Lecture 18 – Diffusion Developments
Notes
Recording
Readings
- An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion, Gal et al., ICLR 2023
- DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation, Ruiz et al., CVPR 2023
- Adding Conditional Control to Text-to-Image Diffusion Models, Zhang et al., 2023
Related Links
- LoRA: Low-Rank Adaptation of Large Language Models, Hu et al., ICLR 2022
- Anime Rock Paper Scissors, Corridor Crew
- Anime Rock Paper Scissors behind the scenes
- Harry Potter by Balenciaga
- Balenciaga how-to