nitrosocke/redshift-diffusion – Run with an API on Replicate

nitrosocke / redshift-diffusion

3D artworks on Stable Diffusion via Dreambooth

Cold

Public
35.9K runs
T4

Iterate in 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=nitrosocke/redshift-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 nitrosocke/redshift-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "nitrosocke/redshift-diffusion:b78a34f0ec6d21d22ae3b10afd52b219cec65f63362e69e81e4dce07a8154ef8",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "redshift style magical princess with golden hair",
      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 nitrosocke/redshift-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "nitrosocke/redshift-diffusion:b78a34f0ec6d21d22ae3b10afd52b219cec65f63362e69e81e4dce07a8154ef8",
    input={
        "width": 512,
        "height": 512,
        "prompt": "redshift style magical princess with golden hair",
        "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 nitrosocke/redshift-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": "nitrosocke/redshift-diffusion:b78a34f0ec6d21d22ae3b10afd52b219cec65f63362e69e81e4dce07a8154ef8",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "redshift style magical princess with golden hair",
      "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": "2022-11-08T12:47:52.820303Z",
  "created_at": "2022-11-08T12:47:37.829234Z",
  "data_removed": false,
  "error": null,
  "id": "nwws45ze4fhz5dfrklpxdm6mbm",
  "input": {
    "width": 512,
    "height": 512,
    "prompt": "redshift style magical princess with golden hair",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 46158\nGlobal seed set to 46158\n\n  0%|          | 0/51 [00:00<?, ?it/s]\n  2%|▏         | 1/51 [00:00<00:16,  2.98it/s]\n  4%|▍         | 2/51 [00:00<00:14,  3.36it/s]\n  6%|▌         | 3/51 [00:00<00:13,  3.47it/s]\n  8%|▊         | 4/51 [00:01<00:13,  3.51it/s]\n 10%|▉         | 5/51 [00:01<00:13,  3.54it/s]\n 12%|█▏        | 6/51 [00:01<00:12,  3.56it/s]\n 14%|█▎        | 7/51 [00:01<00:12,  3.58it/s]\n 16%|█▌        | 8/51 [00:02<00:12,  3.58it/s]\n 18%|█▊        | 9/51 [00:02<00:11,  3.57it/s]\n 20%|█▉        | 10/51 [00:02<00:11,  3.58it/s]\n 22%|██▏       | 11/51 [00:03<00:11,  3.59it/s]\n 24%|██▎       | 12/51 [00:03<00:10,  3.57it/s]\n 25%|██▌       | 13/51 [00:03<00:10,  3.58it/s]\n 27%|██▋       | 14/51 [00:03<00:10,  3.58it/s]\n 29%|██▉       | 15/51 [00:04<00:10,  3.58it/s]\n 31%|███▏      | 16/51 [00:04<00:09,  3.56it/s]\n 33%|███▎      | 17/51 [00:04<00:09,  3.57it/s]\n 35%|███▌      | 18/51 [00:05<00:09,  3.58it/s]\n 37%|███▋      | 19/51 [00:05<00:08,  3.57it/s]\n 39%|███▉      | 20/51 [00:05<00:08,  3.57it/s]\n 41%|████      | 21/51 [00:05<00:08,  3.56it/s]\n 43%|████▎     | 22/51 [00:06<00:08,  3.56it/s]\n 45%|████▌     | 23/51 [00:06<00:07,  3.56it/s]\n 47%|████▋     | 24/51 [00:06<00:07,  3.57it/s]\n 49%|████▉     | 25/51 [00:07<00:07,  3.56it/s]\n 51%|█████     | 26/51 [00:07<00:07,  3.56it/s]\n 53%|█████▎    | 27/51 [00:07<00:06,  3.56it/s]\n 55%|█████▍    | 28/51 [00:07<00:06,  3.56it/s]\n 57%|█████▋    | 29/51 [00:08<00:06,  3.57it/s]\n 59%|█████▉    | 30/51 [00:08<00:05,  3.56it/s]\n 61%|██████    | 31/51 [00:08<00:05,  3.56it/s]\n 63%|██████▎   | 32/51 [00:09<00:05,  3.56it/s]\n 65%|██████▍   | 33/51 [00:09<00:05,  3.55it/s]\n 67%|██████▋   | 34/51 [00:09<00:04,  3.55it/s]\n 69%|██████▊   | 35/51 [00:09<00:04,  3.55it/s]\n 71%|███████   | 36/51 [00:10<00:04,  3.55it/s]\n 73%|███████▎  | 37/51 [00:10<00:03,  3.55it/s]\n 75%|███████▍  | 38/51 [00:10<00:03,  3.54it/s]\n 76%|███████▋  | 39/51 [00:10<00:03,  3.54it/s]\n 78%|███████▊  | 40/51 [00:11<00:03,  3.54it/s]\n 80%|████████  | 41/51 [00:11<00:02,  3.54it/s]\n 82%|████████▏ | 42/51 [00:11<00:02,  3.53it/s]\n 84%|████████▍ | 43/51 [00:12<00:02,  3.53it/s]\n 86%|████████▋ | 44/51 [00:12<00:01,  3.53it/s]\n 88%|████████▊ | 45/51 [00:12<00:01,  3.53it/s]\n 90%|█████████ | 46/51 [00:12<00:01,  3.53it/s]\n 92%|█████████▏| 47/51 [00:13<00:01,  3.53it/s]\n 94%|█████████▍| 48/51 [00:13<00:00,  3.52it/s]\n 96%|█████████▌| 49/51 [00:13<00:00,  3.53it/s]\n 98%|█████████▊| 50/51 [00:14<00:00,  3.52it/s]\n100%|██████████| 51/51 [00:14<00:00,  3.53it/s]\n100%|██████████| 51/51 [00:14<00:00,  3.55it/s]",
  "metrics": {
    "predict_time": 14.957052,
    "total_time": 14.991069
  },
  "output": [
    "https://replicate.delivery/pbxt/ezdgqSe7QZlsLEDZMzGZ4RERf6SRR981TvxnyQLewh9jfAwfD/out-0.png"
  ],
  "started_at": "2022-11-08T12:47:37.863251Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/nwws45ze4fhz5dfrklpxdm6mbm",
    "cancel": "https://api.replicate.com/v1/predictions/nwws45ze4fhz5dfrklpxdm6mbm/cancel"
  },
  "version": "b78a34f0ec6d21d22ae3b10afd52b219cec65f63362e69e81e4dce07a8154ef8"
}

Generated in

15.0 seconds

Tweak itReport

Using seed: 46158
Global seed set to 46158

  0%|          | 0/51 [00:00<?, ?it/s]
  2%|▏         | 1/51 [00:00<00:16,  2.98it/s]
  4%|▍         | 2/51 [00:00<00:14,  3.36it/s]
  6%|▌         | 3/51 [00:00<00:13,  3.47it/s]
  8%|▊         | 4/51 [00:01<00:13,  3.51it/s]
 10%|▉         | 5/51 [00:01<00:13,  3.54it/s]
 12%|█▏        | 6/51 [00:01<00:12,  3.56it/s]
 14%|█▎        | 7/51 [00:01<00:12,  3.58it/s]
 16%|█▌        | 8/51 [00:02<00:12,  3.58it/s]
 18%|█▊        | 9/51 [00:02<00:11,  3.57it/s]
 20%|█▉        | 10/51 [00:02<00:11,  3.58it/s]
 22%|██▏       | 11/51 [00:03<00:11,  3.59it/s]
 24%|██▎       | 12/51 [00:03<00:10,  3.57it/s]
 25%|██▌       | 13/51 [00:03<00:10,  3.58it/s]
 27%|██▋       | 14/51 [00:03<00:10,  3.58it/s]
 29%|██▉       | 15/51 [00:04<00:10,  3.58it/s]
 31%|███▏      | 16/51 [00:04<00:09,  3.56it/s]
 33%|███▎      | 17/51 [00:04<00:09,  3.57it/s]
 35%|███▌      | 18/51 [00:05<00:09,  3.58it/s]
 37%|███▋      | 19/51 [00:05<00:08,  3.57it/s]
 39%|███▉      | 20/51 [00:05<00:08,  3.57it/s]
 41%|████      | 21/51 [00:05<00:08,  3.56it/s]
 43%|████▎     | 22/51 [00:06<00:08,  3.56it/s]
 45%|████▌     | 23/51 [00:06<00:07,  3.56it/s]
 47%|████▋     | 24/51 [00:06<00:07,  3.57it/s]
 49%|████▉     | 25/51 [00:07<00:07,  3.56it/s]
 51%|█████     | 26/51 [00:07<00:07,  3.56it/s]
 53%|█████▎    | 27/51 [00:07<00:06,  3.56it/s]
 55%|█████▍    | 28/51 [00:07<00:06,  3.56it/s]
 57%|█████▋    | 29/51 [00:08<00:06,  3.57it/s]
 59%|█████▉    | 30/51 [00:08<00:05,  3.56it/s]
 61%|██████    | 31/51 [00:08<00:05,  3.56it/s]
 63%|██████▎   | 32/51 [00:09<00:05,  3.56it/s]
 65%|██████▍   | 33/51 [00:09<00:05,  3.55it/s]
 67%|██████▋   | 34/51 [00:09<00:04,  3.55it/s]
 69%|██████▊   | 35/51 [00:09<00:04,  3.55it/s]
 71%|███████   | 36/51 [00:10<00:04,  3.55it/s]
 73%|███████▎  | 37/51 [00:10<00:03,  3.55it/s]
 75%|███████▍  | 38/51 [00:10<00:03,  3.54it/s]
 76%|███████▋  | 39/51 [00:10<00:03,  3.54it/s]
 78%|███████▊  | 40/51 [00:11<00:03,  3.54it/s]
 80%|████████  | 41/51 [00:11<00:02,  3.54it/s]
 82%|████████▏ | 42/51 [00:11<00:02,  3.53it/s]
 84%|████████▍ | 43/51 [00:12<00:02,  3.53it/s]
 86%|████████▋ | 44/51 [00:12<00:01,  3.53it/s]
 88%|████████▊ | 45/51 [00:12<00:01,  3.53it/s]
 90%|█████████ | 46/51 [00:12<00:01,  3.53it/s]
 92%|█████████▏| 47/51 [00:13<00:01,  3.53it/s]
 94%|█████████▍| 48/51 [00:13<00:00,  3.52it/s]
 96%|█████████▌| 49/51 [00:13<00:00,  3.53it/s]
 98%|█████████▊| 50/51 [00:14<00:00,  3.52it/s]
100%|██████████| 51/51 [00:14<00:00,  3.53it/s]
100%|██████████| 51/51 [00:14<00:00,  3.55it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.050 to run on Replicate, or 20 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/nitrosocke/redshift-diffusion

Redshift Diffusion

This is the fine-tuned Stable Diffusion model trained on high resolution 3D artworks. Use the tokens redshift style in your prompts for the effect.

Characters rendered with the model: Videogame Samples Cars and Landscapes rendered with the model: Misc. Samples