Translations:Diffusion Models Are Real-Time Game Engines/83/es: Difference between revisions

Latest revision as of 03:29, 7 September 2024

Information about message (contribute)

This message has no documentation. If you know where or how this message is used, you can help other translators by adding documentation to this message.

Message definition (Diffusion Models Are Real-Time Game Engines)

Diffusion models achieved state-of-the-art results in text-to-image generation (Saharia et al., [https://arxiv.org/html/2408.14837v1#bib.bib27 2022]; Rombach et al., [https://arxiv.org/html/2408.14837v1#bib.bib26 2022]; Ramesh et al., [https://arxiv.org/html/2408.14837v1#bib.bib25 2022]; Podell et al., [https://arxiv.org/html/2408.14837v1#bib.bib23 2023]), a line of work that has also been applied for text-to-video generation tasks (Ho et al., [https://arxiv.org/html/2408.14837v1#bib.bib14 2022]; Blattmann et al., [https://arxiv.org/html/2408.14837v1#bib.bib5 2023b]; [https://arxiv.org/html/2408.14837v1#bib.bib4 a]; Gupta et al., [https://arxiv.org/html/2408.14837v1#bib.bib9 2023]; Girdhar et al., [https://arxiv.org/html/2408.14837v1#bib.bib8 2023]; Bar-Tal et al., [https://arxiv.org/html/2408.14837v1#bib.bib3 2024]). Despite impressive advancements in realism, text adherence, and temporal consistency, video diffusion models remain too slow for real-time applications. Our work extends this line of work and adapts it for real-time generation conditioned autoregressively on a history of past observations and actions.

Los modelos de difusión lograron resultados de estado del arte en la generación de texto a imagen (Saharia et al., 2022; Rombach et al., 2022; Ramesh et al., 2022; Podell et al., 2023), una línea de trabajo que también se ha aplicado a tareas de generación de texto a video (Ho et al., 2022; Blattmann et al., 2023b; a; Gupta et al., 2023; Girdhar et al., 2023; Bar-Tal et al., 2024). A pesar de los impresionantes avances en realismo, adherencia al texto y coherencia temporal, los modelos de difusión de video siguen siendo demasiado lentos para las aplicaciones en tiempo real. Nuestro trabajo amplía esta línea de trabajo y la adapta para la generación en tiempo real condicionada de forma autorregresiva en un historial de observaciones y acciones pasadas.