Home-grown AI unicorn Fractal has developed India’s first text-to-image diffusion model Kalaido.ai capable of generating high quality images from text prompts in English and 17 Indian languages including Hindi, Kannada, Tamil, Telugu and Sanskrit.

“Kalaido, which was trained on a public dataset of 70 million images, has shown 40% higher efficiency in producing rich detail images than our global competitors during internal trials,” Fractal CEO and co-founder Srikanth Velamakanni told ET.

Elevate Your Tech Prowess with High-Value Skill Courses

Offering CollegeCourseWebsite
MITMIT Technology Leadership and InnovationVisit
IIM LucknowIIML Executive Programme in FinTech, Banking & Applied Risk ManagementVisit
IIM KozhikodeIIMK Advanced Data Science For ManagersVisit

Fractal joins the AI diffusion model race with heavyweights such as Open AI’s Dall-E, Stability AI’s Stable Diffusion, Midjourney and Runway etc.

Kalaido, however, is the first Indic language image model which can not only generate images but also enhance user prompts automatically to suggest improved descriptions, cause 2X reduction in time spent on iteration and maximize creative output.

Also read | Ola founder Bhavish Aggarwal’s Krutrim AI turns unicorn with $50 million funding from Matrix, others

The model which is currently available in beta version is set to be launched by end of this month for free-to-use. Albeit, it’s software code and weights won’t be open-sourced, Velamakanni said.

Discover the stories of your interest


“Kalaido was built on a “efficient training” approach and is therefore capable of producing rich detail images in fewer steps, saving time, GPU costs and reducing carbon footprint,” the CEO said adding that the tool will be resourceful in industries such as advertising, graphic designing, social media marketing, and edtech.For instance, for a global soup brand, Kalaido has led to a 79% reduction in the cost of generating an image which would otherwise cost around Euro 5000.

“For a multinational consumer brand, we used neuroscience-based prompt strategy to understand decision-making in the brain and combined that with brand guidelines. And finally we generated a 100-word prompt for text-to-image model which is then fed to Kalaido for generating images,” he said.

The model can be fine-tuned to abide by brand guidelines, he added.

Similarly, for an edtech company, Kalaido has helped to generate 9-hour long course content with just 2 hours of actual shooting, while the rest was generated through images.

About practicing safeguards in publishing AI image generation tools, Velamakanni said that the company is exercising extreme caution like other global leaders.

“We understand that a free-to-use tool like Kalaido can be misused for certain malpractices, especially deepfakes. For this reason, we are watermarking all images with kalaido.ai currently. We also have AI capabilities which decline to process text prompts which have the potential to cause harm and we will improve these capabilities with time” he said.

Mumbai-based AI analytics startup Fractal, backed by TPG Capital, reached a valuation of $2 billion in 2022 when the latter infused $360 million into the company.

Amongst other generative AI capabilities, Fractal has launched FlyFish powering conversational commerce and the Marshal bot which can assist business leaders and C-suite executives in critical thinking. It is an AI Avatar of Marshall Goldsmith – top ten business thinkers in the world and an executive coach.

LEAVE A REPLY

Please enter your comment!
Please enter your name here