cjwbw/pixart-sigma – Run with an API on Replicate

cjwbw / pixart-sigma

Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Cold

Public
6.4K runs
L40S
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Input

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

npx create-replicate --model=cjwbw/pixart-sigma

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

const output = await replicate.run(
  "cjwbw/pixart-sigma:5a54352c99d9fef467986bc8f3a20205e8712cbd3df1cbae4975d6254c902de1",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee.",
      guidance_scale: 4.5,
      negative_prompt: "",
      num_inference_steps: 20
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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 cjwbw/pixart-sigma using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "cjwbw/pixart-sigma:5a54352c99d9fef467986bc8f3a20205e8712cbd3df1cbae4975d6254c902de1",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee.",
        "guidance_scale": 4.5,
        "negative_prompt": "",
        "num_inference_steps": 20
    }
)
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 cjwbw/pixart-sigma 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": "5a54352c99d9fef467986bc8f3a20205e8712cbd3df1cbae4975d6254c902de1",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee.",
      "guidance_scale": 4.5,
      "negative_prompt": "",
      "num_inference_steps": 20
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-04-12T12:27:56.449257Z",
  "created_at": "2024-04-12T12:27:31.431000Z",
  "data_removed": false,
  "error": null,
  "id": "g15d0nzwwxrgp0cet93ag728bg",
  "input": {
    "prompt": "Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee.",
    "guidance_scale": 4.5,
    "num_inference_steps": 20
  },
  "logs": "Using seed: 20940\nSetting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:\n`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.\nSetting `clean_caption` to False...\nSetting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:\n`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.\nSetting `clean_caption` to False...\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:01<00:21,  1.13s/it]\n 10%|█         | 2/20 [00:02<00:20,  1.11s/it]\n 15%|█▌        | 3/20 [00:03<00:18,  1.12s/it]\n 20%|██        | 4/20 [00:04<00:17,  1.12s/it]\n 25%|██▌       | 5/20 [00:05<00:16,  1.12s/it]\n 30%|███       | 6/20 [00:06<00:15,  1.12s/it]\n 35%|███▌      | 7/20 [00:07<00:14,  1.12s/it]\n 40%|████      | 8/20 [00:08<00:13,  1.12s/it]\n 45%|████▌     | 9/20 [00:10<00:12,  1.12s/it]\n 50%|█████     | 10/20 [00:11<00:11,  1.12s/it]\n 55%|█████▌    | 11/20 [00:12<00:10,  1.12s/it]\n 60%|██████    | 12/20 [00:13<00:08,  1.12s/it]\n 65%|██████▌   | 13/20 [00:14<00:07,  1.12s/it]\n 70%|███████   | 14/20 [00:15<00:06,  1.12s/it]\n 75%|███████▌  | 15/20 [00:16<00:05,  1.12s/it]\n 80%|████████  | 16/20 [00:17<00:04,  1.12s/it]\n 85%|████████▌ | 17/20 [00:19<00:03,  1.12s/it]\n 90%|█████████ | 18/20 [00:20<00:02,  1.12s/it]\n 95%|█████████▌| 19/20 [00:21<00:01,  1.12s/it]\n100%|██████████| 20/20 [00:22<00:00,  1.12s/it]\n100%|██████████| 20/20 [00:22<00:00,  1.12s/it]",
  "metrics": {
    "predict_time": 24.970585,
    "total_time": 25.018257
  },
  "output": "https://replicate.delivery/pbxt/zn2mGosXVdI5CJuEdsxSqvR6t2VDlxShAG9BG6OUz76yabqE/out.png",
  "started_at": "2024-04-12T12:27:31.478672Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/g15d0nzwwxrgp0cet93ag728bg",
    "cancel": "https://api.replicate.com/v1/predictions/g15d0nzwwxrgp0cet93ag728bg/cancel"
  },
  "version": "dd378305882101b9be6ade3af645c36337f5050da8819f173f15ec4ad1210067"
}

Generated in

25.0 seconds

Tweak it ShareReport

This output was created using a different version of the model, cjwbw/pixart-sigma:dd378305.

Examples

View more examples

Run time and cost

This model costs approximately $0.072 to run on Replicate, or 13 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 L40S GPU hardware. Predictions typically complete within 74 seconds. The predict time for this model varies significantly based on the inputs.

Readme

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

This repo contains PyTorch model definitions, pre-trained weights and inference/sampling code for our paper exploring Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation. You can find more visualizations on our project page.