georgedavila/pixart-alpha-general – Run with an API on Replicate

georgedavila / pixart-alpha-general

Allows you to test out different Pixart-Alpha models, text encoders for those models, and run custom Pixart-Alpha checkpoints on replicate

Cold

Public
7 runs
L40S
GitHub

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

A cat doing karate in Madrid, cinematic, 8k UHDA cat doing karate in Madrid, cinematic, 8k UHD

Input prompt

Default: "A cat doing karate in Madrid, cinematic, 8k UHD"

negative_prompt

string

Shift + Return to add a new line

Negative prompt

modelChoice

string

Pixart model to use

Default: "PixArt-alpha/PixArt-XL-2-1024-MS"

useCustomModel

boolean

Enter custom model - check this to use the Pixart model you type in below rather than one of the choices above.

Default: false

customModel

string

Shift + Return to add a new line

Custom Pixart model path (from huggingface hub)

Default: "PixArt-alpha/PixArt-XL-2-1024-MS"

textEncoderChoice

string

Text Encoder for Pixart model to use

Default: "PixArt-alpha/PixArt-XL-2-1024-MS"

useCustomTextEncoder

boolean

Enter custom text encoder - check this to use the text encoder you type in below rather than one of the choices above.

Default: false

customTextEncoder

string

Shift + Return to add a new line

Custom text encoder path (from huggingface hub)

Default: "PixArt-alpha/PixArt-XL-2-1024-MS"

style

string

Image style

Default: "None"

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

scheduler

string

scheduler

Default: "DPMSolverMultistep"

num_inference_steps

integer

(minimum: 1, maximum: 100)

Number of denoising steps

Default: 14

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 4.5

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=georgedavila/pixart-alpha-general

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 georgedavila/pixart-alpha-general using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "georgedavila/pixart-alpha-general:3bc1c7f4264ca6bde44c8fb9610c820815ef128bec04f01a33dbb03a091f5b0f",
  {
    input: {
      style: "None",
      width: 1024,
      height: 1024,
      prompt: "A cat doing karate in Madrid, cinematic, 8k UHD",
      scheduler: "DPMSolverMultistep",
      customModel: "PixArt-alpha/PixArt-XL-2-1024-MS",
      modelChoice: "PixArt-alpha/PixArt-XL-2-1024-MS",
      num_outputs: 1,
      guidance_scale: 4.5,
      useCustomModel: false,
      customTextEncoder: "PixArt-alpha/PixArt-XL-2-1024-MS",
      textEncoderChoice: "PixArt-alpha/PixArt-XL-2-1024-MS",
      num_inference_steps: 14,
      useCustomTextEncoder: false
    }
  }
);
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 georgedavila/pixart-alpha-general using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "georgedavila/pixart-alpha-general:3bc1c7f4264ca6bde44c8fb9610c820815ef128bec04f01a33dbb03a091f5b0f",
    input={
        "style": "None",
        "width": 1024,
        "height": 1024,
        "prompt": "A cat doing karate in Madrid, cinematic, 8k UHD",
        "scheduler": "DPMSolverMultistep",
        "customModel": "PixArt-alpha/PixArt-XL-2-1024-MS",
        "modelChoice": "PixArt-alpha/PixArt-XL-2-1024-MS",
        "num_outputs": 1,
        "guidance_scale": 4.5,
        "useCustomModel": False,
        "customTextEncoder": "PixArt-alpha/PixArt-XL-2-1024-MS",
        "textEncoderChoice": "PixArt-alpha/PixArt-XL-2-1024-MS",
        "num_inference_steps": 14,
        "useCustomTextEncoder": False
    }
)
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 georgedavila/pixart-alpha-general 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": "3bc1c7f4264ca6bde44c8fb9610c820815ef128bec04f01a33dbb03a091f5b0f",
    "input": {
      "style": "None",
      "width": 1024,
      "height": 1024,
      "prompt": "A cat doing karate in Madrid, cinematic, 8k UHD",
      "scheduler": "DPMSolverMultistep",
      "customModel": "PixArt-alpha/PixArt-XL-2-1024-MS",
      "modelChoice": "PixArt-alpha/PixArt-XL-2-1024-MS",
      "num_outputs": 1,
      "guidance_scale": 4.5,
      "useCustomModel": false,
      "customTextEncoder": "PixArt-alpha/PixArt-XL-2-1024-MS",
      "textEncoderChoice": "PixArt-alpha/PixArt-XL-2-1024-MS",
      "num_inference_steps": 14,
      "useCustomTextEncoder": false
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

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

Run this to download the model and run it in your local environment:

cog predict r8.im/georgedavila/pixart-alpha-general@sha256:3bc1c7f4264ca6bde44c8fb9610c820815ef128bec04f01a33dbb03a091f5b0f \
  -i 'style="None"' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="A cat doing karate in Madrid, cinematic, 8k UHD"' \
  -i 'scheduler="DPMSolverMultistep"' \
  -i 'customModel="PixArt-alpha/PixArt-XL-2-1024-MS"' \
  -i 'modelChoice="PixArt-alpha/PixArt-XL-2-1024-MS"' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=4.5' \
  -i 'useCustomModel=false' \
  -i 'customTextEncoder="PixArt-alpha/PixArt-XL-2-1024-MS"' \
  -i 'textEncoderChoice="PixArt-alpha/PixArt-XL-2-1024-MS"' \
  -i 'num_inference_steps=14' \
  -i 'useCustomTextEncoder=false'

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

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/georgedavila/pixart-alpha-general@sha256:3bc1c7f4264ca6bde44c8fb9610c820815ef128bec04f01a33dbb03a091f5b0f
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "style": "None",
      "width": 1024,
      "height": 1024,
      "prompt": "A cat doing karate in Madrid, cinematic, 8k UHD",
      "scheduler": "DPMSolverMultistep",
      "customModel": "PixArt-alpha/PixArt-XL-2-1024-MS",
      "modelChoice": "PixArt-alpha/PixArt-XL-2-1024-MS",
      "num_outputs": 1,
      "guidance_scale": 4.5,
      "useCustomModel": false,
      "customTextEncoder": "PixArt-alpha/PixArt-XL-2-1024-MS",
      "textEncoderChoice": "PixArt-alpha/PixArt-XL-2-1024-MS",
      "num_inference_steps": 14,
      "useCustomTextEncoder": false
    }
  }' \
  http://localhost:5000/predictions

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

Output

No output yet! Press "Submit" to start a prediction.

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.