no code implementations • 17 Nov 2023 • Rohit Girdhar, Mannat Singh, Andrew Brown, Quentin Duval, Samaneh Azadi, Sai Saketh Rambhatla, Akbar Shah, Xi Yin, Devi Parikh, Ishan Misra
We present Emu Video, a text-to-video generation model that factorizes the generation into two steps: first generating an image conditioned on the text, and then generating a video conditioned on the text and the generated image.
no code implementations • ICCV 2023 • Samaneh Azadi, Akbar Shah, Thomas Hayes, Devi Parikh, Sonal Gupta
However, existing approaches are limited by their reliance on relatively small-scale motion capture data, leading to poor performance on more diverse, in-the-wild prompts.
Ranked #20 on Motion Synthesis on HumanML3D
no code implementations • 14 Apr 2023 • Samaneh Azadi, Thomas Hayes, Akbar Shah, Guan Pang, Devi Parikh, Sonal Gupta
Recent large-scale text-to-image generation models have made significant improvements in the quality, realism, and diversity of the synthesized images and enable users to control the created content through language.