The WorqHat AI API is a versatile tool that can be used for a wide range of tasks involving natural language, code, and images. Our API provides various models with varying power levels, suitable for different tasks, and can be trained on the fly while generating outputs. With the flexibility to handle content generation, semantic search, and classification, our API offers a comprehensive solution for your needs.

​
Models

We are proud to offer a suite of AI models that are built upon the foundation of four core models. These models have been carefully developed to offer a range of capabilities in processing both images and text, allowing users to leverage the power of AI to unlock new insights and achieve better outcomes.

Our image processing models include ImageCon, which offers advanced image composition and face generation capabilities, and ImageEnhance, which enhances the quality and detail of images, making them clearer and more visually appealing.

For text processing, we offer AiCon, a powerful model that generates high-quality, coherent text from prompts, and categorizes text into predefined categories, enabling users to quickly and accurately classify and analyze large volumes of text data.

All of our models are built on a foundation of cutting-edge AI techniques and are designed to be highly accurate, efficient, and scalable. Additionally, we offer an API that allows developers and researchers to build on top of our models, enabling them to leverage the power of AI in their own projects and applications.

By offering a suite of AI models that are based on these core capabilities, we are committed to helping our users unlock new insights and achieve better outcomes in their work.

​
Text Generation

The text generation model is a powerful tool that can be used to generate text based on a prompt. The model is trained on a large corpus of text, and can be fine-tuned to generate text in a specific style or domain. The model can be used to generate text in a variety of styles, including news articles, blog posts, and even poetry. You can use the model to generate text content for your website, or to generate text for your chatbot.

AiCon V2

The General Purpose Text Generation Model for all your needs. Faster and more efficient than V3.

AiCon V3

Our most powerful Text Generation Model for all creative needs. A bit slower than V2.

AiCon V2 Large (Beta)

This is the Custom Model available to Custom Train and Fine-Tune. You can send in large training data in the form of CSVs and JSONs to create a model that is grounded on your data and is capable of generating text based on your trained content.

AiCon V2 2023 (Alpha)

The Alpha Channel of AiCon V2 is mostly dependent on the Data upto June 2023 and it also Re-Trains content based on the most recent data which makes it relatively upto date and more accurate than the previous versions of AiCon.

The AI for Search model is a powerful tool that can be used to search for texts. Enhance your user’s search experience with custom filters and build a faceted search interface powered by AI in a few lines of code. Requiring very little configuration to be installed, yet highly customizable.

Search V2

The General Purpose Search Model for all your needs. Faster and more efficient than V3 and capable of Handling Spelling Mistakes in Search Queries.

Search V3

Our most powerful Search Model for all creative needs. A bit slower than V2 but more accurate and capable of Handling Searches Based on Context & Meaning.

​
Image Generation

The Image Generation model is a powerful tool that can be used to generate images based on a prompt. The model is trained on a large corpus of images, and can be fine-tuned to generate images in a specific style or domain. The model can be used to generate images in a variety of styles, including paintings, cartoons, and even photographs. You can use the model to generate images for your website, or to generate images for your marketing campaigns and get ideas for your next designs.

ImageCon V2

The General Purpose Image Generation Model for all your needs. Faster and more efficient than V3. However, it is not as accurate as V3 when it comes to generation quality and context understanding.

ImageCon V3

Our most powerful Image Generation Model for all creative needs. A bit slower than V2 but more accurate and capable of Handling Images Based on Context & Meaning. Also capable of handling more complex images and generating better results.

Image to Image Gen V2

A part of the ImageCon V2 Model, this model is capable of generating images based on a Image as a input. The model is trained on a large corpus of images, and can be fine-tuned to generate images in a specific style or domain.

Image to Image Gen V3

A part of the ImageCon V3 Model, this model is capable of generating images based on a Image as a input. The model can be used to generate images in a variety of styles, including paintings, cartoons, and even photographs. You can use the model to generate images for your website, or to generate images for your marketing campaigns and get ideas for your next designs.

Image Enhancer

A part of the ImageCon V3 Model, this model is capable of enhancing the quality of images and making them more visually appealing. The model can be used to enhance the quality of images and resize them to bigger sizes without losing quality.

​
Image Analysis & Classification

The Image Analysis & Classification model is a powerful tool that can be used to analyze and classify images based on a Image Style. A part of the ImageCon V2 Model, and an important part of our Multi Modal approach, this model is capable of analyzing and classifying images based on an Image as an input. The model is trained on a large corpus of images, and can be fine-tuned to analyze and classify images in a specific style or domain. The model can be used to analyze and classify images according to Activity, Emotion, Object, Scene, and many more.

Image Analysis & Classification V2

Designed to analyze the contents of images and detect various labels associated with them. These models have undergone extensive training to identify specific objects, scenes, actions, and concepts within an image. By utilizing these models, you can gain insights into the different elements present in a given photograph.

Face Analysis & Detection V2

Robust face analysis capabilities for images. Detect faces within an image, and obtain valuable information about those faces. This includes the location of detected faces, facial landmarks such as the position of eyes, and attributes such as emotions (e.g., happiness or sadness) and the presence of glasses or face occlusion.

Face Comparison V2

Designed to determine if a face in one image matches a face in another image. This face comparison system takes an input image and predicts whether it matches any face in a provided database or image. The system is built to compare faces irrespective of variations in expression, facial hair, and age.

​
Text Extraction Models

The Text Extraction Model is a highly capable tool designed to extract text from images, webpages, and documents efficiently. These models are trained on extensive datasets consisting of diverse images and documents, making them adaptable for specific styles or domains through fine-tuning. With their capabilities, these models can extract text from various sources such as handwritten notes, printed materials, and even scanned documents. Whether you need to extract text from images, documents, or webpages for your website or utilize it for marketing campaigns and design inspiration, the text extraction model can provide valuable assistance.

Extraction from PDF Files

Machine learning (ML) service that automatically extracts text, handwriting, and data from scanned documents. It goes beyond simple optical character recognition (OCR) to identify, understand, and extract data from forms and tables.

Extraction from Web Pages

AI-powered content extraction algorithms use machine learning and natural language processing techniques to understand the layout and structure of a web page and extract the most relevant and useful content.

Extraction from Images

By leveraging the detected text in images, you can retrieve and display visually similar images that contain the same or similar textual content. This opens up avenues for enhanced search experiences, recommendation systems, and content discovery.

​
Speech Extraction Models

The Speech Extraction Model is a highly capable tool designed to extract text from audio files efficiently. SpeechAI, a state-of-the-art speech recognition model trained on 850K hours of audio data that achieves near human-level performance and robustness across a variety of data.

SpeechAI

The General Purpose Speech Generation Model for all your needs. Capable of handling multiple languages and accents.

​
Content Moderation Models

The Content Moderation Model is a highly capable tool designed to moderate content from images, and text efficiently. These models are trained on extensive datasets consisting of diverse images and documents, making them adaptable for specific styles or domains through fine-tuning. With their capabilities, these models can moderate content from various sources such as handwritten notes, printed materials, and even scanned documents when combined other WorqHat AI Models. Whether you need to moderate content from images, documents, or webpages for your website or utilize it for marketing campaigns and design inspiration, the content moderation model can provide valuable assistance.

Text Content Moderation

The Moderation AI uses LLM-based classifiers to identify inappropriate content, including sexual, violent, hateful, and self-harm promoting content that violates WorqHat’s content policy.

Image Moderation

Effectively utilized in various scenarios such as social media platforms, broadcast media, advertising, and e-commerce, ensuring a safer user experience, providing brand safety assurances to advertisers, and complying with local and global regulations.