQnHlV3D7y0Xuerf3lDJGksDs2ixd1fzdz/yoni2.jpg",
      "width": 1024,
      "height": 1024,
      "prompt": "a man riding a skateboard",
      "num_outputs": 1,
      "control_image": "https://replicate.delivery/pbxt/ML6lOSgpOfStaqp64xbmJMRLwdLHYGZqsAoQAOdPjKfAE0fk/man_on_skateboard.webp",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.02,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/jhorovitz/flux-dev-redux-control@sha256:2d77f82dce2466dee3646296420ef620bf8ab28580ef4cd7c60d22d8900e5337 \
  -i 'redux="https://replicate.delivery/pbxt/ML6lOgKvDAmP2ByQnHlV3D7y0Xuerf3lDJGksDs2ixd1fzdz/yoni2.jpg"' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="a man riding a skateboard"' \
  -i 'num_outputs=1' \
  -i 'control_image="https://replicate.delivery/pbxt/ML6lOSgpOfStaqp64xbmJMRLwdLHYGZqsAoQAOdPjKfAE0fk/man_on_skateboard.webp"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=3.5' \
  -i 'output_quality=80' \
  -i 'redux_strength=0.02' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/jhorovitz/flux-dev-redux-control@sha256:2d77f82dce2466dee3646296420ef620bf8ab28580ef4cd7c60d22d8900e5337
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "redux": "https://replicate.delivery/pbxt/ML6lOgKvDAmP2ByQnHlV3D7y0Xuerf3lDJGksDs2ixd1fzdz/yoni2.jpg",
      "width": 1024,
      "height": 1024,
      "prompt": "a man riding a skateboard",
      "num_outputs": 1,
      "control_image": "https://replicate.delivery/pbxt/ML6lOSgpOfStaqp64xbmJMRLwdLHYGZqsAoQAOdPjKfAE0fk/man_on_skateboard.webp",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.02,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2025-01-17T21:38:01.325336Z",
  "created_at": "2025-01-17T21:35:26.592000Z",
  "data_removed": false,
  "error": null,
  "id": "1vybxphzg1rmc0cmerrt8qjnqw",
  "input": {
    "redux": "https://replicate.delivery/pbxt/ML6lOgKvDAmP2ByQnHlV3D7y0Xuerf3lDJGksDs2ixd1fzdz/yoni2.jpg",
    "width": 1024,
    "height": 1024,
    "prompt": "a man riding a skateboard",
    "num_outputs": 1,
    "control_image": "https://replicate.delivery/pbxt/ML6lOSgpOfStaqp64xbmJMRLwdLHYGZqsAoQAOdPjKfAE0fk/man_on_skateboard.webp",
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "redux_strength": 0.02,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 63979\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:25,  1.06it/s]\n  7%|▋         | 2/28 [00:01<00:21,  1.19it/s]\n 11%|█         | 3/28 [00:02<00:22,  1.13it/s]\n 14%|█▍        | 4/28 [00:03<00:21,  1.10it/s]\n 18%|█▊        | 5/28 [00:04<00:21,  1.09it/s]\n 21%|██▏       | 6/28 [00:05<00:20,  1.08it/s]\n 25%|██▌       | 7/28 [00:06<00:19,  1.07it/s]\n 29%|██▊       | 8/28 [00:07<00:18,  1.07it/s]\n 32%|███▏      | 9/28 [00:08<00:17,  1.07it/s]\n 36%|███▌      | 10/28 [00:09<00:16,  1.06it/s]\n 39%|███▉      | 11/28 [00:10<00:15,  1.06it/s]\n 43%|████▎     | 12/28 [00:11<00:15,  1.06it/s]\n 46%|████▋     | 13/28 [00:12<00:14,  1.06it/s]\n 50%|█████     | 14/28 [00:13<00:13,  1.06it/s]\n 54%|█████▎    | 15/28 [00:13<00:12,  1.06it/s]\n 57%|█████▋    | 16/28 [00:14<00:11,  1.06it/s]\n 61%|██████    | 17/28 [00:15<00:10,  1.06it/s]\n 64%|██████▍   | 18/28 [00:16<00:09,  1.06it/s]\n 68%|██████▊   | 19/28 [00:17<00:08,  1.06it/s]\n 71%|███████▏  | 20/28 [00:18<00:07,  1.06it/s]\n 75%|███████▌  | 21/28 [00:19<00:06,  1.06it/s]\n 79%|███████▊  | 22/28 [00:20<00:05,  1.06it/s]\n 82%|████████▏ | 23/28 [00:21<00:04,  1.06it/s]\n 86%|████████▌ | 24/28 [00:22<00:03,  1.06it/s]\n 89%|████████▉ | 25/28 [00:23<00:02,  1.06it/s]\n 93%|█████████▎| 26/28 [00:24<00:01,  1.06it/s]\n 96%|█████████▋| 27/28 [00:25<00:00,  1.06it/s]\n100%|██████████| 28/28 [00:26<00:00,  1.06it/s]\n100%|██████████| 28/28 [00:26<00:00,  1.07it/s]",
  "metrics": {
    "predict_time": 47.817573414,
    "total_time": 154.733336
  },
  "output": [
    "https://replicate.delivery/xezq/1tbYbNrU2e0xOa4UYJrMaGHH3qpXHdelLjFgo0DyenBy9PMoA/out-0.webp"
  ],
  "started_at": "2025-01-17T21:37:13.507762Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-anjfbaggxt656nbwx65nzaxt2ojitqouuu2u43noyecgwlmzdzba",
    "get": "https://api.replicate.com/v1/predictions/1vybxphzg1rmc0cmerrt8qjnqw",
    "cancel": "https://api.replicate.com/v1/predictions/1vybxphzg1rmc0cmerrt8qjnqw/cancel"
  },
  "version": "2d77f82dce2466dee3646296420ef620bf8ab28580ef4cd7c60d22d8900e5337"
}

Generated in

47.8 seconds

jhorovitz/flux-dev-redux-control:2d77f82dce2466dee3646296420ef620bf8ab28580ef4cd7c60d22d8900e5337

Prediction

Model

jhorovitz/flux-dev-redux-control:2d77f82d

ID

4cr0ctb7phrme0cmes1abf45x8

Status

Succeeded

Source

Web

Hardware

H100

Total duration

1m 49s

Created

5 months ago

Input

redux
width: 1024
height: 1024
prompt: A man dunks a basketball.
num_outputs: 1
control_image
output_format: webp
guidance_scale: 3.5
output_quality: 80
redux_strength: 0.03
num_inference_steps: 28

{
  "redux": "https://replicate.delivery/pbxt/ML738gNkiO5CwfgYYFzurowFWCSw0XuHqymyr2G3Yn9UHCFE/yoni2.jpg",
  "width": 1024,
  "height": 1024,
  "prompt": "A man dunks a basketball.",
  "num_outputs": 1,
  "control_image": "https://replicate.delivery/pbxt/ML738uwQCTWapriJXkto879KRvTTkXT8svws30FJavJbM3Xr/dunk.webp",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "redux_strength": 0.03,
  "num_inference_steps": 28
}

npm install replicate

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 jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jhorovitz/flux-dev-redux-control:2d77f82dce2466dee3646296420ef620bf8ab28580ef4cd7c60d22d8900e5337",
  {
    input: {
      redux: "https://replicate.delivery/pbxt/ML738gNkiO5CwfgYYFzurowFWCSw0XuHqymyr2G3Yn9UHCFE/yoni2.jpg",
      width: 1024,
      height: 1024,
      prompt: "A man dunks a basketball.",
      num_outputs: 1,
      control_image: "https://replicate.delivery/pbxt/ML738uwQCTWapriJXkto879KRvTTkXT8svws30FJavJbM3Xr/dunk.webp",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      redux_strength: 0.03,
      num_inference_steps: 28
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

Run jhorovitz/flux-dev-redux-control using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jhorovitz/flux-dev-redux-control:2d77f82dce2466dee3646296420ef620bf8ab28580ef4cd7c60d22d8900e5337",
    input={
        "redux": "https://replicate.delivery/pbxt/ML738gNkiO5CwfgYYFzurowFWCSw0XuHqymyr2G3Yn9UHCFE/yoni2.jpg",
        "width": 1024,
        "height": 1024,
        "prompt": "A man dunks a basketball.",
        "num_outputs": 1,
        "control_image": "https://replicate.delivery/pbxt/ML738uwQCTWapriJXkto879KRvTTkXT8svws30FJavJbM3Xr/dunk.webp",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "redux_strength": 0.03,
        "num_inference_steps": 28
    }
)
print(output)

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

Run jhorovitz/flux-dev-redux-control 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 $'{
    "version": "jhorovitz/flux-dev-redux-control:2d77f82dce2466dee3646296420ef620bf8ab28580ef4cd7c60d22d8900e5337",
    "input": {
      "redux": "https://replicate.delivery/pbxt/ML738gNkiO5CwfgYYFzurowFWCSw0XuHqymyr2G3Yn9UHCFE/yoni2.jpg",
      "width": 1024,
      "height": 1024,
      "prompt": "A man dunks a basketball.",
      "num_outputs": 1,
      "control_image": "https://replicate.delivery/pbxt/ML738uwQCTWapriJXkto879KRvTTkXT8svws30FJavJbM3Xr/dunk.webp",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.03,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/jhorovitz/flux-dev-redux-control@sha256:2d77f82dce2466dee3646296420ef620bf8ab28580ef4cd7c60d22d8900e5337 \
  -i 'redux="https://replicate.delivery/pbxt/ML738gNkiO5CwfgYYFzurowFWCSw0XuHqymyr2G3Yn9UHCFE/yoni2.jpg"' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="A man dunks a basketball."' \
  -i 'num_outputs=1' \
  -i 'control_image="https://replicate.delivery/pbxt/ML738uwQCTWapriJXkto879KRvTTkXT8svws30FJavJbM3Xr/dunk.webp"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=3.5' \
  -i 'output_quality=80' \
  -i 'redux_strength=0.03' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/jhorovitz/flux-dev-redux-control@sha256:2d77f82dce2466dee3646296420ef620bf8ab28580ef4cd7c60d22d8900e5337
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "redux": "https://replicate.delivery/pbxt/ML738gNkiO5CwfgYYFzurowFWCSw0XuHqymyr2G3Yn9UHCFE/yoni2.jpg",
      "width": 1024,
      "height": 1024,
      "prompt": "A man dunks a basketball.",
      "num_outputs": 1,
      "control_image": "https://replicate.delivery/pbxt/ML738uwQCTWapriJXkto879KRvTTkXT8svws30FJavJbM3Xr/dunk.webp",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "redux_strength": 0.03,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2025-01-17T21:55:59.684308Z",
  "created_at": "2025-01-17T21:54:10.996000Z",
  "data_removed": false,
  "error": null,
  "id": "4cr0ctb7phrme0cmes1abf45x8",
  "input": {
    "redux": "https://replicate.delivery/pbxt/ML738gNkiO5CwfgYYFzurowFWCSw0XuHqymyr2G3Yn9UHCFE/yoni2.jpg",
    "width": 1024,
    "height": 1024,
    "prompt": "A man dunks a basketball.",
    "num_outputs": 1,
    "control_image": "https://replicate.delivery/pbxt/ML738uwQCTWapriJXkto879KRvTTkXT8svws30FJavJbM3Xr/dunk.webp",
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "redux_strength": 0.03,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 46977\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:25,  1.04it/s]\n  7%|▋         | 2/28 [00:01<00:22,  1.17it/s]\n 11%|█         | 3/28 [00:02<00:22,  1.11it/s]\n 14%|█▍        | 4/28 [00:03<00:22,  1.08it/s]\n 18%|█▊        | 5/28 [00:04<00:21,  1.07it/s]\n 21%|██▏       | 6/28 [00:05<00:20,  1.06it/s]\n 25%|██▌       | 7/28 [00:06<00:19,  1.06it/s]\n 29%|██▊       | 8/28 [00:07<00:18,  1.05it/s]\n 32%|███▏      | 9/28 [00:08<00:18,  1.05it/s]\n 36%|███▌      | 10/28 [00:09<00:17,  1.05it/s]\n 39%|███▉      | 11/28 [00:10<00:16,  1.05it/s]\n 43%|████▎     | 12/28 [00:11<00:15,  1.05it/s]\n 46%|████▋     | 13/28 [00:12<00:14,  1.05it/s]\n 50%|█████     | 14/28 [00:13<00:13,  1.05it/s]\n 54%|█████▎    | 15/28 [00:14<00:12,  1.05it/s]\n 57%|█████▋    | 16/28 [00:15<00:11,  1.05it/s]\n 61%|██████    | 17/28 [00:16<00:10,  1.05it/s]\n 64%|██████▍   | 18/28 [00:17<00:09,  1.05it/s]\n 68%|██████▊   | 19/28 [00:17<00:08,  1.05it/s]\n 71%|███████▏  | 20/28 [00:18<00:07,  1.05it/s]\n 75%|███████▌  | 21/28 [00:19<00:06,  1.05it/s]\n 79%|███████▊  | 22/28 [00:20<00:05,  1.05it/s]\n 82%|████████▏ | 23/28 [00:21<00:04,  1.05it/s]\n 86%|████████▌ | 24/28 [00:22<00:03,  1.05it/s]\n 89%|████████▉ | 25/28 [00:23<00:02,  1.05it/s]\n 93%|█████████▎| 26/28 [00:24<00:01,  1.05it/s]\n 96%|█████████▋| 27/28 [00:25<00:00,  1.05it/s]\n100%|██████████| 28/28 [00:26<00:00,  1.05it/s]\n100%|██████████| 28/28 [00:26<00:00,  1.05it/s]",
  "metrics": {
    "predict_time": 50.448543743,
    "total_time": 108.688308
  },
  "output": [
    "https://replicate.delivery/xezq/yewaLp2VvnxOCS6TsBTELeDem4me1bnW5P1mnz42ffdy7DiBF/out-0.webp"
  ],
  "started_at": "2025-01-17T21:55:09.235764Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-i4jd3qgsyovilscszqpz4zxrxr2p4yf7kixhpbkp6hcl3vtxpbwq",
    "get": "https://api.replicate.com/v1/predictions/4cr0ctb7phrme0cmes1abf45x8",
    "cancel": "https://api.replicate.com/v1/predictions/4cr0ctb7phrme0cmes1abf45x8/cancel"
  },
  "version": "2d77f82dce2466dee3646296420ef620bf8ab28580ef4cd7c60d22d8900e5337"
}

Generated in

50.5 seconds