lucataco/realistic-vision-v5-img2img – Run with an API on Replicate

Input

image

*file

Input image

prompt

string

Shift + Return to add a new line

Default: "a latina woman with a pearl earring"

negative_prompt

string

Shift + Return to add a new line

(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation

Default: "disfigured, kitsch, ugly, oversaturated, greain, low-res, deformed, blurry"

steps

integer

(minimum: 0, maximum: 50)

num_inference_steps

Default: 30

strength

number

(minimum: 0, maximum: 1)

strength/weight

Default: 0.8

seed

integer

Leave blank to randomize

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

npx create-replicate --model=lucataco/realistic-vision-v5-img2img

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 lucataco/realistic-vision-v5-img2img using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/realistic-vision-v5-img2img:82bbb4595458d6be142450fc6d8c4d79c936b92bd184dd2d6dd71d0796159819",
  {
    input: {
      seed: 50983,
      image: "https://replicate.delivery/pbxt/JMESNk5z9xLE0aSICVprNYUUFbiltwjQJFns2aK50ukGMEe0/demo.jpg",
      steps: 30,
      prompt: "a latina woman with a pearl earring",
      strength: 0.8,
      negative_prompt: "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation"
    }
  }
);
console.log(output);

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 lucataco/realistic-vision-v5-img2img using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/realistic-vision-v5-img2img:82bbb4595458d6be142450fc6d8c4d79c936b92bd184dd2d6dd71d0796159819",
    input={
        "seed": 50983,
        "image": "https://replicate.delivery/pbxt/JMESNk5z9xLE0aSICVprNYUUFbiltwjQJFns2aK50ukGMEe0/demo.jpg",
        "steps": 30,
        "prompt": "a latina woman with a pearl earring",
        "strength": 0.8,
        "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation"
    }
)
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 lucataco/realistic-vision-v5-img2img 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": "82bbb4595458d6be142450fc6d8c4d79c936b92bd184dd2d6dd71d0796159819",
    "input": {
      "seed": 50983,
      "image": "https://replicate.delivery/pbxt/JMESNk5z9xLE0aSICVprNYUUFbiltwjQJFns2aK50ukGMEe0/demo.jpg",
      "steps": 30,
      "prompt": "a latina woman with a pearl earring",
      "strength": 0.8,
      "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-08-16T01:24:09.995355Z",
  "created_at": "2023-08-16T01:23:57.916443Z",
  "data_removed": false,
  "error": null,
  "id": "bufjzp3b344buwb5h2ecrfrtsa",
  "input": {
    "seed": 50983,
    "image": "https://replicate.delivery/pbxt/JMESNk5z9xLE0aSICVprNYUUFbiltwjQJFns2aK50ukGMEe0/demo.jpg",
    "steps": 30,
    "prompt": "a latina woman with a pearl earring",
    "strength": 0.8,
    "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation"
  },
  "logs": "Using seed: 50983\n  0%|          | 0/24 [00:00<?, ?it/s]\n  4%|▍         | 1/24 [00:00<00:09,  2.51it/s]\n  8%|▊         | 2/24 [00:00<00:08,  2.51it/s]\n 12%|█▎        | 3/24 [00:01<00:08,  2.50it/s]\n 17%|█▋        | 4/24 [00:01<00:08,  2.50it/s]\n 21%|██        | 5/24 [00:02<00:07,  2.49it/s]\n 25%|██▌       | 6/24 [00:02<00:07,  2.49it/s]\n 29%|██▉       | 7/24 [00:02<00:06,  2.49it/s]\n 33%|███▎      | 8/24 [00:03<00:06,  2.49it/s]\n 38%|███▊      | 9/24 [00:03<00:06,  2.49it/s]\n 42%|████▏     | 10/24 [00:04<00:05,  2.49it/s]\n 46%|████▌     | 11/24 [00:04<00:05,  2.49it/s]\n 50%|█████     | 12/24 [00:04<00:04,  2.48it/s]\n 54%|█████▍    | 13/24 [00:05<00:04,  2.48it/s]\n 58%|█████▊    | 14/24 [00:05<00:04,  2.48it/s]\n 62%|██████▎   | 15/24 [00:06<00:03,  2.48it/s]\n 67%|██████▋   | 16/24 [00:06<00:03,  2.48it/s]\n 71%|███████   | 17/24 [00:06<00:02,  2.48it/s]\n 75%|███████▌  | 18/24 [00:07<00:02,  2.48it/s]\n 79%|███████▉  | 19/24 [00:07<00:02,  2.48it/s]\n 83%|████████▎ | 20/24 [00:08<00:01,  2.48it/s]\n 88%|████████▊ | 21/24 [00:08<00:01,  2.48it/s]\n 92%|█████████▏| 22/24 [00:08<00:00,  2.48it/s]\n 96%|█████████▌| 23/24 [00:09<00:00,  2.48it/s]\n100%|██████████| 24/24 [00:09<00:00,  2.48it/s]\n100%|██████████| 24/24 [00:09<00:00,  2.48it/s]",
  "metrics": {
    "predict_time": 12.056523,
    "total_time": 12.078912
  },
  "output": "https://replicate.delivery/pbxt/o6QHnbAobJqmOt0IWUFptgHIp9rx9Npw9TO3UuEvSlcOXnWE/output.png",
  "started_at": "2023-08-16T01:23:57.938832Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/bufjzp3b344buwb5h2ecrfrtsa",
    "cancel": "https://api.replicate.com/v1/predictions/bufjzp3b344buwb5h2ecrfrtsa/cancel"
  },
  "version": "82bbb4595458d6be142450fc6d8c4d79c936b92bd184dd2d6dd71d0796159819"
}

Generated in

12.1 seconds

Tweak it Report

Run time and cost

This model costs approximately $0.015 to run on Replicate, or 66 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 L40S GPU hardware. Predictions typically complete within 16 seconds. The predict time for this model varies significantly based on the inputs.