Yannic Kilcher Videos (Audio Only) DeepFloyd IF - Pixel-Based Text-to-Image Diffusion (w/ Authors)
Aug 28, 2023
Guests Misha Konstantinov and Daria Bakshandaeva from DeepFloyd discuss their open-source model, IF, which follows Google's implementation of Imagen. They explain the working of the model, its performance in creating realistic images, experiments with text encoders, multilingual content generation, and plans for future releases and collaborations.
Chapters
Transcript
Episode notes
1 2 3 4 5 6 7
Introduction
00:00 • 2min
Text-to-Image Model with Pixel Cascaded Diffusion
01:40 • 10min
Text Encoders and Model Experiments
11:35 • 21min
Generating Cool Images and Multilingual Content
32:43 • 10min
Capabilities and Requirements for Running the Largest Model as a Single Person
42:23 • 2min
Model Release Plans
44:36 • 6min
Future plans and collaboration for Deep Floyd
50:46 • 3min