A video generated using OpenAI's unreleased, open source Sora text-to-video model, using the prompt: A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse. She wears sunglasses and red lipstick. She walks confidently and casually. The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about.
A text-to-video model is a machine learning model that uses a natural language description as input to produce a video relevant to the input text.[1] Advancements during the 2020s in the generation of high-quality, text-conditioned videos have largely been driven by the development of video diffusion models.[2]
There are different models, including open source models. Chinese-language input[3] CogVideo is the earliest text-to-video model "of 9.4 billion parameters" to be developed, with its demo version of open source codes first presented on GitHub in 2022.[4] That year, Meta Platforms released a partial text-to-video model called "Make-A-Video",[5][6][7] and Google's Brain (later Google DeepMind) introduced Imagen Video, a text-to-video model with 3D U-Net.[8][9][10][11][12]
In March 2023, a research paper by Alibaba was published that applied many of the principles found in latent image diffusion models to video generation.[13][14] The following year, Alibaba released ModelScope.[15] Services like Kaiber and Reemix subsequently adopted similar approaches to video generation in their respective products.[citation needed]
Matthias Niessner and Lourdes Agapito at AI company Synthesia work on developing 3D neural rendering techniques that can synthesise realistic video by using 2D and 3D neural representations of shape, appearances, and motion for controllable video synthesis of avatars.[16] In June 2024, Luma Labs launched its Dream Machine video tool.[17][18] That same month,[19]Kuaishou extended its Kling AI text-to-video model to international users. In July 2024, TikTok owner ByteDance released Jimeng AI in China, through its subsidiary, Faceu Technology.[20]
AI chatbot Grok added a text-to-video feature on August 13, 2024 that creates and posts generated video on the X platform. Social media sites were quickly flooded with fabricated images of Donald Trump, Kamala Harris, X site owner Elon Musk, and others, including in false, disturbing depictions, such as participating in 9/11 attacks.[21]
Alternative approaches to text-to-video models include[22] Google's Phenaki, Hour One, Colossyan,[23]Runway's Gen-3 Alpha,[24][25] and OpenAI's unreleased (as at August 2024) Sora,[26] available only to alpha testers.[27]
^Artificial Intelligence Index Report 2023(PDF) (Report). Stanford Institute for Human-Centered Artificial Intelligence. p. 98. Multiple high quality text-to-video models, AI systems that can generate video clips from prompted text, were released in 2022.