Uploaded December 2022 | Updated November 2026, 2 hours ago
Over the last 6 months text to image models such as DallE-2, ImageGen, and StableDiffusion have taken off. These models can achieve previously unfathomable levels of photorealism, illustrate entirely new images from a single text prompt, and even paint your favorite animal in the art style of Picasso. The potential of these models is nearly limitless. This talk walks through enabling diffusion models to generate novel yet coherent images, explores some advanced uses of text to image models, and lastly shows you how to get started with generating images using KerasCV, the most optimized implementation of StableDiffusion available to date.
Speaker: Divyashree Sreepathihalli
Resources:
(Demo) American Pie Music Video by KerasCV+StableDiffusion → https://goo.gle/3YapOff
High-performance image generation using Stable Diffusion in KerasCV → https://goo.gle/3j4ZFOL
A walk through latent space with Stable Diffusion → https://goo.gle/3BDSd3M
Teach StableDiffusion new concepts via Textual Inversion → https://goo.gle/3FvPni7
Watch more:
Watch all the Women in ML Symposium 2022 Sessions → https://goo.gle/WiML22-all
Subscribe to the TensorFlow channel → https://goo.gle/TensorFlow
#WIMLsymposium
Over the last 6 months text to image models such as DallE-2, ImageGen, and StableDiffusion have taken off. These models can achieve previously unfathomable levels of photorealism, illustrate entirely new images from a single text prompt, and even paint your favorite animal in the art style of Picasso. The potential of these models is nearly limitless. This talk walks through enabling diffusion models to generate novel yet coherent images, explores some advanced uses of text to image models, and lastly shows you how to get started with generating images using KerasCV, the most optimized implementation of StableDiffusion available to date.
Speaker: Divyashree Sreepathihalli
Resources:
(Demo) American Pie Music Video by KerasCV+StableDiffusion → https://goo.gle/3YapOff
High-performance image generation using Stable Diffusion in KerasCV → https://goo.gle/3j4ZFOL
A walk through latent space with Stable Diffusion → https://goo.gle/3BDSd3M
Teach StableDiffusion new concepts via Textual Inversion → https://goo.gle/3FvPni7
Watch more:
Watch all the Women in ML Symposium 2022 Sessions → https://goo.gle/WiML22-all
Subscribe to the TensorFlow channel → https://goo.gle/TensorFlow
#WIMLsymposium







![Apply responsible AI principles when building remote sensing datasets
Learn how to apply responsible AI frameworks while making decisions related to datasets and coding with large-scale social benefit in mind. Walk through a version of the developer tutorial, “Hello [Dynamic] World,” and learn how to use a new dataset using Google Earth Engine data responsibly. Presented in collaboration with Google’s Geo for Good team.
Speakers: Unni Nair, Darryl-Mason Robinson
Watch more:
All Google I/O 2022 Sessions → https://goo.gle/IO22_AllSessions
ML/AI at I/O 2022 playlist → https://goo.gle/IO22_ML-AI
All Google I/O 2022 workshops → https://goo.gle/IO22_Workshops
Building Products for Good: A Hands on Workshop → https://goo.gle/39ihW68
Subscribe to TensorFlow → https://goo.gle/TensorFlow
#GoogleIO Apply responsible AI principles when building remote sensing datasets](https://i.ytimg.com/vi/sH8jzyCrSqw/mqdefault.jpg)


