Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis Paper • 2312.03491 • Published Dec 6, 2023 • 34
Terminus XL Collection v-prediction SDXL clone with zero-terminal SNR noise schedule • 8 items • Updated Apr 24 • 6
LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models Paper • 2309.15103 • Published Sep 26, 2023 • 42