Artificial Intelligence: Google Announces Imagen, Its Text-To-Video Tool

It’s Google’s reply to Meta’s video generating tool.

Google has announced Imagen Video, an AI video generator that can create 1280×768 HD video at 24 fps from written text. Though it’s still in research mode, it seems to be a quick riposte to Meta’s recently unveiled text-to-video AI tool, Make-A-Video. It also comes within six months of OpenAi’s DALLE-2 text-to-image generator. (ARS TECHNICA)

Here are some examples of Imagen videos generated with the indicated written prompts below each.


An astronaut riding a horse.                          Flying through an intense battle between pirate ships in a stormy ocean.


A Panda Eating Bamboo On a Rock.              View of a castle with fantastically high towers reaching into the clouds in a hilly forest at dawn.

The Imagen system generates a a 16-frame, three-frames-per-second video at 24-by-48-pixel resolution from the input text prompt. In a subsequent “cascade” of steps, it simulates additional frames at higher resolutions, finally producing a 128-frame, 24-frames-per-second video at 720p (1280×768) that is 5.3 seconds in length.

Imagen has some unique abilities, including creating works that are similar to those from famous painters such as Vincent van Gogh, rotating 3D objects without distorting their shape, and various animation styles.

Imagen is what is known as a “diffusion” model, and competitive activity in this area is growing rapidly. Apart form the aforementioned tool from Meta, other rivals include Phenaki and DreamFusion.

The model was trained on a combination of an internal dataset consisting of 14 million video-text pairs and 60 million image-text pairs, and the publicly available LAION-400M image-text dataset.


Google warns in its research paper: “Imagen Video and its frozen T5-XXL text encoder were trained on problematic data… While our internal testing suggests much of explicit and violent content can be filtered out, there still exists social biases and stereotypes which are challenging to detect and filter.”

“We have decided not to release the Imagen Video model or its source code until these concerns are mitigated.”

Related Story: OpenAI Opens Up Beta Version Of DALL-E 2 To Millions On Waitlist

Free Industry News

Subscribe to our free newsletter for updates and news about alternatives investments.

  • This field is for validation purposes and should be left unchanged.


Latest Alternative Investment News
Alternative Investments/ESG: Six New Responsible Funds Flag Off Morgan Stanley’s ETF Platform

Morgan Stanley Investment Management (MSIM) has launched its ETF platform with six Calvert ETFs listed on NYSE Arca. The ETFs feature Calvert’s responsible investing approach and offer access to four…
Artificial Intelligence: MusicLM, A New Generative AI Tool From Google, Creates Music From Text
February 2, 2023     Artificial Intelligence, News

Google (NASDAQ: GOOGL) recently published a research paper on its new AI tool, MusicLM, designed to create music. The tool is based on machine learning and is trained on vast…
Artificial Intelligence: Snap Mulling AR Glasses Powered By Generative AI
February 2, 2023     Artificial Intelligence, News

Snap (NYSE: SNAP), the parent company of Snapchat, has hinted at future AR glasses powered by generative AI technology. CEO Evan Spiegel stated that AI will be critical to the…
Digital Assets: Binance And Mastercard Launch Prepaid Crypto Card In Brazil
February 1, 2023     Digital Assets, News

Binance and Mastercard (NYSE: MA) have jointly launched the Binance Card in Brazil, allowing Binance users in the country to make purchases and pay bills with cryptocurrencies like bitcoin and…