cjwbw/sd-textual-inversion-ugly-sonic – Run with an API on Replicate

cjwbw / sd-textual-inversion-ugly-sonic

stable-diffusion-textual-inversion fine-tuned with ugly sonic

Cold

Public
2K runs
T4

Iterate in the playground

Run with an API

Playground API Examples README Versions

Input

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

npx create-replicate --model=cjwbw/sd-textual-inversion-ugly-sonic

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 cjwbw/sd-textual-inversion-ugly-sonic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "cjwbw/sd-textual-inversion-ugly-sonic:57d8c937dead2f8437b8c93e586fa8dec20841dfdfc63ff5b4719ee8b867d483",
  {
    input: {
      prompt: "a beautiful portrait of [[[<ugly-sonic>]]] by Leonardo Da Vinci, (((painting, oil on canvas)))",
      num_outputs: 1,
      guidance_scale: 7.5,
      num_inference_steps: 50
    }
  }
);

// 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 cjwbw/sd-textual-inversion-ugly-sonic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "cjwbw/sd-textual-inversion-ugly-sonic:57d8c937dead2f8437b8c93e586fa8dec20841dfdfc63ff5b4719ee8b867d483",
    input={
        "prompt": "a beautiful portrait of [[[<ugly-sonic>]]] by Leonardo Da Vinci, (((painting, oil on canvas)))",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "num_inference_steps": 50
    }
)
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 cjwbw/sd-textual-inversion-ugly-sonic 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": "cjwbw/sd-textual-inversion-ugly-sonic:57d8c937dead2f8437b8c93e586fa8dec20841dfdfc63ff5b4719ee8b867d483",
    "input": {
      "prompt": "a beautiful portrait of [[[<ugly-sonic>]]] by Leonardo Da Vinci, (((painting, oil on canvas)))",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-09-19T20:41:36.434355Z",
  "created_at": "2022-09-19T20:41:11.488251Z",
  "data_removed": false,
  "error": null,
  "id": "lhd5ocvcubgtfbqemc67xqs3ue",
  "input": {
    "prompt": "a beautiful portrait of [[[<ugly-sonic>]]] by Leonardo Da Vinci, (((painting, oil on canvas)))",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 939\nGlobal seed set to 939\n\n  0%|          | 0/51 [00:00<?, ?it/s]\n  2%|▏         | 1/51 [00:00<00:05,  8.55it/s]\n  4%|▍         | 2/51 [00:00<00:10,  4.76it/s]\n  6%|▌         | 3/51 [00:00<00:11,  4.15it/s]\n  8%|▊         | 4/51 [00:00<00:12,  3.80it/s]\n 10%|▉         | 5/51 [00:01<00:12,  3.73it/s]\n 12%|█▏        | 6/51 [00:01<00:12,  3.70it/s]\n 14%|█▎        | 7/51 [00:01<00:11,  3.67it/s]\n 16%|█▌        | 8/51 [00:02<00:11,  3.60it/s]\n 18%|█▊        | 9/51 [00:02<00:11,  3.60it/s]\n 20%|█▉        | 10/51 [00:02<00:11,  3.60it/s]\n 22%|██▏       | 11/51 [00:02<00:11,  3.58it/s]\n 24%|██▎       | 12/51 [00:03<00:10,  3.55it/s]\n 25%|██▌       | 13/51 [00:03<00:10,  3.56it/s]\n 27%|██▋       | 14/51 [00:03<00:10,  3.58it/s]\n 29%|██▉       | 15/51 [00:04<00:10,  3.55it/s]\n 31%|███▏      | 16/51 [00:04<00:09,  3.54it/s]\n 33%|███▎      | 17/51 [00:04<00:09,  3.54it/s]\n 35%|███▌      | 18/51 [00:04<00:09,  3.54it/s]\n 37%|███▋      | 19/51 [00:05<00:09,  3.52it/s]\n 39%|███▉      | 20/51 [00:05<00:08,  3.52it/s]\n 41%|████      | 21/51 [00:05<00:08,  3.54it/s]\n 43%|████▎     | 22/51 [00:06<00:08,  3.52it/s]\n 45%|████▌     | 23/51 [00:06<00:07,  3.52it/s]\n 47%|████▋     | 24/51 [00:06<00:07,  3.54it/s]\n 49%|████▉     | 25/51 [00:06<00:07,  3.54it/s]\n 51%|█████     | 26/51 [00:07<00:07,  3.53it/s]\n 53%|█████▎    | 27/51 [00:07<00:06,  3.52it/s]\n 55%|█████▍    | 28/51 [00:07<00:06,  3.52it/s]\n 57%|█████▋    | 29/51 [00:08<00:06,  3.51it/s]\n 59%|█████▉    | 30/51 [00:08<00:05,  3.51it/s]\n 61%|██████    | 31/51 [00:08<00:05,  3.51it/s]\n 63%|██████▎   | 32/51 [00:08<00:05,  3.51it/s]\n 65%|██████▍   | 33/51 [00:09<00:05,  3.52it/s]\n 67%|██████▋   | 34/51 [00:09<00:04,  3.52it/s]\n 69%|██████▊   | 35/51 [00:09<00:04,  3.52it/s]\n 71%|███████   | 36/51 [00:10<00:04,  3.52it/s]\n 73%|███████▎  | 37/51 [00:10<00:03,  3.52it/s]\n 75%|███████▍  | 38/51 [00:10<00:03,  3.52it/s]\n 76%|███████▋  | 39/51 [00:10<00:03,  3.52it/s]\n 78%|███████▊  | 40/51 [00:11<00:03,  3.51it/s]\n 80%|████████  | 41/51 [00:11<00:02,  3.49it/s]\n 82%|████████▏ | 42/51 [00:11<00:02,  3.49it/s]\n 84%|████████▍ | 43/51 [00:12<00:02,  3.48it/s]\n 86%|████████▋ | 44/51 [00:12<00:02,  3.49it/s]\n 88%|████████▊ | 45/51 [00:12<00:01,  3.50it/s]\n 90%|█████████ | 46/51 [00:12<00:01,  3.50it/s]\n 92%|█████████▏| 47/51 [00:13<00:01,  3.50it/s]\n 94%|█████████▍| 48/51 [00:13<00:00,  3.48it/s]\n 96%|█████████▌| 49/51 [00:13<00:00,  3.49it/s]\n 98%|█████████▊| 50/51 [00:14<00:00,  3.50it/s]\n100%|██████████| 51/51 [00:14<00:00,  3.51it/s]\n100%|██████████| 51/51 [00:14<00:00,  3.57it/s]",
  "metrics": {
    "predict_time": 15.706281,
    "total_time": 24.946104
  },
  "output": [
    "https://replicate.delivery/mgxm/d3c1458b-c2a7-446d-8799-9bd0bf2d6cbc/out-0.png"
  ],
  "started_at": "2022-09-19T20:41:20.728074Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/lhd5ocvcubgtfbqemc67xqs3ue",
    "cancel": "https://api.replicate.com/v1/predictions/lhd5ocvcubgtfbqemc67xqs3ue/cancel"
  },
  "version": "57d8c937dead2f8437b8c93e586fa8dec20841dfdfc63ff5b4719ee8b867d483"
}

Generated in

15.7 seconds

Tweak itReport

Using seed: 939
Global seed set to 939

  0%|          | 0/51 [00:00<?, ?it/s]
  2%|▏         | 1/51 [00:00<00:05,  8.55it/s]
  4%|▍         | 2/51 [00:00<00:10,  4.76it/s]
  6%|▌         | 3/51 [00:00<00:11,  4.15it/s]
  8%|▊         | 4/51 [00:00<00:12,  3.80it/s]
 10%|▉         | 5/51 [00:01<00:12,  3.73it/s]
 12%|█▏        | 6/51 [00:01<00:12,  3.70it/s]
 14%|█▎        | 7/51 [00:01<00:11,  3.67it/s]
 16%|█▌        | 8/51 [00:02<00:11,  3.60it/s]
 18%|█▊        | 9/51 [00:02<00:11,  3.60it/s]
 20%|█▉        | 10/51 [00:02<00:11,  3.60it/s]
 22%|██▏       | 11/51 [00:02<00:11,  3.58it/s]
 24%|██▎       | 12/51 [00:03<00:10,  3.55it/s]
 25%|██▌       | 13/51 [00:03<00:10,  3.56it/s]
 27%|██▋       | 14/51 [00:03<00:10,  3.58it/s]
 29%|██▉       | 15/51 [00:04<00:10,  3.55it/s]
 31%|███▏      | 16/51 [00:04<00:09,  3.54it/s]
 33%|███▎      | 17/51 [00:04<00:09,  3.54it/s]
 35%|███▌      | 18/51 [00:04<00:09,  3.54it/s]
 37%|███▋      | 19/51 [00:05<00:09,  3.52it/s]
 39%|███▉      | 20/51 [00:05<00:08,  3.52it/s]
 41%|████      | 21/51 [00:05<00:08,  3.54it/s]
 43%|████▎     | 22/51 [00:06<00:08,  3.52it/s]
 45%|████▌     | 23/51 [00:06<00:07,  3.52it/s]
 47%|████▋     | 24/51 [00:06<00:07,  3.54it/s]
 49%|████▉     | 25/51 [00:06<00:07,  3.54it/s]
 51%|█████     | 26/51 [00:07<00:07,  3.53it/s]
 53%|█████▎    | 27/51 [00:07<00:06,  3.52it/s]
 55%|█████▍    | 28/51 [00:07<00:06,  3.52it/s]
 57%|█████▋    | 29/51 [00:08<00:06,  3.51it/s]
 59%|█████▉    | 30/51 [00:08<00:05,  3.51it/s]
 61%|██████    | 31/51 [00:08<00:05,  3.51it/s]
 63%|██████▎   | 32/51 [00:08<00:05,  3.51it/s]
 65%|██████▍   | 33/51 [00:09<00:05,  3.52it/s]
 67%|██████▋   | 34/51 [00:09<00:04,  3.52it/s]
 69%|██████▊   | 35/51 [00:09<00:04,  3.52it/s]
 71%|███████   | 36/51 [00:10<00:04,  3.52it/s]
 73%|███████▎  | 37/51 [00:10<00:03,  3.52it/s]
 75%|███████▍  | 38/51 [00:10<00:03,  3.52it/s]
 76%|███████▋  | 39/51 [00:10<00:03,  3.52it/s]
 78%|███████▊  | 40/51 [00:11<00:03,  3.51it/s]
 80%|████████  | 41/51 [00:11<00:02,  3.49it/s]
 82%|████████▏ | 42/51 [00:11<00:02,  3.49it/s]
 84%|████████▍ | 43/51 [00:12<00:02,  3.48it/s]
 86%|████████▋ | 44/51 [00:12<00:02,  3.49it/s]
 88%|████████▊ | 45/51 [00:12<00:01,  3.50it/s]
 90%|█████████ | 46/51 [00:12<00:01,  3.50it/s]
 92%|█████████▏| 47/51 [00:13<00:01,  3.50it/s]
 94%|█████████▍| 48/51 [00:13<00:00,  3.48it/s]
 96%|█████████▌| 49/51 [00:13<00:00,  3.49it/s]
 98%|█████████▊| 50/51 [00:14<00:00,  3.50it/s]
100%|██████████| 51/51 [00:14<00:00,  3.51it/s]
100%|██████████| 51/51 [00:14<00:00,  3.57it/s]

Examples

View more examples

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 T4 GPU hardware. Predictions typically complete within 66 seconds. The predict time for this model varies significantly based on the inputs.