asiryan/flux-dev – Run with an API on Replicate

Input

prompt

string

Shift + Return to add a new line

black forest gateau cake spelling out the words "FLUX DEV", tasty, food photography, dynamic shotblack forest gateau cake spelling out the words "FLUX DEV", tasty, food photography, dynamic shot

Prompt for generated image

Default: "a tiny astronaut hatching from an egg on the moon"

image

file

Input image for image to image mode. The aspect ratio of your output will match this image

width

integer

Width of output image

Default: 1024

height

integer

Height of output image

Default: 1024

strength

number

(minimum: 0, maximum: 1)

Prompt strength (or denoising strength) when using image to image. 1.0 corresponds to full destruction of information in image.

Default: 0.8

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 100)

Number of inference steps

Default: 28

guidance_scale

number

(minimum: 0, maximum: 10)

Guidance scale for the diffusion process

Default: 3.5

seed

integer

Random seed. Set for reproducible generation

output_format

string

Format of the output images

Default: "png"

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: 100

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

npx create-replicate --model=asiryan/flux-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";

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

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

const output = await replicate.run(
  "asiryan/flux-dev:6871951c85104c710f9a723c3151465b88f4d9190919d498bfe99f8d94bc5197",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "black forest gateau cake spelling out the words \"FLUX DEV\", tasty, food photography, dynamic shot",
      strength: 0.8,
      num_outputs: 1,
      output_format: "png",
      guidance_scale: 3.5,
      output_quality: 100,
      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.

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

output = replicate.run(
    "asiryan/flux-dev:6871951c85104c710f9a723c3151465b88f4d9190919d498bfe99f8d94bc5197",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "black forest gateau cake spelling out the words \"FLUX DEV\", tasty, food photography, dynamic shot",
        "strength": 0.8,
        "num_outputs": 1,
        "output_format": "png",
        "guidance_scale": 3.5,
        "output_quality": 100,
        "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 asiryan/flux-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 $'{
    "version": "6871951c85104c710f9a723c3151465b88f4d9190919d498bfe99f8d94bc5197",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "black forest gateau cake spelling out the words \\"FLUX DEV\\", tasty, food photography, dynamic shot",
      "strength": 0.8,
      "num_outputs": 1,
      "output_format": "png",
      "guidance_scale": 3.5,
      "output_quality": 100,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-09-19T21:30:54.891155Z",
  "created_at": "2024-09-19T21:30:40.471000Z",
  "data_removed": false,
  "error": null,
  "id": "yzp5k8y1txrj00cj1grsw0qm6c",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "black forest gateau cake spelling out the words \"FLUX DEV\", tasty, food photography, dynamic shot",
    "num_outputs": 1,
    "output_format": "png",
    "guidance_scale": 3.5,
    "output_quality": 100,
    "prompt_strength": 0.8,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 60515\nPrompt: black forest gateau cake spelling out the words \"FLUX DEV\", tasty, food photography, dynamic shot\ntxt2img mode\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:12,  2.09it/s]\n  7%|▋         | 2/28 [00:00<00:09,  2.62it/s]\n 11%|█         | 3/28 [00:01<00:10,  2.34it/s]\n 14%|█▍        | 4/28 [00:01<00:10,  2.23it/s]\n 18%|█▊        | 5/28 [00:02<00:10,  2.18it/s]\n 21%|██▏       | 6/28 [00:02<00:10,  2.14it/s]\n 25%|██▌       | 7/28 [00:03<00:09,  2.12it/s]\n 29%|██▊       | 8/28 [00:03<00:09,  2.11it/s]\n 32%|███▏      | 9/28 [00:04<00:09,  2.10it/s]\n 36%|███▌      | 10/28 [00:04<00:08,  2.10it/s]\n 39%|███▉      | 11/28 [00:05<00:08,  2.09it/s]\n 43%|████▎     | 12/28 [00:05<00:07,  2.09it/s]\n 46%|████▋     | 13/28 [00:06<00:07,  2.09it/s]\n 50%|█████     | 14/28 [00:06<00:06,  2.08it/s]\n 54%|█████▎    | 15/28 [00:07<00:06,  2.08it/s]\n 57%|█████▋    | 16/28 [00:07<00:05,  2.08it/s]\n 61%|██████    | 17/28 [00:08<00:05,  2.08it/s]\n 64%|██████▍   | 18/28 [00:08<00:04,  2.08it/s]\n 68%|██████▊   | 19/28 [00:08<00:04,  2.08it/s]\n 71%|███████▏  | 20/28 [00:09<00:03,  2.08it/s]\n 75%|███████▌  | 21/28 [00:09<00:03,  2.08it/s]\n 79%|███████▊  | 22/28 [00:10<00:02,  2.08it/s]\n 82%|████████▏ | 23/28 [00:10<00:02,  2.08it/s]\n 86%|████████▌ | 24/28 [00:11<00:01,  2.08it/s]\n 89%|████████▉ | 25/28 [00:11<00:01,  2.07it/s]\n 93%|█████████▎| 26/28 [00:12<00:00,  2.08it/s]\n 96%|█████████▋| 27/28 [00:12<00:00,  2.07it/s]\n100%|██████████| 28/28 [00:13<00:00,  2.07it/s]\n100%|██████████| 28/28 [00:13<00:00,  2.10it/s]",
  "metrics": {
    "predict_time": 14.408146509,
    "total_time": 14.420155
  },
  "output": [
    "https://replicate.delivery/yhqm/5upIb1PiJorIH1QFmj0igJw7dtcxXjfMOKtvLYqXUjOHUSvJA/out-0.png"
  ],
  "started_at": "2024-09-19T21:30:40.483009Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/yzp5k8y1txrj00cj1grsw0qm6c",
    "cancel": "https://api.replicate.com/v1/predictions/yzp5k8y1txrj00cj1grsw0qm6c/cancel"
  },
  "version": "e904c4442564f8413c17fc669f9d48400dbd01d6881f9eb8ff9ad0f00bf1bca5"
}

Generated in

14.4 seconds

Tweak it ShareReport

This output was created using a different version of the model, asiryan/flux-dev:e904c444.

Run time and cost

This model costs approximately $0.18 to run on Replicate, or 5 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 132 seconds. The predict time for this model varies significantly based on the inputs.

asiryan / flux-dev

Input

Output

Examples

Run time and cost

Readme

Logs (yzp5k8y1txrj00cj1grsw0qm6c)