Readme
…
Model description
…
Intended use
…
Ethical considerations
…
Caveats and recommendations
…
Use `Aubrey man` or `Aubrey woman` for the name of the avatar
Run this model in Node.js with one line of code:
npm install replicate
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import Replicate from "replicate";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});
Run web-cardinalblue/avatar-loras using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"web-cardinalblue/avatar-loras:44a21f6c64c59a601eb588ddd782ac8b7bb01a168bc5c6d3e31a6fce6651850f",
{
input: {
seamless: false,
batch_size: 1,
lora_model: "filipe",
num_images: 1,
negative_prompt: "no face, face out of frame, cut-off face, no person, cutlow quality, blurry, bad anatomy, worst quality, text, watermark, ugly, signature, lowres, deformed, extra limbs, disfigured, cropped, jpeg artifacts, bad hands, error, mutation, missing fingers, poorly drawn hands, poorly drawn face, extra digit, fewer digits, out of frame, extra fingers, mutated hands, extra legs, extra arms, bad proportions, long neck, fused fingers, missing arms, duplicate, mutated, missing legs, too many fingers, mutilated, malformed limbs, artist name, gross proportions, cloned face, morbid, bad art, logo, nsfw, poorly drawn, sketches, skin blemishes, skin spots, censored, acnes, close up, mutated hands and fingers, malformed hands, long body, child, missing limb, age spot, extra limb, bad feet, sketch, greyscale, floating limbs, disconnected limbs, poorly drawn feet, tiling, body out of frame, glans, out of focus, cross-eye, disgusting, bad body, multiple views, malformed, nude"
}
}
);
// 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.
No output yet! Press "Submit" to start a prediction.
This model costs approximately $0.0092 to run on Replicate, or 108 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 7 seconds.
…
…
…
…
…