Recently, diffusion models have been very successful in text-to-image generation. They're generating high-quality images, running faster, and helping us be more creative. But it's still hard to efficiently control generation, especially with conditions that are difficult to describe with text
That's why we're excited to announce MediaPipe diffusion plugins. They let you run controllable text-to-image generation on-device.
Learn more by reading the paper linked below.
Resources:
Read more about on-device diffusion plugins for conditioned text-to-image generation → https://goo.gle/44jkCIl
Watch more episodes of THE DROP → https://goo.gle/3JDTKun
Subscribe to the Google Research Channel → https://goo.gle/GoogleResearch
#GoogleResearch #GoogleAI