jhorovitz/omini-schnell:98ccf187 – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

jhorovitz /omini-schnell:98ccf187

Input

prompt

string

Shift + Return to add a new line

A grid of four images of this shoe. In each image the shoe is in the same position, but the background is different. One on snow climbing a mountain. One in a lush jungle. One in the desert standing on a sand dune. And one walking on a cobblestone street.A grid of four images of this shoe. In each image the shoe is in the same position, but the background is different. One on snow climbing a mountain. One in a lush jungle. One in the desert standing on a sand dune. And one walking on a cobblestone street.

Text prompt

task

string

OminiControl task

Default: "subject_512"

control_image

file

Control image.

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 50)

Number of inference steps

Default: 8

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: "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

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

npx create-replicate --model=jhorovitz/omini-schnell

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 jhorovitz/omini-schnell using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jhorovitz/omini-schnell:98ccf187274f4237a514ed82cd372629b90a010e1203c956cae7f28364f1cafb",
  {
    input: {
      task: "subject_1024",
      prompt: "A grid of four images of this shoe. In each image the shoe is in the same position, but the background is different. One on snow climbing a mountain. One in a lush jungle. One in the desert standing on a sand dune. And one walking on a cobblestone street.",
      num_outputs: 1,
      control_image: "https://api.replicate.com/v1/files/NjM1N2E2MDgtMzAxYS00NjY0LWJiMzItN2E2MDAwYTlmYTdh/download?expiry=1739819676&owner=jhorovitz&signature=piMNQQ5l9ZzxgPFs4Y%252Bmb54Iud07pa5eRcsi4NH2XlQ%253D",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      num_inference_steps: 8
    }
  }
);

// 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 jhorovitz/omini-schnell using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jhorovitz/omini-schnell:98ccf187274f4237a514ed82cd372629b90a010e1203c956cae7f28364f1cafb",
    input={
        "task": "subject_1024",
        "prompt": "A grid of four images of this shoe. In each image the shoe is in the same position, but the background is different. One on snow climbing a mountain. One in a lush jungle. One in the desert standing on a sand dune. And one walking on a cobblestone street.",
        "num_outputs": 1,
        "control_image": "https://api.replicate.com/v1/files/NjM1N2E2MDgtMzAxYS00NjY0LWJiMzItN2E2MDAwYTlmYTdh/download?expiry=1739819676&owner=jhorovitz&signature=piMNQQ5l9ZzxgPFs4Y%252Bmb54Iud07pa5eRcsi4NH2XlQ%253D",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "num_inference_steps": 8
    }
)
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 jhorovitz/omini-schnell 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/omini-schnell:98ccf187274f4237a514ed82cd372629b90a010e1203c956cae7f28364f1cafb",
    "input": {
      "task": "subject_1024",
      "prompt": "A grid of four images of this shoe. In each image the shoe is in the same position, but the background is different. One on snow climbing a mountain. One in a lush jungle. One in the desert standing on a sand dune. And one walking on a cobblestone street.",
      "num_outputs": 1,
      "control_image": "https://api.replicate.com/v1/files/NjM1N2E2MDgtMzAxYS00NjY0LWJiMzItN2E2MDAwYTlmYTdh/download?expiry=1739819676&owner=jhorovitz&signature=piMNQQ5l9ZzxgPFs4Y%252Bmb54Iud07pa5eRcsi4NH2XlQ%253D",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "num_inference_steps": 8
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-02-17T18:14:42.231232Z",
  "created_at": "2025-02-17T18:14:36.240000Z",
  "data_removed": false,
  "error": null,
  "id": "hptjhq43t1rj00cn2mf95anyer",
  "input": {
    "task": "subject_1024",
    "prompt": "A grid of four images of this shoe. In each image the shoe is in the same position, but the background is different. One on snow climbing a mountain. One in a lush jungle. One in the desert standing on a sand dune. And one walking on a cobblestone street.",
    "num_outputs": 1,
    "control_image": "https://api.replicate.com/v1/files/NjM1N2E2MDgtMzAxYS00NjY0LWJiMzItN2E2MDAwYTlmYTdh/download?expiry=1739819676&owner=jhorovitz&signature=piMNQQ5l9ZzxgPFs4Y%252Bmb54Iud07pa5eRcsi4NH2XlQ%253D",
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "num_inference_steps": 8
  },
  "logs": "Using seed: 36602\n  0%|          | 0/8 [00:00<?, ?it/s]\n 12%|█▎        | 1/8 [00:00<00:04,  1.55it/s]\n 25%|██▌       | 2/8 [00:01<00:03,  1.68it/s]\n 38%|███▊      | 3/8 [00:01<00:03,  1.61it/s]\n 50%|█████     | 4/8 [00:02<00:02,  1.58it/s]\n 62%|██████▎   | 5/8 [00:03<00:01,  1.57it/s]\n 75%|███████▌  | 6/8 [00:03<00:01,  1.56it/s]\n 88%|████████▊ | 7/8 [00:04<00:00,  1.56it/s]\n100%|██████████| 8/8 [00:05<00:00,  1.55it/s]\n100%|██████████| 8/8 [00:05<00:00,  1.57it/s]",
  "metrics": {
    "predict_time": 5.983030502,
    "total_time": 5.991232
  },
  "output": [
    "https://replicate.delivery/yhqm/ODH7LrCZgt41OJxeYuy0jEoIxebuixWlGYBJF9wZvGvS6SQUA/out-0.webp"
  ],
  "started_at": "2025-02-17T18:14:36.248201Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/yswh-xr6jtupprbcxzcma6detolkj4mxkc75yyhsjfzyqkek4z2r7iqdq",
    "get": "https://api.replicate.com/v1/predictions/hptjhq43t1rj00cn2mf95anyer",
    "cancel": "https://api.replicate.com/v1/predictions/hptjhq43t1rj00cn2mf95anyer/cancel"
  },
  "version": "98ccf187274f4237a514ed82cd372629b90a010e1203c956cae7f28364f1cafb"
}

Generated in

6.0 seconds

Tweak it ShareReport