dhanushreddy291/amused-text-to-image – Run with an API on Replicate

dhanushreddy291 / amused-text-to-image

Amused is a lightweight text to image model based off of the muse architecture. Amused is particularly useful in applications that require a lightweight and fast model such as generating many images quickly at once.

Cold

Public
196 runs
L40S
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

a photo of a colorful lemon mocktail can with mint leaves with an abstract backgrounda photo of a colorful lemon mocktail can with mint leaves with an abstract background

Input prompt

Default: "a cute minimalistic simple capybara side profile, in the style of Jon Klassen, desaturated light and airy pastel color palette, nursery art, white background"

negative_prompt

string

Shift + Return to add a new line

3d, cgi, render, bad quality, normal quality3d, cgi, render, bad quality, normal quality

Input Negative Prompt

Default: "3d, cgi, render, bad quality, normal quality"

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

guidance_scale

number

Guidance Scale

Default: 10

num_inference_steps

integer

(minimum: 10, maximum: 50)

Number of inference steps

Default: 30

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=dhanushreddy291/amused-text-to-image

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 dhanushreddy291/amused-text-to-image using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "dhanushreddy291/amused-text-to-image:6f67e16d8ad72712b34058e1206329d10e9e18b9fbf5686f9485cfa0bd2be8f6",
  {
    input: {
      prompt: "a photo of a colorful lemon mocktail can with mint leaves with an abstract background",
      num_outputs: 1,
      guidance_scale: 20,
      negative_prompt: "3d, cgi, render, bad quality, normal quality",
      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 dhanushreddy291/amused-text-to-image using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "dhanushreddy291/amused-text-to-image:6f67e16d8ad72712b34058e1206329d10e9e18b9fbf5686f9485cfa0bd2be8f6",
    input={
        "prompt": "a photo of a colorful lemon mocktail can with mint leaves with an abstract background",
        "num_outputs": 1,
        "guidance_scale": 20,
        "negative_prompt": "3d, cgi, render, bad quality, normal quality",
        "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 dhanushreddy291/amused-text-to-image 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": "6f67e16d8ad72712b34058e1206329d10e9e18b9fbf5686f9485cfa0bd2be8f6",
    "input": {
      "prompt": "a photo of a colorful lemon mocktail can with mint leaves with an abstract background",
      "num_outputs": 1,
      "guidance_scale": 20,
      "negative_prompt": "3d, cgi, render, bad quality, normal quality",
      "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": "2024-01-10T16:35:13.508688Z",
  "created_at": "2024-01-10T16:35:10.383038Z",
  "data_removed": false,
  "error": null,
  "id": "v563bc3bwzbft5egvh6qvte52i",
  "input": {
    "prompt": "a photo of a colorful lemon mocktail can with mint leaves with an abstract background",
    "num_outputs": 1,
    "guidance_scale": 20,
    "negative_prompt": "3d, cgi, render, bad quality, normal quality",
    "num_inference_steps": 50
  },
  "logs": "Using seed: 1386652\n  0%|          | 0/50 [00:00<?, ?it/s]\n  6%|▌         | 3/50 [00:00<00:01, 26.23it/s]\n 12%|█▏        | 6/50 [00:00<00:01, 27.20it/s]\n 18%|█▊        | 9/50 [00:00<00:01, 27.67it/s]\n 24%|██▍       | 12/50 [00:00<00:01, 27.99it/s]\n 30%|███       | 15/50 [00:00<00:01, 28.26it/s]\n 36%|███▌      | 18/50 [00:00<00:01, 28.43it/s]\n 42%|████▏     | 21/50 [00:00<00:01, 27.70it/s]\n 48%|████▊     | 24/50 [00:00<00:00, 27.39it/s]\n 54%|█████▍    | 27/50 [00:00<00:00, 26.45it/s]\n 60%|██████    | 30/50 [00:01<00:00, 25.59it/s]\n 66%|██████▌   | 33/50 [00:01<00:00, 25.87it/s]\n 72%|███████▏  | 36/50 [00:01<00:00, 26.26it/s]\n 78%|███████▊  | 39/50 [00:01<00:00, 26.88it/s]\n 84%|████████▍ | 42/50 [00:01<00:00, 27.38it/s]\n 90%|█████████ | 45/50 [00:01<00:00, 27.60it/s]\n 96%|█████████▌| 48/50 [00:01<00:00, 26.99it/s]\n100%|██████████| 50/50 [00:01<00:00, 27.03it/s]",
  "metrics": {
    "predict_time": 3.091566,
    "total_time": 3.12565
  },
  "output": [
    "https://replicate.delivery/pbxt/qeggT9SUk1Vqb68IOOcqeqMu4asrfYRreZ7jCcUnv89AUeYRC/out-0.png"
  ],
  "started_at": "2024-01-10T16:35:10.417122Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/v563bc3bwzbft5egvh6qvte52i",
    "cancel": "https://api.replicate.com/v1/predictions/v563bc3bwzbft5egvh6qvte52i/cancel"
  },
  "version": "6f67e16d8ad72712b34058e1206329d10e9e18b9fbf5686f9485cfa0bd2be8f6"
}

Generated in

3.1 seconds

Tweak itReport

Examples

View more examples

Run time and cost

This model costs approximately $0.0030 to run on Replicate, or 333 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 4 seconds. The predict time for this model varies significantly based on the inputs.

Readme

aMUSEd is based on Masked Image Modeling. It makes for a compelling use case for the community to explore components that are known to work in language modeling in the context of image generation.

Learn more at: https://huggingface.co/blog/amused