Isaac 0.1

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

Inference$ Commercial useFrom 1 credit per run

About Isaac 0.1

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

multimodalvision

Pricing

A run with the default settings costs 1 credits. The exact cost updates in the playground as you change settings, and you're only charged when you press Run. Failed runs are refunded automatically.

Inputs

image_urlfilerequired

Image URL to be processed

prompttextarearequired

Prompt to be used for the image

response_styleselectdefault: "text"

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.

Options: text, box, point, polygon

More from Isaac 0.1

Isaac 0.1 [OpenAI Compatible Endpoint]

OpenAI spec compatible endpoint of Isaac-01 which is a multimodal vision-language model from Perceptron for various vision language tasks.

multimodal

vision

Related vision models

OpenRouter [Vision]

Run any Vision Language Model with fal. Analyze and understand images using Claude (Anthropic), GPT-5 / GPT-4o (OpenAI), Gemini (Google), Grok (xAI), Llama (Meta), Qwen, Pixtral (Mistral), and more. Send one or multiple images for captioning, analysis, OCR, or visual Q&A. Powered by OpenRouter.

vision

NSFW Filter

Predict the probability of an image being NSFW.

filtersafety

vision

Video Understanding

A video understanding model to analyze video content and answer questions about what's happening in the video based on user prompts.

utility

vision

NSFW Checker

Predict whether an image is NSFW or SFW.

filtersafety

vision

Moondream3 Preview [Detect]

Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.

Vision

vision

Moondream 3 Preview [Query]

Vision

vision

Florence-2 Large

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

captioningmultimodal

vision

Moondream2

Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.

Vision

vision

Moondream2

Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.

image-to-image

vision

Florence 2 Large OCR

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

ocrmultimodal

vision

MoonDreamNext

MoonDreamNext is a multimodal vision-language model for captioning, gaze detection, bbox detection, point detection, and more.

multimodal

vision

Florence 2 Large Detailed Caption

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

captioningmultimodal

vision