asiryan/kolors – Run with an API on Replicate

asiryan / kolors

Kolors Model (Text2Img and Img2Img)

Cold

Public
16.4K runs
A100 (80GB)
GitHub
Paper

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Expressive illustration of a pug puppy on a Water Slide basked in summer heatExpressive illustration of a pug puppy on a Water Slide basked in summer heat

Input prompt

Default: "Expressive illustration of a pug puppy on a Water Slide basked in summer heat"

negative_prompt

string

Shift + Return to add a new line

Negative Input prompt

Default: ""

image

file

Input image for img2img or inpaint mode

width

integer

Width of output image

Default: 1024

height

integer

Height of output image

Default: 1024

num_outputs

integer

(minimum: 1, maximum: 4)

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: 50)

Scale for classifier-free guidance

Default: 5

strength

number

(minimum: 0, maximum: 1)

Prompt strength when using img2img 1.0 corresponds to full destruction of information in image

Default: 0.8

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=asiryan/kolors

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 asiryan/kolors using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "asiryan/kolors:6f54f70da4ccaeb79084738ad549b7b222dd24229948083d49af110791beb0fe",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "Expressive illustration of a pug puppy on a Water Slide basked in summer heat",
      strength: 0.8,
      num_outputs: 1,
      guidance_scale: 5,
      negative_prompt: "",
      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 asiryan/kolors using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "asiryan/kolors:6f54f70da4ccaeb79084738ad549b7b222dd24229948083d49af110791beb0fe",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "Expressive illustration of a pug puppy on a Water Slide basked in summer heat",
        "strength": 0.8,
        "num_outputs": 1,
        "guidance_scale": 5,
        "negative_prompt": "",
        "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 asiryan/kolors 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": "6f54f70da4ccaeb79084738ad549b7b222dd24229948083d49af110791beb0fe",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "Expressive illustration of a pug puppy on a Water Slide basked in summer heat",
      "strength": 0.8,
      "num_outputs": 1,
      "guidance_scale": 5,
      "negative_prompt": "",
      "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": "2024-08-31T17:24:53.951894Z",
  "created_at": "2024-08-31T17:21:20.555000Z",
  "data_removed": false,
  "error": null,
  "id": "sgqpmfn8ndrgp0chn5ta2hqmyg",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "Expressive illustration of a pug puppy on a Water Slide basked in summer heat",
    "strength": 0.8,
    "num_outputs": 1,
    "guidance_scale": 5,
    "negative_prompt": "",
    "num_inference_steps": 50
  },
  "logs": "Using seed: 21729\nPrompt: Expressive illustration of a pug puppy on a Water Slide basked in summer heat\ntxt2img mode\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:16,  2.95it/s]\n  6%|▌         | 3/50 [00:00<00:09,  5.00it/s]\n  8%|▊         | 4/50 [00:00<00:09,  4.95it/s]\n 10%|█         | 5/50 [00:01<00:09,  4.92it/s]\n 12%|█▏        | 6/50 [00:01<00:09,  4.89it/s]\n 14%|█▍        | 7/50 [00:01<00:08,  4.87it/s]\n 16%|█▌        | 8/50 [00:01<00:08,  4.86it/s]\n 18%|█▊        | 9/50 [00:01<00:08,  4.86it/s]\n 20%|██        | 10/50 [00:02<00:08,  4.85it/s]\n 22%|██▏       | 11/50 [00:02<00:08,  4.84it/s]\n 24%|██▍       | 12/50 [00:02<00:07,  4.84it/s]\n 26%|██▌       | 13/50 [00:02<00:07,  4.84it/s]\n 28%|██▊       | 14/50 [00:02<00:07,  4.84it/s]\n 30%|███       | 15/50 [00:03<00:07,  4.83it/s]\n 32%|███▏      | 16/50 [00:03<00:07,  4.83it/s]\n 34%|███▍      | 17/50 [00:03<00:06,  4.82it/s]\n 36%|███▌      | 18/50 [00:03<00:06,  4.82it/s]\n 38%|███▊      | 19/50 [00:03<00:06,  4.83it/s]\n 40%|████      | 20/50 [00:04<00:06,  4.82it/s]\n 42%|████▏     | 21/50 [00:04<00:06,  4.82it/s]\n 44%|████▍     | 22/50 [00:04<00:05,  4.82it/s]\n 46%|████▌     | 23/50 [00:04<00:05,  4.82it/s]\n 48%|████▊     | 24/50 [00:04<00:05,  4.82it/s]\n 50%|█████     | 25/50 [00:05<00:05,  4.82it/s]\n 52%|█████▏    | 26/50 [00:05<00:04,  4.82it/s]\n 54%|█████▍    | 27/50 [00:05<00:04,  4.83it/s]\n 56%|█████▌    | 28/50 [00:05<00:04,  4.84it/s]\n 58%|█████▊    | 29/50 [00:06<00:04,  4.84it/s]\n 60%|██████    | 30/50 [00:06<00:04,  4.84it/s]\n 62%|██████▏   | 31/50 [00:06<00:03,  4.84it/s]\n 64%|██████▍   | 32/50 [00:06<00:03,  4.85it/s]\n 66%|██████▌   | 33/50 [00:06<00:03,  4.85it/s]\n 68%|██████▊   | 34/50 [00:07<00:03,  4.85it/s]\n 70%|███████   | 35/50 [00:07<00:03,  4.85it/s]\n 72%|███████▏  | 36/50 [00:07<00:02,  4.84it/s]\n 74%|███████▍  | 37/50 [00:07<00:02,  4.85it/s]\n 76%|███████▌  | 38/50 [00:07<00:02,  4.85it/s]\n 78%|███████▊  | 39/50 [00:08<00:02,  4.85it/s]\n 80%|████████  | 40/50 [00:08<00:02,  4.84it/s]\n 82%|████████▏ | 41/50 [00:08<00:01,  4.84it/s]\n 84%|████████▍ | 42/50 [00:08<00:01,  4.85it/s]\n 86%|████████▌ | 43/50 [00:08<00:01,  4.85it/s]\n 88%|████████▊ | 44/50 [00:09<00:01,  4.85it/s]\n 90%|█████████ | 45/50 [00:09<00:01,  4.84it/s]\n 92%|█████████▏| 46/50 [00:09<00:00,  4.84it/s]\n 94%|█████████▍| 47/50 [00:09<00:00,  4.84it/s]\n 96%|█████████▌| 48/50 [00:09<00:00,  4.84it/s]\n 98%|█████████▊| 49/50 [00:10<00:00,  4.84it/s]\n100%|██████████| 50/50 [00:10<00:00,  4.84it/s]\n100%|██████████| 50/50 [00:10<00:00,  4.83it/s]",
  "metrics": {
    "predict_time": 12.481473536,
    "total_time": 213.396894
  },
  "output": [
    "https://replicate.delivery/pbxt/frO57S8xnmwbaChZa5bFuYXW8ls0aWQKggRCfda2GW3lPQYTA/out-0.png"
  ],
  "started_at": "2024-08-31T17:24:41.470420Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/sgqpmfn8ndrgp0chn5ta2hqmyg",
    "cancel": "https://api.replicate.com/v1/predictions/sgqpmfn8ndrgp0chn5ta2hqmyg/cancel"
  },
  "version": "6f54f70da4ccaeb79084738ad549b7b222dd24229948083d49af110791beb0fe"
}

Generated in

12.5 seconds

Tweak it ShareReport

Using seed: 21729
Prompt: Expressive illustration of a pug puppy on a Water Slide basked in summer heat
txt2img mode
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:16,  2.95it/s]
  6%|▌         | 3/50 [00:00<00:09,  5.00it/s]
  8%|▊         | 4/50 [00:00<00:09,  4.95it/s]
 10%|█         | 5/50 [00:01<00:09,  4.92it/s]
 12%|█▏        | 6/50 [00:01<00:09,  4.89it/s]
 14%|█▍        | 7/50 [00:01<00:08,  4.87it/s]
 16%|█▌        | 8/50 [00:01<00:08,  4.86it/s]
 18%|█▊        | 9/50 [00:01<00:08,  4.86it/s]
 20%|██        | 10/50 [00:02<00:08,  4.85it/s]
 22%|██▏       | 11/50 [00:02<00:08,  4.84it/s]
 24%|██▍       | 12/50 [00:02<00:07,  4.84it/s]
 26%|██▌       | 13/50 [00:02<00:07,  4.84it/s]
 28%|██▊       | 14/50 [00:02<00:07,  4.84it/s]
 30%|███       | 15/50 [00:03<00:07,  4.83it/s]
 32%|███▏      | 16/50 [00:03<00:07,  4.83it/s]
 34%|███▍      | 17/50 [00:03<00:06,  4.82it/s]
 36%|███▌      | 18/50 [00:03<00:06,  4.82it/s]
 38%|███▊      | 19/50 [00:03<00:06,  4.83it/s]
 40%|████      | 20/50 [00:04<00:06,  4.82it/s]
 42%|████▏     | 21/50 [00:04<00:06,  4.82it/s]
 44%|████▍     | 22/50 [00:04<00:05,  4.82it/s]
 46%|████▌     | 23/50 [00:04<00:05,  4.82it/s]
 48%|████▊     | 24/50 [00:04<00:05,  4.82it/s]
 50%|█████     | 25/50 [00:05<00:05,  4.82it/s]
 52%|█████▏    | 26/50 [00:05<00:04,  4.82it/s]
 54%|█████▍    | 27/50 [00:05<00:04,  4.83it/s]
 56%|█████▌    | 28/50 [00:05<00:04,  4.84it/s]
 58%|█████▊    | 29/50 [00:06<00:04,  4.84it/s]
 60%|██████    | 30/50 [00:06<00:04,  4.84it/s]
 62%|██████▏   | 31/50 [00:06<00:03,  4.84it/s]
 64%|██████▍   | 32/50 [00:06<00:03,  4.85it/s]
 66%|██████▌   | 33/50 [00:06<00:03,  4.85it/s]
 68%|██████▊   | 34/50 [00:07<00:03,  4.85it/s]
 70%|███████   | 35/50 [00:07<00:03,  4.85it/s]
 72%|███████▏  | 36/50 [00:07<00:02,  4.84it/s]
 74%|███████▍  | 37/50 [00:07<00:02,  4.85it/s]
 76%|███████▌  | 38/50 [00:07<00:02,  4.85it/s]
 78%|███████▊  | 39/50 [00:08<00:02,  4.85it/s]
 80%|████████  | 40/50 [00:08<00:02,  4.84it/s]
 82%|████████▏ | 41/50 [00:08<00:01,  4.84it/s]
 84%|████████▍ | 42/50 [00:08<00:01,  4.85it/s]
 86%|████████▌ | 43/50 [00:08<00:01,  4.85it/s]
 88%|████████▊ | 44/50 [00:09<00:01,  4.85it/s]
 90%|█████████ | 45/50 [00:09<00:01,  4.84it/s]
 92%|█████████▏| 46/50 [00:09<00:00,  4.84it/s]
 94%|█████████▍| 47/50 [00:09<00:00,  4.84it/s]
 96%|█████████▌| 48/50 [00:09<00:00,  4.84it/s]
 98%|█████████▊| 49/50 [00:10<00:00,  4.84it/s]
100%|██████████| 50/50 [00:10<00:00,  4.84it/s]
100%|██████████| 50/50 [00:10<00:00,  4.83it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.091 to run on Replicate, or 10 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 A100 (80GB) GPU hardware. Predictions typically complete within 65 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Kolors Model (Text2Img and Img2Img)