#67 Imagen: Text-to-Image Diffusion Models

Imagen: Text-to-Image Diffusion Models

We present Imagen, a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding. Imagen builds on the power of large transformer language models in understanding text and hinges on the strength of diffusion models in high-fidelity image generation.

Creativity requires solitude

If you go deeply into solitude, it will grow clearer to you that it’s not something you choose to do or not to do. Humans are fundamentally solitary. That is our nature.

Peloton CEO thinks losing $1.2 billion is ‘substantial progress’

Peloton reported a $1.2 billion loss in its Q4 2022 earnings, sending its stock plummeting 13 percent. Despite predicting further losses, CEO Barry McCarthy says that the company’s restructuring plan is on track for success.

SpaceX, T-Mobile to Connect Satellites to Cellphones in Remote Areas

Elon Musk unveiled a plan to use the rocket company’s satellites to provide connections to T-Mobile cellphones across the U.S., including in remote areas with no current wireless service.

Why the Apple M2 Pro processor will be even better than expected

Multiple sources say the Apple’s upcoming M2 Pro chip will be made with an enhanced manufacturing process that wasn't yet available for the recently

newsletters

Would you like to become a sponsor and advertise in one of the issues? Check out our media kit and get in touch.