deutschla/character-generator – Run with an API on Replicate

deutschla / character-generator

Replicate model that creates a creature from a sketch.

Cold

Public
4K runs
T4

Run with an API

Playground API Examples README Versions

Input

image

file

Input image

Default: "@test-scribble.png"

prompt

string

Shift + Return to add a new line

a duck head, dinosaur leg, tiger claw, bird leg, tentacle arm, dragon bodya duck head, dinosaur leg, tiger claw, bird leg, tentacle arm, dragon body

Prompt to guide the image generation

Default: "duck head, insect wing, crab claw, bird leg, tentacle leg, dragon body"

negative_prompt

string

Shift + Return to add a new line

The prompt or prompts not to guide the image generation (what you do not want to see in the generation). Ignored when not using guidance.

Default: ""

additional_prompt

string

Shift + Return to add a new line

childrens illustration, fantasy creature, solo, single creature, white-backgroundchildrens illustration, fantasy creature, solo, single creature, white-background

Additional prompts to guide the image generation. Ignored when not using guidance.

Default: "childrens illustration, fantasy creature, solo, single creature, white-background, masterpiece"

additional_negative_prompt

string

Shift + Return to add a new line

(worst quality, low quality:1.4), shadow, mouth, multiple eyes, signature, watermark, nsfw, plants, human, man, woman, animal, child, boy, girl(worst quality, low quality:1.4), shadow, mouth, multiple eyes, signature, watermark, nsfw, plants, human, man, woman, animal, child, boy, girl

The prompt or prompts not to guide the image generation (what you do not want to see in the generation). Ignored when not using guidance.

Default: "worst quality, low quality, shadow, mouth, multiple eyes, signature, watermark, nsfw, plants, human, man, woman, animal, child, boy, girl"

num_inference_steps

integer

(minimum: 1, maximum: 500)

The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.

Default: 50

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance. Higher guidance scale encourages to generate images that are closely linked to the text prompt, usually at the expense of lower image quality.

Default: 7.5

seed

integer

Random seed. Leave blank to randomize the seed

invert_colors

boolean

Invert the colors of the control image. Use this for scribbles with black strokes on a white background.

Default: true

remove_background

boolean

Remove the background of the final output image.

Default: true

upscale_image

boolean

Upscales the final output image 4x using ESRGAN. Final size will be 2048x2048

Default: true

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

npx create-replicate --model=deutschla/character-generator

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 deutschla/character-generator using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "deutschla/character-generator:602288aab4a00324ecd0a26fd1d360f70823e4e90a55e72c06b34f460b97a274",
  {
    input: {
      image: "https://replicate.delivery/pbxt/J8duw7Y8vqazMA0ujMPM9j2Tht8YiAH7VZFlIR2wZpUbDfXB/test-scribble.png",
      prompt: "a duck head, dinosaur leg, tiger claw, bird leg, tentacle arm, dragon body",
      invert_colors: true,
      upscale_image: true,
      guidance_scale: 8,
      negative_prompt: "",
      additional_prompt: "childrens illustration, fantasy creature, solo, single creature, white-background",
      remove_background: true,
      num_inference_steps: 50,
      additional_negative_prompt: "(worst quality, low quality:1.4), shadow, mouth, multiple eyes, signature, watermark, nsfw, plants, human, man, woman, animal, child, boy, girl"
    }
  }
);
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 deutschla/character-generator using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "deutschla/character-generator:602288aab4a00324ecd0a26fd1d360f70823e4e90a55e72c06b34f460b97a274",
    input={
        "image": "https://replicate.delivery/pbxt/J8duw7Y8vqazMA0ujMPM9j2Tht8YiAH7VZFlIR2wZpUbDfXB/test-scribble.png",
        "prompt": "a duck head, dinosaur leg, tiger claw, bird leg, tentacle arm, dragon body",
        "invert_colors": True,
        "upscale_image": True,
        "guidance_scale": 8,
        "negative_prompt": "",
        "additional_prompt": "childrens illustration, fantasy creature, solo, single creature, white-background",
        "remove_background": True,
        "num_inference_steps": 50,
        "additional_negative_prompt": "(worst quality, low quality:1.4), shadow, mouth, multiple eyes, signature, watermark, nsfw, plants, human, man, woman, animal, child, boy, girl"
    }
)
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 deutschla/character-generator 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": "602288aab4a00324ecd0a26fd1d360f70823e4e90a55e72c06b34f460b97a274",
    "input": {
      "image": "https://replicate.delivery/pbxt/J8duw7Y8vqazMA0ujMPM9j2Tht8YiAH7VZFlIR2wZpUbDfXB/test-scribble.png",
      "prompt": "a duck head, dinosaur leg, tiger claw, bird leg, tentacle arm, dragon body",
      "invert_colors": true,
      "upscale_image": true,
      "guidance_scale": 8,
      "negative_prompt": "",
      "additional_prompt": "childrens illustration, fantasy creature, solo, single creature, white-background",
      "remove_background": true,
      "num_inference_steps": 50,
      "additional_negative_prompt": "(worst quality, low quality:1.4), shadow, mouth, multiple eyes, signature, watermark, nsfw, plants, human, man, woman, animal, child, boy, girl"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-07-21T19:36:01.580403Z",
  "created_at": "2023-07-21T19:35:38.076343Z",
  "data_removed": false,
  "error": null,
  "id": "oha4smzbp5eif5skog5o5xnhry",
  "input": {
    "image": "https://replicate.delivery/pbxt/J8duw7Y8vqazMA0ujMPM9j2Tht8YiAH7VZFlIR2wZpUbDfXB/test-scribble.png",
    "prompt": "a duck head, dinosaur leg, tiger claw, bird leg, tentacle arm, dragon body",
    "invert_colors": true,
    "upscale_image": true,
    "guidance_scale": 8,
    "additional_prompt": "childrens illustration, fantasy creature, solo, single creature, white-background",
    "remove_background": true,
    "num_inference_steps": 50,
    "additional_negative_prompt": "(worst quality, low quality:1.4), shadow, mouth, multiple eyes, signature, watermark, nsfw, plants, human, man, woman, animal, child, boy, girl"
  },
  "logs": "Using seed: 37878\nInverting colors of control image\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:01<01:07,  1.37s/it]\n  4%|▍         | 2/50 [00:01<00:33,  1.44it/s]\n  6%|▌         | 3/50 [00:01<00:22,  2.08it/s]\n  8%|▊         | 4/50 [00:02<00:17,  2.66it/s]\n 10%|█         | 5/50 [00:02<00:14,  3.13it/s]\n 12%|█▏        | 6/50 [00:02<00:12,  3.50it/s]\n 14%|█▍        | 7/50 [00:02<00:11,  3.78it/s]\n 16%|█▌        | 8/50 [00:02<00:10,  3.98it/s]\n 18%|█▊        | 9/50 [00:03<00:09,  4.13it/s]\n 20%|██        | 10/50 [00:03<00:09,  4.28it/s]\n 22%|██▏       | 11/50 [00:03<00:08,  4.37it/s]\n 24%|██▍       | 12/50 [00:03<00:08,  4.43it/s]\n 26%|██▌       | 13/50 [00:04<00:08,  4.40it/s]\n 28%|██▊       | 14/50 [00:04<00:08,  4.46it/s]\n 30%|███       | 15/50 [00:04<00:07,  4.48it/s]\n 32%|███▏      | 16/50 [00:04<00:07,  4.50it/s]\n 34%|███▍      | 17/50 [00:04<00:07,  4.49it/s]\n 36%|███▌      | 18/50 [00:05<00:07,  4.50it/s]\n 38%|███▊      | 19/50 [00:05<00:06,  4.49it/s]\n 40%|████      | 20/50 [00:05<00:06,  4.49it/s]\n 42%|████▏     | 21/50 [00:05<00:06,  4.46it/s]\n 44%|████▍     | 22/50 [00:06<00:06,  4.44it/s]\n 46%|████▌     | 23/50 [00:06<00:06,  4.49it/s]\n 48%|████▊     | 24/50 [00:06<00:05,  4.51it/s]\n 50%|█████     | 25/50 [00:06<00:05,  4.50it/s]\n 52%|█████▏    | 26/50 [00:06<00:05,  4.48it/s]\n 54%|█████▍    | 27/50 [00:07<00:05,  4.52it/s]\n 56%|█████▌    | 28/50 [00:07<00:04,  4.51it/s]\n 58%|█████▊    | 29/50 [00:07<00:04,  4.50it/s]\n 60%|██████    | 30/50 [00:07<00:04,  4.48it/s]\n 62%|██████▏   | 31/50 [00:08<00:04,  4.49it/s]\n 64%|██████▍   | 32/50 [00:08<00:03,  4.51it/s]\n 66%|██████▌   | 33/50 [00:08<00:03,  4.50it/s]\n 68%|██████▊   | 34/50 [00:08<00:03,  4.50it/s]\n 70%|███████   | 35/50 [00:08<00:03,  4.48it/s]\n 72%|███████▏  | 36/50 [00:09<00:03,  4.49it/s]\n 74%|███████▍  | 37/50 [00:09<00:02,  4.50it/s]\n 76%|███████▌  | 38/50 [00:09<00:02,  4.47it/s]\n 78%|███████▊  | 39/50 [00:09<00:02,  4.48it/s]\n 80%|████████  | 40/50 [00:10<00:02,  4.47it/s]\n 82%|████████▏ | 41/50 [00:10<00:02,  4.47it/s]\n 84%|████████▍ | 42/50 [00:10<00:01,  4.46it/s]\n 86%|████████▌ | 43/50 [00:10<00:01,  4.48it/s]\n 88%|████████▊ | 44/50 [00:10<00:01,  4.48it/s]\n 90%|█████████ | 45/50 [00:11<00:01,  4.48it/s]\n 92%|█████████▏| 46/50 [00:11<00:00,  4.49it/s]\n 94%|█████████▍| 47/50 [00:11<00:00,  4.49it/s]\n 96%|█████████▌| 48/50 [00:11<00:00,  4.49it/s]\n 98%|█████████▊| 49/50 [00:12<00:00,  4.47it/s]\n100%|██████████| 50/50 [00:12<00:00,  4.50it/s]\n100%|██████████| 50/50 [00:12<00:00,  4.08it/s]",
  "metrics": {
    "predict_time": 23.519298,
    "total_time": 23.50406
  },
  "output": [
    "https://replicate.delivery/pbxt/pemIvCVUqYwZOyvd56FpQuR7S1HanFkV9DH4UC8KuYcQgEpIA/0-37878-remb.png"
  ],
  "started_at": "2023-07-21T19:35:38.061105Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/oha4smzbp5eif5skog5o5xnhry",
    "cancel": "https://api.replicate.com/v1/predictions/oha4smzbp5eif5skog5o5xnhry/cancel"
  },
  "version": "602288aab4a00324ecd0a26fd1d360f70823e4e90a55e72c06b34f460b97a274"
}

Generated in

23.5 seconds

Tweak itReport

Using seed: 37878
Inverting colors of control image
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:01<01:07,  1.37s/it]
  4%|▍         | 2/50 [00:01<00:33,  1.44it/s]
  6%|▌         | 3/50 [00:01<00:22,  2.08it/s]
  8%|▊         | 4/50 [00:02<00:17,  2.66it/s]
 10%|█         | 5/50 [00:02<00:14,  3.13it/s]
 12%|█▏        | 6/50 [00:02<00:12,  3.50it/s]
 14%|█▍        | 7/50 [00:02<00:11,  3.78it/s]
 16%|█▌        | 8/50 [00:02<00:10,  3.98it/s]
 18%|█▊        | 9/50 [00:03<00:09,  4.13it/s]
 20%|██        | 10/50 [00:03<00:09,  4.28it/s]
 22%|██▏       | 11/50 [00:03<00:08,  4.37it/s]
 24%|██▍       | 12/50 [00:03<00:08,  4.43it/s]
 26%|██▌       | 13/50 [00:04<00:08,  4.40it/s]
 28%|██▊       | 14/50 [00:04<00:08,  4.46it/s]
 30%|███       | 15/50 [00:04<00:07,  4.48it/s]
 32%|███▏      | 16/50 [00:04<00:07,  4.50it/s]
 34%|███▍      | 17/50 [00:04<00:07,  4.49it/s]
 36%|███▌      | 18/50 [00:05<00:07,  4.50it/s]
 38%|███▊      | 19/50 [00:05<00:06,  4.49it/s]
 40%|████      | 20/50 [00:05<00:06,  4.49it/s]
 42%|████▏     | 21/50 [00:05<00:06,  4.46it/s]
 44%|████▍     | 22/50 [00:06<00:06,  4.44it/s]
 46%|████▌     | 23/50 [00:06<00:06,  4.49it/s]
 48%|████▊     | 24/50 [00:06<00:05,  4.51it/s]
 50%|█████     | 25/50 [00:06<00:05,  4.50it/s]
 52%|█████▏    | 26/50 [00:06<00:05,  4.48it/s]
 54%|█████▍    | 27/50 [00:07<00:05,  4.52it/s]
 56%|█████▌    | 28/50 [00:07<00:04,  4.51it/s]
 58%|█████▊    | 29/50 [00:07<00:04,  4.50it/s]
 60%|██████    | 30/50 [00:07<00:04,  4.48it/s]
 62%|██████▏   | 31/50 [00:08<00:04,  4.49it/s]
 64%|██████▍   | 32/50 [00:08<00:03,  4.51it/s]
 66%|██████▌   | 33/50 [00:08<00:03,  4.50it/s]
 68%|██████▊   | 34/50 [00:08<00:03,  4.50it/s]
 70%|███████   | 35/50 [00:08<00:03,  4.48it/s]
 72%|███████▏  | 36/50 [00:09<00:03,  4.49it/s]
 74%|███████▍  | 37/50 [00:09<00:02,  4.50it/s]
 76%|███████▌  | 38/50 [00:09<00:02,  4.47it/s]
 78%|███████▊  | 39/50 [00:09<00:02,  4.48it/s]
 80%|████████  | 40/50 [00:10<00:02,  4.47it/s]
 82%|████████▏ | 41/50 [00:10<00:02,  4.47it/s]
 84%|████████▍ | 42/50 [00:10<00:01,  4.46it/s]
 86%|████████▌ | 43/50 [00:10<00:01,  4.48it/s]
 88%|████████▊ | 44/50 [00:10<00:01,  4.48it/s]
 90%|█████████ | 45/50 [00:11<00:01,  4.48it/s]
 92%|█████████▏| 46/50 [00:11<00:00,  4.49it/s]
 94%|█████████▍| 47/50 [00:11<00:00,  4.49it/s]
 96%|█████████▌| 48/50 [00:11<00:00,  4.49it/s]
 98%|█████████▊| 49/50 [00:12<00:00,  4.47it/s]
100%|██████████| 50/50 [00:12<00:00,  4.50it/s]
100%|██████████| 50/50 [00:12<00:00,  4.08it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.023 to run on Replicate, or 43 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 103 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.