afiaka87/retrieval-augmented-diffusion:aace17ed

Version

You're looking at a specific version of this model. Jump to the model overview.

afiaka87 /retrieval-augmented-diffusion:aace17ed

Playground API

Input

prompt

string

Shift + Return to add a new line

model will try to generate this text.

Default: ""

prompt_scale

number

Determines influence of the prompt on the generated image. Going above 5.0 is likely to cause artifacting.

Default: 5

database_name

string

Which database to use for the semantic search. Different databases have different capabilties.

Default: "laion-aesthetic"

num_database_reuslts

integer

(minimum: 1, maximum: 20)

The number of search results to guide the generation with. Using more will 'broaden' capabilities of the model at the risk of causing mode collapse or artifacting.

Default: 10

num_generations

integer

Number of images to generate. Using more will make generation take longer.

Default: 4

height

integer

Desired height of generated images.

Default: 768

width

integer

Desired width of generated images.

Default: 768

steps

integer

How many steps to run the model for. Using more will make generation take longer. 50 tends to work well.

Default: 50

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

npx create-replicate --model=afiaka87/retrieval-augmented-diffusion

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 afiaka87/retrieval-augmented-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "afiaka87/retrieval-augmented-diffusion:aace17ed89538eb52e300bae380bdd7f2e75827cab303d38fe5852bbc5d0b1a8",
  {
    input: {
      steps: 50,
      width: 768,
      height: 768,
      prompt: "",
      prompt_scale: 5,
      database_name: "laion-aesthetic",
      num_generations: 4,
      num_database_reuslts: 10
    }
  }
);

// 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 afiaka87/retrieval-augmented-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "afiaka87/retrieval-augmented-diffusion:aace17ed89538eb52e300bae380bdd7f2e75827cab303d38fe5852bbc5d0b1a8",
    input={
        "steps": 50,
        "width": 768,
        "height": 768,
        "prompt": "",
        "prompt_scale": 5,
        "database_name": "laion-aesthetic",
        "num_generations": 4,
        "num_database_reuslts": 10
    }
)
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 afiaka87/retrieval-augmented-diffusion 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": "afiaka87/retrieval-augmented-diffusion:aace17ed89538eb52e300bae380bdd7f2e75827cab303d38fe5852bbc5d0b1a8",
    "input": {
      "steps": 50,
      "width": 768,
      "height": 768,
      "prompt": "",
      "prompt_scale": 5,
      "database_name": "laion-aesthetic",
      "num_generations": 4,
      "num_database_reuslts": 10
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

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