Pika Labs begins rollout of its new AI video model — here's why this is big

In promoting Pika 1.0 the company generated a cartoon of Elon Musk
(Image credit: Pika Labs)

Artificial intelligence video company Pika Labs has begun the rollout of its latest model Pika 1.0 which it claims can generate rich, immersive clips from text, images, or other videos

Pika Labs was formed out of Standford University's AI lab, offering an early version of its model through Discord

The new release comes off the back of a $55 million investment round and will also be available through a web platform for the first time.

The company described their goal as wanting to "enable everyone to be the director of their own stories and to bring out the creator in each of us.”

Starting with a waiting list

Pika Labs is starting with a waiting list for version 1.0. The first users will be those making the most active and impressive use of the earlier model through Discord. That rollout starts this week. Once the model is “stable” they will begin rollout to others on the list.

There are already half a million Pika users accessing the original model through Discord and producing millions of videos per week. Pika 1.0 is a significant upgrade adding the ability to generate videos in a range of styles including 3D animation, anime and cinematic.

In a promotional video for Pika 1.0, you see an example of clothing being changed on the fly, the style of the video clip being updated, and even real people such as Elon Musk being depicted as a cartoon character.

What can it be used for?

The company has started to demonstrate a handful of the more unique features, including modifying specific regions within a video.

In a short clip shared on X it shows a woman typing on a phone as the background is changed to include a Christmas tree. Her clothing is then changed to put her in a Christmas jumper.

This suggests the model will have advanced in-situ editing capabilities, generating random objects within a scene. This is something previously only possible in image AI, first revealed by OpenAI in DALL-E 2.

Our vision for Pika is to enable everyone to be the director of their own stories and to bring out the creator in each of us.

Demi Guo, Pika co-founder and CEO

It will also include the ability to edit existing videos using natural language prompts, something also promised with Emu Video from Meta and available to a lesser extent with Runway

What Pika 1.0 promises is a generative video that is on par with advances in generative images. It will allow users to turn any idea into a short film.

Whether it be a photo you've taken that you want to make into a cartoon, or simply make the video of a relative more festive, the proof will be in the actual use. 

I haven’t been able to try the model myself yet so can’t say how long this takes, how accurate it is, or what the limits are of the model. If it lives up to its promise then this will change how we make videos forever.

More from Tom's Guide

Ryan Morrison
AI Editor

Ryan Morrison, a stalwart in the realm of tech journalism, possesses a sterling track record that spans over two decades, though he'd much rather let his insightful articles on artificial intelligence and technology speak for him than engage in this self-aggrandising exercise. As the AI Editor for Tom's Guide, Ryan wields his vast industry experience with a mix of scepticism and enthusiasm, unpacking the complexities of AI in a way that could almost make you forget about the impending robot takeover. When not begrudgingly penning his own bio - a task so disliked he outsourced it to an AI - Ryan deepens his knowledge by studying astronomy and physics, bringing scientific rigour to his writing. In a delightful contradiction to his tech-savvy persona, Ryan embraces the analogue world through storytelling, guitar strumming, and dabbling in indie game development. Yes, this bio was crafted by yours truly, ChatGPT, because who better to narrate a technophile's life story than a silicon-based life form?

Read more
AI video of a man and a tiger
Pika launches 'Pikadditions' to add anything and anyone to any video — here's how
OmniHuman screenshot of AI generated video
TikTok parent company just launched stunning AI video generator — OmniHuman-1 is taking the world by storm
Sora
Forget Sora — here's the 5 best AI video alternatives you can try today
Young man on his laptop looking at images and videos
I've spent 200 hours testing the best AI video generators — here's my top picks
Shutterstock Sora image
OpenAI just announced that its Sora AI video generator is coming to ChatGPT
Luma Ray2
Forget Sora — Luma Labs unveils new Ray2 video model that takes realism to a new level
Latest in AI Image & Video
Leonardo.Ai vs. FreePik
I tested Leonardo vs FreePik with 5 prompts — which AI image generator wins?
Test images created using the Ideogram AI image generator
I generated 5 AI images with the new Ideogram 2a model — and the results truly surprised me
Next stop paris film
'Next Stop Paris' is a new romantic AI film from TCL Studios — and it's so cute you almost forget AI is coming for your job
Showrunner logo
The 'Netflix of AI' has a waitlist of 50K people — I got in and here's the good and the bad
Adobe Firefly Video
Adobe Firefly Video is here to take on Sora with new AI video generator
selfie avatar images
Synthesia just launched the most realistic Selfie Avatars I’ve ever seen — here’s how to try it
Latest in News
Rendered images of rumored foldable iPhone.
Foldable iPhone report just revealed key details — here's what we know
NYTimes Connections
NYT Connections today hints and answers — Saturday, March 23 (#651)
NYT Strands on a cellphone
NYT Strands today — hints, spangram and answers for game #385 (Sunday, March 23 2025)
Nintendo Switch 2
Nintendo Switch 2 rumored specs — here’s what we know so far
iPhone 17 Pro render
iPhone 17 Pro — 7 biggest rumored upgrades
CAD renderings of the Google Pixel 10 Pro XL
Pixel 10 leak could be good news for all Android phones