J

Janus 1.3B ONNX

Developed by onnx-community
Janus-1.3B is a multimodal causal language model that supports text-to-image, image-to-text, and image-text-to-text conversion tasks.
Downloads 123
Release Time : 10/26/2024

Model Overview

Janus-1.3B is a multimodal model based on ONNX weights, compatible with Transformers.js, capable of handling interactive tasks involving images and text, such as generating image descriptions or creating images from text.

Model Features

Multimodal Support
Capable of processing both image and text inputs, enabling cross-modal interaction and generation.
ONNX Compatibility
Provides ONNX weights, compatible with Transformers.js, facilitating deployment in browsers and edge devices.
Efficient Generation
Supports efficient text and image generation, suitable for real-time applications.

Model Capabilities

Text-to-image generation
Image-to-text conversion
Image-text-to-text conversion
Multimodal interaction

Use Cases

Education
Formula Conversion
Convert images of mathematical formulas into LaTeX code.
Generates accurate LaTeX code for academic document writing.
Creative Design
Image Generation
Generate high-quality images based on text descriptions.
Produces images that match the descriptions, suitable for artistic creation and design.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase