Google has released a research paper on a new text-to-image generator called Imagen, which combines the power of large transformer language models for text with the capabilities of diffusion models in high-fidelity image generation. “Our key discovery is that generic large language models (e.g. T5), pretrained on text-only corpora, are surprisingly effective at encoding text for image synthesis,” the company said. Simultaneously, Google is introducing DrawBench, a benchmark for text-to-image models it says was used to compare Imagen with other recent technologies including VQGAN+CLIP, latent diffusion models, and OpenAI’s DALL-E 2. Continue reading Google’s Imagen AI Model Makes Advances in Text-to-Image

Researchers from Adobe, the Indian Institute of Technology and Stanford University teamed up to create SieveNet, an AI-powered technology that allows a user to virtually try on clothing. The “image-based virtual try-on” maps the item to the virtual body, retaining its characteristics without creating blurry or bleeding textures. According to banking company Klarna, 29 percent of shoppers want to virtually try on apparel, accessories and cosmetics and 49 percent would like solutions that take their measurements into account. Continue reading AI-Powered App Enables Improved Virtual Apparel Try-Ons