We're excited to introduce StyleDrop, a model that allows a significantly higher level of stylized text-to-image synthesis. Instead of seeking text prompts to describe the style, StyleDrop uses as few as one image to describe the style for text-to-image generation.
Resources: Read more about StyleDrop→ https://goo.gle/3TmaVGK
Subscribe to the Google Research Channel → https://goo.gle/GoogleResearch
#GoogleResearch #GoogleAI