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

Input

Image Url*

Hint: Drag and drop image files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: jpg, jpeg, png, webp, gif, avif

Prompt*

Response Style

Streaming

Result

Idle

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.

1. **Identify the Vehicles**: 
   - There are three vehicles visible: a green truck, an orange car, and a brown car.
   - The green truck is positioned in front of the garage entrance.
   - The orange car is parked to the left of the green truck.
   - The brown car is parked to the right of the green truck.

2. **Analyze the Positions**:
   - The green truck is directly in front of the garage entrance, suggesting it is in the process of moving towards the entrance.
   - The orange car is parked parallel to the garage but is not in the path of the green truck.
   - The brown car is also parked parallel to the garage but is not in the path of the green truck.

3. **Determine the Action**:
   - 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.
   - The orange and brown cars are already parked and do not appear to be in motion or attempting to park.

Therefore, the car that is trying to park into the garage is the green truck.

{
  "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."
}

$0.26 per 1M input tokens, $2.17 per 1M output tokens

Logs

For an OpenAI compatible API, you can use it like below:

py
from openai import OpenAI

client = OpenAI(
    base_url="https://perceptron.fal.ai/openai/v1",
    api_key="N/A",
    default_headers={
        "Authorization": f"Key {os.environ['FAL_KEY']}",
    }
)

response_style = "box"
messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image_url",
                "image_url": {
                    "url": "https://storage.googleapis.com/falserverless/model_tests/perceptron/8d3aef9b-5b44-4853-8381-80c24dd24deb.webp"
                }
            }
        ]
    },
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "Was a shot taken before the buzzer? Use the ball positioning and the shot clock to make your decision. Provide a one sentence rationale."
            }
        ]
    },
]

response = client.chat.completions.create(
    model="perceptron",
    messages=messages,
    extra_body={
        "response_style": response_style,
    }
)

Or directly use the endpoint via cURL:

bash
curl https://fal.run/perceptron/isaac-01/openai/v1/chat/completions \
-H "Authorization: Key $FAL_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "perceptron", "messages": [{"role": "user", "content": [{"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/falserverless/model_tests/perceptron/8d3aef9b-5b44-4853-8381-80c24dd24deb.webp" }}]}, {"role": "user", "content": [{"type": "text", "text": "Was a shot taken before the buzzer? Use the ball positioning and the shot clock to make your decision. Provide a one sentence rationale." }] }], "extra_body": {"response_style": "box"}}'

Isaac 01 Vision

Input

Result

Logs