cjwbw/van-gogh-diffusion – Run with an API on Replicate

cjwbw / van-gogh-diffusion

Van Gough on Stable Diffusion via Dreambooth

Cold

Public
5.5K runs
T4
License

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/van-gogh-diffusion

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/van-gogh-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "cjwbw/van-gogh-diffusion:2d43b996608bd7d4aba4cacbe9b751399892a9d6cbc27a39f8f49347a3a16f9c",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "lvngvncnt, beautiful woman at sunset",
      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/van-gogh-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "cjwbw/van-gogh-diffusion:2d43b996608bd7d4aba4cacbe9b751399892a9d6cbc27a39f8f49347a3a16f9c",
    input={
        "width": 512,
        "height": 512,
        "prompt": "lvngvncnt, beautiful woman at sunset",
        "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/van-gogh-diffusion 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/van-gogh-diffusion:2d43b996608bd7d4aba4cacbe9b751399892a9d6cbc27a39f8f49347a3a16f9c",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "lvngvncnt, beautiful woman at sunset",
      "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": "2022-11-08T11:59:48.396239Z",
  "created_at": "2022-11-08T11:59:34.555360Z",
  "data_removed": false,
  "error": null,
  "id": "em3v3lrdtbednmu66bwyvhb4su",
  "input": {
    "width": 512,
    "height": 512,
    "prompt": "lvngvncnt, beautiful woman at sunset",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 53092\nGlobal seed set to 53092\n\n  0%|          | 0/51 [00:00<?, ?it/s]\n  2%|▏         | 1/51 [00:00<00:16,  3.02it/s]\n  4%|▍         | 2/51 [00:00<00:14,  3.48it/s]\n  6%|▌         | 3/51 [00:00<00:13,  3.65it/s]\n  8%|▊         | 4/51 [00:01<00:12,  3.75it/s]\n 10%|▉         | 5/51 [00:01<00:12,  3.77it/s]\n 12%|█▏        | 6/51 [00:01<00:11,  3.80it/s]\n 14%|█▎        | 7/51 [00:01<00:11,  3.82it/s]\n 16%|█▌        | 8/51 [00:02<00:11,  3.84it/s]\n 18%|█▊        | 9/51 [00:02<00:10,  3.84it/s]\n 20%|█▉        | 10/51 [00:02<00:10,  3.85it/s]\n 22%|██▏       | 11/51 [00:02<00:10,  3.85it/s]\n 24%|██▎       | 12/51 [00:03<00:10,  3.85it/s]\n 25%|██▌       | 13/51 [00:03<00:09,  3.85it/s]\n 27%|██▋       | 14/51 [00:03<00:09,  3.85it/s]\n 29%|██▉       | 15/51 [00:03<00:09,  3.85it/s]\n 31%|███▏      | 16/51 [00:04<00:09,  3.86it/s]\n 33%|███▎      | 17/51 [00:04<00:08,  3.85it/s]\n 35%|███▌      | 18/51 [00:04<00:08,  3.85it/s]\n 37%|███▋      | 19/51 [00:04<00:08,  3.85it/s]\n 39%|███▉      | 20/51 [00:05<00:08,  3.85it/s]\n 41%|████      | 21/51 [00:05<00:07,  3.86it/s]\n 43%|████▎     | 22/51 [00:05<00:07,  3.85it/s]\n 45%|████▌     | 23/51 [00:06<00:07,  3.85it/s]\n 47%|████▋     | 24/51 [00:06<00:07,  3.85it/s]\n 49%|████▉     | 25/51 [00:06<00:06,  3.85it/s]\n 51%|█████     | 26/51 [00:06<00:06,  3.86it/s]\n 53%|█████▎    | 27/51 [00:07<00:06,  3.85it/s]\n 55%|█████▍    | 28/51 [00:07<00:05,  3.85it/s]\n 57%|█████▋    | 29/51 [00:07<00:05,  3.84it/s]\n 59%|█████▉    | 30/51 [00:07<00:05,  3.84it/s]\n 61%|██████    | 31/51 [00:08<00:05,  3.85it/s]\n 63%|██████▎   | 32/51 [00:08<00:04,  3.85it/s]\n 65%|██████▍   | 33/51 [00:08<00:04,  3.85it/s]\n 67%|██████▋   | 34/51 [00:08<00:04,  3.84it/s]\n 69%|██████▊   | 35/51 [00:09<00:04,  3.84it/s]\n 71%|███████   | 36/51 [00:09<00:03,  3.84it/s]\n 73%|███████▎  | 37/51 [00:09<00:03,  3.84it/s]\n 75%|███████▍  | 38/51 [00:09<00:03,  3.84it/s]\n 76%|███████▋  | 39/51 [00:10<00:03,  3.84it/s]\n 78%|███████▊  | 40/51 [00:10<00:02,  3.85it/s]\n 80%|████████  | 41/51 [00:10<00:02,  3.83it/s]\n 82%|████████▏ | 42/51 [00:10<00:02,  3.83it/s]\n 84%|████████▍ | 43/51 [00:11<00:02,  3.82it/s]\n 86%|████████▋ | 44/51 [00:11<00:01,  3.83it/s]\n 88%|████████▊ | 45/51 [00:11<00:01,  3.83it/s]\n 90%|█████████ | 46/51 [00:12<00:01,  3.83it/s]\n 92%|█████████▏| 47/51 [00:12<00:01,  3.83it/s]\n 94%|█████████▍| 48/51 [00:12<00:00,  3.84it/s]\n 96%|█████████▌| 49/51 [00:12<00:00,  3.83it/s]\n 98%|█████████▊| 50/51 [00:13<00:00,  3.83it/s]\n100%|██████████| 51/51 [00:13<00:00,  3.82it/s]\n100%|██████████| 51/51 [00:13<00:00,  3.83it/s]",
  "metrics": {
    "predict_time": 13.802485,
    "total_time": 13.840879
  },
  "output": [
    "https://replicate.delivery/pbxt/gVidGfayGfulGkTWWSGCCpQuA0sjkycleounGgfEoGQQr93fB/out-0.png"
  ],
  "started_at": "2022-11-08T11:59:34.593754Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/em3v3lrdtbednmu66bwyvhb4su",
    "cancel": "https://api.replicate.com/v1/predictions/em3v3lrdtbednmu66bwyvhb4su/cancel"
  },
  "version": "2d43b996608bd7d4aba4cacbe9b751399892a9d6cbc27a39f8f49347a3a16f9c"
}

Generated in

13.8 seconds

Tweak itReport

Using seed: 53092
Global seed set to 53092

  0%|          | 0/51 [00:00<?, ?it/s]
  2%|▏         | 1/51 [00:00<00:16,  3.02it/s]
  4%|▍         | 2/51 [00:00<00:14,  3.48it/s]
  6%|▌         | 3/51 [00:00<00:13,  3.65it/s]
  8%|▊         | 4/51 [00:01<00:12,  3.75it/s]
 10%|▉         | 5/51 [00:01<00:12,  3.77it/s]
 12%|█▏        | 6/51 [00:01<00:11,  3.80it/s]
 14%|█▎        | 7/51 [00:01<00:11,  3.82it/s]
 16%|█▌        | 8/51 [00:02<00:11,  3.84it/s]
 18%|█▊        | 9/51 [00:02<00:10,  3.84it/s]
 20%|█▉        | 10/51 [00:02<00:10,  3.85it/s]
 22%|██▏       | 11/51 [00:02<00:10,  3.85it/s]
 24%|██▎       | 12/51 [00:03<00:10,  3.85it/s]
 25%|██▌       | 13/51 [00:03<00:09,  3.85it/s]
 27%|██▋       | 14/51 [00:03<00:09,  3.85it/s]
 29%|██▉       | 15/51 [00:03<00:09,  3.85it/s]
 31%|███▏      | 16/51 [00:04<00:09,  3.86it/s]
 33%|███▎      | 17/51 [00:04<00:08,  3.85it/s]
 35%|███▌      | 18/51 [00:04<00:08,  3.85it/s]
 37%|███▋      | 19/51 [00:04<00:08,  3.85it/s]
 39%|███▉      | 20/51 [00:05<00:08,  3.85it/s]
 41%|████      | 21/51 [00:05<00:07,  3.86it/s]
 43%|████▎     | 22/51 [00:05<00:07,  3.85it/s]
 45%|████▌     | 23/51 [00:06<00:07,  3.85it/s]
 47%|████▋     | 24/51 [00:06<00:07,  3.85it/s]
 49%|████▉     | 25/51 [00:06<00:06,  3.85it/s]
 51%|█████     | 26/51 [00:06<00:06,  3.86it/s]
 53%|█████▎    | 27/51 [00:07<00:06,  3.85it/s]
 55%|█████▍    | 28/51 [00:07<00:05,  3.85it/s]
 57%|█████▋    | 29/51 [00:07<00:05,  3.84it/s]
 59%|█████▉    | 30/51 [00:07<00:05,  3.84it/s]
 61%|██████    | 31/51 [00:08<00:05,  3.85it/s]
 63%|██████▎   | 32/51 [00:08<00:04,  3.85it/s]
 65%|██████▍   | 33/51 [00:08<00:04,  3.85it/s]
 67%|██████▋   | 34/51 [00:08<00:04,  3.84it/s]
 69%|██████▊   | 35/51 [00:09<00:04,  3.84it/s]
 71%|███████   | 36/51 [00:09<00:03,  3.84it/s]
 73%|███████▎  | 37/51 [00:09<00:03,  3.84it/s]
 75%|███████▍  | 38/51 [00:09<00:03,  3.84it/s]
 76%|███████▋  | 39/51 [00:10<00:03,  3.84it/s]
 78%|███████▊  | 40/51 [00:10<00:02,  3.85it/s]
 80%|████████  | 41/51 [00:10<00:02,  3.83it/s]
 82%|████████▏ | 42/51 [00:10<00:02,  3.83it/s]
 84%|████████▍ | 43/51 [00:11<00:02,  3.82it/s]
 86%|████████▋ | 44/51 [00:11<00:01,  3.83it/s]
 88%|████████▊ | 45/51 [00:11<00:01,  3.83it/s]
 90%|█████████ | 46/51 [00:12<00:01,  3.83it/s]
 92%|█████████▏| 47/51 [00:12<00:01,  3.83it/s]
 94%|█████████▍| 48/51 [00:12<00:00,  3.84it/s]
 96%|█████████▌| 49/51 [00:12<00:00,  3.83it/s]
 98%|█████████▊| 50/51 [00:13<00:00,  3.83it/s]
100%|██████████| 51/51 [00:13<00:00,  3.82it/s]
100%|██████████| 51/51 [00:13<00:00,  3.83it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.046 to run on Replicate, or 21 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 4 minutes. The predict time for this model varies significantly based on the inputs.

Readme

Model weights: https://huggingface.co/dallinmackay/Van-Gogh-diffusion

Van Gogh Diffusion

This is a fine-tuned Stable Diffusion model (based on v1.5) trained on screenshots from the film Loving Vincent. Use the token lvngvncnt at the BEGINNING of your prompts to use the style (e.g., “lvngvncnt, beautiful woman at sunset”)

Characters rendered with this model: Character Samples prompt and settings used: lvngvncnt, [person], highly detailed | Steps: 25, Sampler: Euler, CFG scale: 6

Landscapes/miscellaneous rendered with this model: Landscape Samples prompt and settings used: lvngvncnt, [subject/setting], highly detailed | Steps: 25, Sampler: Euler, CFG scale: 6