Isaac 01 | Vision

perceptron/isaac-01

Isaac-01 is a multimodal vision-language model from Perceptron for various vision language tasks.

Inference

Commercial use

Streaming

Partner

Schema

LLMs

Playground API

About

Run Vision

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Migrate to @fal-ai/client

The @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Please check the migration guide for more information.

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("perceptron/isaac-01", {
  input: {
    image_url: "https://v3b.fal.media/files/b/penguin/BxDPafViqMBGfNyvcmG-C_image-1d100e9%20(4).jpg",
    prompt: "Which car is trying to park into garage?"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

Streaming#

This model supports streaming requests. You can stream data directly to the model and get the result in real-time.

import { fal } from "@fal-ai/client";

const stream = await fal.stream("perceptron/isaac-01", {
  input: {
    image_url: "https://v3b.fal.media/files/b/penguin/BxDPafViqMBGfNyvcmG-C_image-1d100e9%20(4).jpg",
    prompt: "Which car is trying to park into garage?"
  }
});

for await (const event of stream) {
  console.log(event);
}

const result = await stream.done();

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration.

import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

Protect your API Key

When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.

3. Queue#

Long-running requests

For long-running requests, such as training jobs or models with slower inference times, it is recommended to check the Queue status and rely on Webhooks instead of blocking while waiting for the result.

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("perceptron/isaac-01", {
  input: {
    image_url: "https://v3b.fal.media/files/b/penguin/BxDPafViqMBGfNyvcmG-C_image-1d100e9%20(4).jpg",
    prompt: "Which car is trying to park into garage?"
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("perceptron/isaac-01", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("perceptron/isaac-01", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Auto uploads

The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).

Read more about file handling in our file upload guide.

5. Schema#

Input#

image_url string* required

Image URL to be processed

prompt string* required

Prompt to be used for the image

response_style ResponseStyleEnum

Response style to be used for the image.

text: Model will output text. Good for descriptions and captioning.
box: Model will output a combination of text and bounding boxes. Good for localization.
point: Model will output a combination of text and points. Good for counting many objects.
polygon: Model will output a combination of text and polygons. Good for granular segmentation. Default value: "text"

Possible enum values: text, box, point, polygon

{
  "image_url": "https://v3b.fal.media/files/b/penguin/BxDPafViqMBGfNyvcmG-C_image-1d100e9%20(4).jpg",
  "prompt": "Which car is trying to park into garage?",
  "response_style": "text"
}

Output#

output string* required

Generated output

partial boolean

Whether the output is partial

error string

Error message if an error occurred

usage CompletionUsage

Usage information

{
  "output": "To determine which car is trying to park into the garage, we need to carefully observe the positions and movements of the vehicles in the image.\n\n1. **Identify the Vehicles**: \n   - There are three vehicles visible: a green truck, an orange car, and a brown car.\n   - The green truck is positioned in front of the garage entrance.\n   - The orange car is parked to the left of the green truck.\n   - The brown car is parked to the right of the green truck.\n\n2. **Analyze the Positions**:\n   - The green truck is directly in front of the garage entrance, suggesting it is in the process of moving towards the entrance.\n   - The orange car is parked parallel to the garage but is not in the path of the green truck.\n   - The brown car is also parked parallel to the garage but is not in the path of the green truck.\n\n3. **Determine the Action**:\n   - Given the position of the green truck directly in front of the garage entrance, it is most likely that the green truck is trying to park into the garage.\n   - The orange and brown cars are already parked and do not appear to be in motion or attempting to park.\n\nTherefore, the car that is trying to park into the garage is the green truck."
}

Other types#

CompletionUsage#

completion_tokens integer* required

Number of tokens in the completion

prompt_tokens integer* required

Number of tokens in the prompt

total_tokens integer* required

Total tokens used

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

Streaming#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

CompletionUsage#

Related Models

Isaac 01 Vision

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

Streaming#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

CompletionUsage#

Related Models