⚡️ Our Astronomy Domine (Daria) and Interstellar Overdrive (Misha) shed light on the DeepFloyd IF's architecture and performance at the Weights & Biases MLOps virtual conference, Fully Connected 2023.
IF LARGE TEXT-TO-IMAGE MODELS WERE OPEN-SOURCE, Fully Connected 2023 (YouTube)
Post #375
5.93K
Forwarded from DeepFloyd
YouTube Building The Next Large Model: DeepFloyd LLM + Text-to-Image = IF (Stability AI) *From Fully Connected 2023* Daria Bakshandeava and Misha Konstantinov of DeepFloyd discuss large language modeling for text-image models, with a focus on their soon-to-be open-source, state-of-the-art text-to-image diffusion model.- 👨💻 18
- 🕊 3