You are on page 1of 9

/ Tech / Reviews / Science / Entertainment / More

ARTIFICIAL INTELLIGENCE / TECH / GOOGLE

Google’s Lumiere brings AI video closer to


real than unreal / Five-second clips generated
with Lumiere show how the AI tools can create
video from a prompt with realistic motion.
By Emilia David, a reporter who covers AI. Prior to joining The Verge, she covered the intersection
between technology, finance, and the economy.
Jan 27, 2024 at 11:30 PM GMT+8 | 22 Comments / 24 New

Lumiere

Google’s new video generation AI model Lumiere uses a new diffusion


model called Space-Time-U-Net, or STUNet, that figures out where
things are in a video (space) and how they simultaneously move and
:
change (time). Ars Technica reports this method lets Lumiere create
the video in one process instead of putting smaller still frames
together.

Lumiere starts with creating a base frame from the prompt. Then, it
uses the STUNet framework to begin approximating where objects
within that frame will move to create more frames that flow into each
other, creating the appearance of seamless motion. Lumiere also
generates 80 frames compared to 25 frames from Stable Video
Diffusion.

Admittedly, I am more of a text reporter than a video person, but the


sizzle reel Google published, along with a pre-print scientific paper,
shows that AI video generation and editing tools have gone from
uncanny valley to near realistic in just a few years. It also establishes
Google’s tech in the space already occupied by competitors like
Runway, Stable Video Diffusion, or Meta’s Emu. Runway, one of the first
mass-market text-to-video platforms, released Runway Gen-2 in March
last year and has started to offer more realistic-looking videos. Runway
videos also have a hard time portraying movement.

Google was kind enough to put clips and prompts on the Lumiere site,
which let me put the same prompts through Runway for comparison.
Here are the results:
:
Google Lumiere-generated video

Runway-generated video

Yes, some of the clips presented have a touch of artificiality, especially


if you look closely at skin texture or if the scene is more atmospheric.
But look at that turtle! It moves like a turtle actually would in water! It
looks like a real turtle! I sent the Lumiere intro video to a friend who is
a professional video editor. While she pointed out that “you can clearly
tell it’s not entirely real,” she thought it was impressive that if I hadn’t
told her it was AI, she would think it was CGI. (She also said: “It’s going
to take my job, isn’t it?”)
:
/ Top Stories

READ MORE

Other models stitch videos together from generated key frames where
the movement already happened (think of drawings in a flip book),
while STUNet lets Lumiere focus on the movement itself based on
where the generated content should be at a given time in the video.

Google has not been a big player in the text-to-video category, but it has
slowly released more advanced AI models and leaned into a more
multimodal focus. Its Gemini large language model will eventually
bring image generation to Bard. Lumiere is not yet available for testing,
but it shows Google’s capability to develop an AI video platform that is
comparable to — and arguably a bit better than — generally available AI
video generators like Runway and Pika. And just a reminder, this was
where Google was with AI video two years ago.
:
Google Imagen clip from 2022 Image: Google

Beyond text-to-video generation, Lumiere will also allow for image-to-


video generation, stylized generation, which lets users make videos in a
specific style, cinemagraphs that animate only a portion of a video, and
inpainting to mask out an area of the video to change the color or
pattern.

Google’s Lumiere paper, though, noted that “there is a risk of misuse for
creating fake or harmful content with our technology, and we believe
that it is crucial to develop and apply tools for detecting biases and
malicious use cases to ensure a safe and fair use.” The paper’s authors
didn’t explain how this can be achieved.

22 COMMENTS (24 NEW)

F E AT U R E D V I D E O S F R O M T H E V E R G E

Which M2 is right for you?


(Apple 2023 buying guide)
:
00:19 17:18

With Apple's recent release of the new 14-inch MacBook Pro, 16-inch
MacBook Pro, and Mac Mini, there are now four different MacBooks and a
desktop that you can buy with M2 chips inside. That's great for Apple fans,
but can also be... intimidating. Becca Farsace, Monica Chin, and Chris
Welch break down each of these M2 devices, what it's good at, and who it's
for. Help us help you.
:
More from this stream From ChatGPT to Google Bard: how AI is
rewriting the internet

OpenAI cures GPT-4 ‘laziness’ with new updates


Jan 26, 2024 at 6:04 AM GMT+8

Google’s Hugging Face deal puts ‘supercomputer’ power behind


open-source AI
Jan 26, 2024 at 2:11 AM GMT+8

Google cancels contract with an AI data firm that’s helped train


Bard
:
Jan 24, 2024 at 7:42 AM GMT+8

Microsoft is building a team to build smaller, cheaper AI models.


Jan 24, 2024 at 6:45 AM GMT+8

SEE AL L 405 STORIES

RECOMMENDED

North Korea [Pics] Most These Steve Jobs Solar roof tiles Canada:
tears down Hilarious Liposuction Left His are the future Stairlift Deals
'reunification' Failures In Patches are Daughter and (Take A Look)
arch, sending Product the Ultimate Billions surprisingly Sponsored | Stairlift
message to Design Ever Solution for Making Her affordable. | Search Ads
Seoul Sponsored | Stubborn Fat The Richest Sponsored | Solar
Sponsored | Nikkei Investing Magazine Sponsored | Heiress Roof Shingles I
Asia Wonder Patch Sponsored | Search Ads.
Investing Magazine

AD
:
T E RM S OF U S E / PRIVACY NOTICE / CO OKIE POL ICY / D O NOT S EL L OR S H ARE MY PERSON AL I NFO / L ICEN S ING FAQ
/ AC CE SS IBI L I TY / PL AT FORM STATU S / HOW WE RATE AND REVI EW PRODUCT S

CONTACT / TIP U S / COM M UN ITY GU IDEL IN ES / ABOUT / ETHICS STAT EME NT

T HE VERGE IS A VOX MEDI A NETWORK

A DVERTISE WITH US / JOBS @ VOX MEDI A

© 2 02 4 VOX M E D I A , L L C . A L L R I G H T S R E S E RV E D
:

You might also like