nitrosocke/classic-anim-diffusion – Run with an API on Replicate

nitrosocke / classic-anim-diffusion

Animation Studio on Stable Diffusion via Dreambooth

Cold

Public
4.4K runs
T4

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

classic disney style magical princess with golden hairclassic disney style magical princess with golden hair

Input prompt

Default: "classic disney style magical princess with golden hair"

width

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

height

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

num_outputs

integer

Number of images to output

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

seed

integer

Random seed. Leave blank to randomize the seed

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

npx create-replicate --model=nitrosocke/classic-anim-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/classic-anim-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "nitrosocke/classic-anim-diffusion:fee3cbc40c374790857553c13c55582985835af6efa4d4655c0e3ddfe3c7cc9d",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "classic disney 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/classic-anim-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "nitrosocke/classic-anim-diffusion:fee3cbc40c374790857553c13c55582985835af6efa4d4655c0e3ddfe3c7cc9d",
    input={
        "width": 512,
        "height": 512,
        "prompt": "classic disney 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/classic-anim-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/classic-anim-diffusion:fee3cbc40c374790857553c13c55582985835af6efa4d4655c0e3ddfe3c7cc9d",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "classic disney 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": "2022-11-08T13:41:28.219157Z",
  "created_at": "2022-11-08T13:38:30.413830Z",
  "data_removed": false,
  "error": null,
  "id": "tpojtov5pfckzfk6qoxhe7lgfm",
  "input": {
    "width": 512,
    "height": 512,
    "prompt": "classic disney style magical princess with golden hair",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 58549\nGlobal seed set to 58549\n\n  0%|          | 0/51 [00:00<?, ?it/s]\n  2%|▏         | 1/51 [00:04<03:42,  4.46s/it]\n  4%|▍         | 2/51 [00:04<01:37,  1.98s/it]\n  6%|▌         | 3/51 [00:04<00:57,  1.19s/it]\n  8%|▊         | 4/51 [00:05<00:38,  1.22it/s]\n 10%|▉         | 5/51 [00:05<00:28,  1.62it/s]\n 12%|█▏        | 6/51 [00:05<00:22,  2.03it/s]\n 14%|█▎        | 7/51 [00:05<00:18,  2.41it/s]\n 16%|█▌        | 8/51 [00:06<00:15,  2.75it/s]\n 18%|█▊        | 9/51 [00:06<00:13,  3.04it/s]\n 20%|█▉        | 10/51 [00:06<00:12,  3.27it/s]\n 22%|██▏       | 11/51 [00:06<00:11,  3.44it/s]\n 24%|██▎       | 12/51 [00:07<00:10,  3.59it/s]\n 25%|██▌       | 13/51 [00:07<00:10,  3.68it/s]\n 27%|██▋       | 14/51 [00:07<00:09,  3.76it/s]\n 29%|██▉       | 15/51 [00:08<00:09,  3.81it/s]\n 31%|███▏      | 16/51 [00:08<00:09,  3.87it/s]\n 33%|███▎      | 17/51 [00:08<00:08,  3.89it/s]\n 35%|███▌      | 18/51 [00:08<00:08,  3.90it/s]\n 37%|███▋      | 19/51 [00:09<00:08,  3.91it/s]\n 39%|███▉      | 20/51 [00:09<00:07,  3.93it/s]\n 41%|████      | 21/51 [00:09<00:07,  3.93it/s]\n 43%|████▎     | 22/51 [00:09<00:07,  3.92it/s]\n 45%|████▌     | 23/51 [00:10<00:07,  3.92it/s]\n 47%|████▋     | 24/51 [00:10<00:06,  3.93it/s]\n 49%|████▉     | 25/51 [00:10<00:06,  3.93it/s]\n 51%|█████     | 26/51 [00:10<00:06,  3.93it/s]\n 53%|█████▎    | 27/51 [00:11<00:06,  3.94it/s]\n 55%|█████▍    | 28/51 [00:11<00:05,  3.95it/s]\n 57%|█████▋    | 29/51 [00:11<00:05,  3.95it/s]\n 59%|█████▉    | 30/51 [00:11<00:05,  3.95it/s]\n 61%|██████    | 31/51 [00:12<00:05,  3.94it/s]\n 63%|██████▎   | 32/51 [00:12<00:04,  3.94it/s]\n 65%|██████▍   | 33/51 [00:12<00:04,  3.94it/s]\n 67%|██████▋   | 34/51 [00:12<00:04,  3.94it/s]\n 69%|██████▊   | 35/51 [00:13<00:04,  3.92it/s]\n 71%|███████   | 36/51 [00:13<00:03,  3.93it/s]\n 73%|███████▎  | 37/51 [00:13<00:03,  3.93it/s]\n 75%|███████▍  | 38/51 [00:13<00:03,  3.93it/s]\n 76%|███████▋  | 39/51 [00:14<00:03,  3.93it/s]\n 78%|███████▊  | 40/51 [00:14<00:02,  3.92it/s]\n 80%|████████  | 41/51 [00:14<00:02,  3.92it/s]\n 82%|████████▏ | 42/51 [00:14<00:02,  3.92it/s]\n 84%|████████▍ | 43/51 [00:15<00:02,  3.93it/s]\n 86%|████████▋ | 44/51 [00:15<00:01,  3.92it/s]\n 88%|████████▊ | 45/51 [00:15<00:01,  3.92it/s]\n 90%|█████████ | 46/51 [00:15<00:01,  3.91it/s]\n 92%|█████████▏| 47/51 [00:16<00:01,  3.92it/s]\n 94%|█████████▍| 48/51 [00:16<00:00,  3.92it/s]\n 96%|█████████▌| 49/51 [00:16<00:00,  3.91it/s]\n 98%|█████████▊| 50/51 [00:16<00:00,  3.90it/s]\n100%|██████████| 51/51 [00:17<00:00,  3.91it/s]\n100%|██████████| 51/51 [00:17<00:00,  2.97it/s]",
  "metrics": {
    "predict_time": 21.387373,
    "total_time": 177.805327
  },
  "output": [
    "https://replicate.delivery/pbxt/2gTh9Htp2Ko1CRHuYs5R7gP3ongWA0eyL7qCLQIp9HAEdAfPA/out-0.png"
  ],
  "started_at": "2022-11-08T13:41:06.831784Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/tpojtov5pfckzfk6qoxhe7lgfm",
    "cancel": "https://api.replicate.com/v1/predictions/tpojtov5pfckzfk6qoxhe7lgfm/cancel"
  },
  "version": "fee3cbc40c374790857553c13c55582985835af6efa4d4655c0e3ddfe3c7cc9d"
}

Generated in

21.4 seconds

Tweak itReport

Using seed: 58549
Global seed set to 58549

  0%|          | 0/51 [00:00<?, ?it/s]
  2%|▏         | 1/51 [00:04<03:42,  4.46s/it]
  4%|▍         | 2/51 [00:04<01:37,  1.98s/it]
  6%|▌         | 3/51 [00:04<00:57,  1.19s/it]
  8%|▊         | 4/51 [00:05<00:38,  1.22it/s]
 10%|▉         | 5/51 [00:05<00:28,  1.62it/s]
 12%|█▏        | 6/51 [00:05<00:22,  2.03it/s]
 14%|█▎        | 7/51 [00:05<00:18,  2.41it/s]
 16%|█▌        | 8/51 [00:06<00:15,  2.75it/s]
 18%|█▊        | 9/51 [00:06<00:13,  3.04it/s]
 20%|█▉        | 10/51 [00:06<00:12,  3.27it/s]
 22%|██▏       | 11/51 [00:06<00:11,  3.44it/s]
 24%|██▎       | 12/51 [00:07<00:10,  3.59it/s]
 25%|██▌       | 13/51 [00:07<00:10,  3.68it/s]
 27%|██▋       | 14/51 [00:07<00:09,  3.76it/s]
 29%|██▉       | 15/51 [00:08<00:09,  3.81it/s]
 31%|███▏      | 16/51 [00:08<00:09,  3.87it/s]
 33%|███▎      | 17/51 [00:08<00:08,  3.89it/s]
 35%|███▌      | 18/51 [00:08<00:08,  3.90it/s]
 37%|███▋      | 19/51 [00:09<00:08,  3.91it/s]
 39%|███▉      | 20/51 [00:09<00:07,  3.93it/s]
 41%|████      | 21/51 [00:09<00:07,  3.93it/s]
 43%|████▎     | 22/51 [00:09<00:07,  3.92it/s]
 45%|████▌     | 23/51 [00:10<00:07,  3.92it/s]
 47%|████▋     | 24/51 [00:10<00:06,  3.93it/s]
 49%|████▉     | 25/51 [00:10<00:06,  3.93it/s]
 51%|█████     | 26/51 [00:10<00:06,  3.93it/s]
 53%|█████▎    | 27/51 [00:11<00:06,  3.94it/s]
 55%|█████▍    | 28/51 [00:11<00:05,  3.95it/s]
 57%|█████▋    | 29/51 [00:11<00:05,  3.95it/s]
 59%|█████▉    | 30/51 [00:11<00:05,  3.95it/s]
 61%|██████    | 31/51 [00:12<00:05,  3.94it/s]
 63%|██████▎   | 32/51 [00:12<00:04,  3.94it/s]
 65%|██████▍   | 33/51 [00:12<00:04,  3.94it/s]
 67%|██████▋   | 34/51 [00:12<00:04,  3.94it/s]
 69%|██████▊   | 35/51 [00:13<00:04,  3.92it/s]
 71%|███████   | 36/51 [00:13<00:03,  3.93it/s]
 73%|███████▎  | 37/51 [00:13<00:03,  3.93it/s]
 75%|███████▍  | 38/51 [00:13<00:03,  3.93it/s]
 76%|███████▋  | 39/51 [00:14<00:03,  3.93it/s]
 78%|███████▊  | 40/51 [00:14<00:02,  3.92it/s]
 80%|████████  | 41/51 [00:14<00:02,  3.92it/s]
 82%|████████▏ | 42/51 [00:14<00:02,  3.92it/s]
 84%|████████▍ | 43/51 [00:15<00:02,  3.93it/s]
 86%|████████▋ | 44/51 [00:15<00:01,  3.92it/s]
 88%|████████▊ | 45/51 [00:15<00:01,  3.92it/s]
 90%|█████████ | 46/51 [00:15<00:01,  3.91it/s]
 92%|█████████▏| 47/51 [00:16<00:01,  3.92it/s]
 94%|█████████▍| 48/51 [00:16<00:00,  3.92it/s]
 96%|█████████▌| 49/51 [00:16<00:00,  3.91it/s]
 98%|█████████▊| 50/51 [00:16<00:00,  3.90it/s]
100%|██████████| 51/51 [00:17<00:00,  3.91it/s]
100%|██████████| 51/51 [00:17<00:00,  2.97it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.012 to run on Replicate, or 83 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 56 seconds. The predict time for this model varies significantly based on the inputs.

Readme

weights: https://huggingface.co/nitrosocke/classic-anim-diffusion

Classic Animation Diffusion

This is the fine-tuned Stable Diffusion model trained on screenshots from a popular animation studio. Use the tokens classic disney style in your prompts for the effect.

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