pagebrain/wuerstchen-v2 – Run with an API on Replicate

Input

prompt

string

Shift + Return to add a new line

Anthropomorphic chicken dressed as an officerAnthropomorphic chicken dressed as an officer

Input prompt

negative_prompt

string

Shift + Return to add a new line

Specify things to not see in the output.

width

integer

Width of output image. Maximum size is 1536

Default: 1024

height

integer

Height of output image. Maximum size is 1536

Default: 1024

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

prior_guidance_scale

number

(minimum: 1, maximum: 20)

prior_guidance_scale

Default: 4

prior_num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 30

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 12

decoder_guidance_scale

number

(minimum: 0, maximum: 20)

Scale for classifier-free guidance

Default: 0

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=pagebrain/wuerstchen-v2

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 pagebrain/wuerstchen-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "pagebrain/wuerstchen-v2:0725c5f70905b87ffadd7d6fe4cfae1b5457784d911eebd8521022892deb481a",
  {
    input: {
      seed: 39564,
      width: 1024,
      height: 1024,
      prompt: "Anthropomorphic chicken dressed as an officer",
      num_outputs: 1,
      num_inference_steps: 12,
      prior_guidance_scale: 4,
      decoder_guidance_scale: 0,
      prior_num_inference_steps: 30
    }
  }
);
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 pagebrain/wuerstchen-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "pagebrain/wuerstchen-v2:0725c5f70905b87ffadd7d6fe4cfae1b5457784d911eebd8521022892deb481a",
    input={
        "seed": 39564,
        "width": 1024,
        "height": 1024,
        "prompt": "Anthropomorphic chicken dressed as an officer",
        "num_outputs": 1,
        "num_inference_steps": 12,
        "prior_guidance_scale": 4,
        "decoder_guidance_scale": 0,
        "prior_num_inference_steps": 30
    }
)
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 pagebrain/wuerstchen-v2 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": "0725c5f70905b87ffadd7d6fe4cfae1b5457784d911eebd8521022892deb481a",
    "input": {
      "seed": 39564,
      "width": 1024,
      "height": 1024,
      "prompt": "Anthropomorphic chicken dressed as an officer",
      "num_outputs": 1,
      "num_inference_steps": 12,
      "prior_guidance_scale": 4,
      "decoder_guidance_scale": 0,
      "prior_num_inference_steps": 30
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run pagebrain/wuerstchen-v2 using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/pagebrain/wuerstchen-v2@sha256:0725c5f70905b87ffadd7d6fe4cfae1b5457784d911eebd8521022892deb481a \
  -i 'seed=39564' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="Anthropomorphic chicken dressed as an officer"' \
  -i 'num_outputs=1' \
  -i 'num_inference_steps=12' \
  -i 'prior_guidance_scale=4' \
  -i 'decoder_guidance_scale=0' \
  -i 'prior_num_inference_steps=30'

To learn more, take a look at the Cog documentation.

Pull and run pagebrain/wuerstchen-v2 using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/pagebrain/wuerstchen-v2@sha256:0725c5f70905b87ffadd7d6fe4cfae1b5457784d911eebd8521022892deb481a
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 39564,
      "width": 1024,
      "height": 1024,
      "prompt": "Anthropomorphic chicken dressed as an officer",
      "num_outputs": 1,
      "num_inference_steps": 12,
      "prior_guidance_scale": 4,
      "decoder_guidance_scale": 0,
      "prior_num_inference_steps": 30
    }
  }' \
  http://localhost:5000/predictions

Output

{
  "completed_at": "2023-09-16T06:43:30.217513Z",
  "created_at": "2023-09-16T06:43:26.376094Z",
  "data_removed": false,
  "error": null,
  "id": "yetdezjbedldgfhnmq2oe5x4yq",
  "input": {
    "seed": 39564,
    "width": 1024,
    "height": 1024,
    "prompt": "Anthropomorphic chicken dressed as an officer",
    "num_outputs": 1,
    "num_inference_steps": 12,
    "prior_guidance_scale": 4,
    "decoder_guidance_scale": 0,
    "prior_num_inference_steps": 30
  },
  "logs": "Using seed: 39564\nPrompt: Anthropomorphic chicken dressed as an officer\n  0%|          | 0/30 [00:00<?, ?it/s]\n 10%|█         | 3/30 [00:00<00:01, 20.60it/s]\n 20%|██        | 6/30 [00:00<00:01, 21.28it/s]\n 30%|███       | 9/30 [00:00<00:00, 21.40it/s]\n 40%|████      | 12/30 [00:00<00:00, 21.46it/s]\n 50%|█████     | 15/30 [00:00<00:00, 21.38it/s]\n 60%|██████    | 18/30 [00:00<00:00, 21.50it/s]\n 70%|███████   | 21/30 [00:00<00:00, 21.32it/s]\n 80%|████████  | 24/30 [00:01<00:00, 21.55it/s]\n 90%|█████████ | 27/30 [00:01<00:00, 21.61it/s]\n100%|██████████| 30/30 [00:01<00:00, 21.70it/s]\n100%|██████████| 30/30 [00:01<00:00, 21.50it/s]\n  0%|          | 0/12 [00:00<?, ?it/s]\n 17%|█▋        | 2/12 [00:00<00:00, 12.24it/s]\n 33%|███▎      | 4/12 [00:00<00:00, 12.83it/s]\n 50%|█████     | 6/12 [00:00<00:00, 13.03it/s]\n 67%|██████▋   | 8/12 [00:00<00:00, 13.19it/s]\n 83%|████████▎ | 10/12 [00:00<00:00, 13.21it/s]\n100%|██████████| 12/12 [00:00<00:00, 13.30it/s]\n100%|██████████| 12/12 [00:00<00:00, 13.14it/s]",
  "metrics": {
    "predict_time": 3.879448,
    "total_time": 3.841419
  },
  "output": [
    "https://pbxt.replicate.delivery/e2U2mWZ6NTQhFqZeeX8U8TxLIuffsNBSxGKSSHlpJ6COSAmMC/out-0.png"
  ],
  "started_at": "2023-09-16T06:43:26.338065Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/yetdezjbedldgfhnmq2oe5x4yq",
    "cancel": "https://api.replicate.com/v1/predictions/yetdezjbedldgfhnmq2oe5x4yq/cancel"
  },
  "version": "0725c5f70905b87ffadd7d6fe4cfae1b5457784d911eebd8521022892deb481a"
}

Generated in

3.9 seconds

Tweak itReport

Run time and cost

This model costs approximately $0.0057 to run on Replicate, or 175 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 5 seconds. The predict time for this model varies significantly based on the inputs.