With ChatGPT now with us officially for a year, as of November 30, 2022, fast forward a year, and the generative AI space has grown tremendously. There has been a LOT of work done in the space of text to imagery, and also text to video, and this new Pika.art development is really exciting.
First, let’s take a look at Pika.art’s demo video, which I’ve embedded immediately below:
Here’s what Pika says in its about us page – my description of the video is below this announcement.
Video is at the heart of entertainment, yet the process of making high-quality videos to date is still complicated and resource-intensive. When we started Pika six months ago, we wanted to push the boundaries of technology and design a future interface of video making that is effortless and accessible to everyone. Since then, we’re proud to have grown the Pika community to half a million users, who are generating millions of videos per week.
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. Today, we reached a milestone that brings us closer to our vision. We are thrilled to unveil Pika 1.0, a major product upgrade that includes a new AI model capable of generating and editing videos in diverse styles such as3D animation, anime, cartoon and cinematic, and a new web experience that makes it easier to use. You can join the waitlist for Pika 1.0 at https://pika.art.
We are also excited to announce our fundraising milestones: we have raised $55 million, initiated with pre-seed and seed rounds led by Nat Friedman & Daniel Gross, and our Series A round led by Lightspeed Venture Partners. Our investors also include Elad Gil, Adam D’Angelo (Founder and CEO of Quora), Zach (Co-Founder of Ramp), Andrej Karpathy, Clem Delangue (Co-Founder and CEO of Hugging Face and Partner at Factorial Capital), Craig Kallman (CEO of Atlantic Records), Alex Chung (Co-Founder of Giphy), Aravind Srinivas (CEO of Perplexity), Vipul Ved Prakash (CEO of Together), Mateusz Staniszewski (CEO of ElevenLabs), and Keith Peiris (CEO of Tome), as well as venture firms such as Homebrew, Conviction Partners, SV Angel, and Ben’s Bites, alongside many other esteemed industry leaders and AI experts.
We are humbled to reach this milestone, and we couldn’t be happier to share Pika 1.0 with everyone. We would also like to thank our academic advisors at Stanford and Harvard, including Chris Manning, Ron Fedkiw, Stefano Ermon, and Alexander Rush, who have continued to support us as company academic advisors. We’re also grateful for our users, investors, advisors and all the supporters along the way.
As a small and dynamic team, we’re looking for passionate and driven individuals to join us on this exciting journey to push the limits of AI and creativity. You can explore our open roles here.
To stay up to date on the latest about Pika, follow @pika_labs on X, join our Discord community and access our beta product here, and join the waitlist for the new Pika 1.0 at https://pika.art.
Here’s my description of what’s seen in the must-see video above:
The video starts off with “Elon Musk in a space suit, 3D animation” and we see just that. This is then followed by a visual of a cow in space, audibly mooing. We see a racoon in space, a with sunglasses and a backpack, and the text “A new kind of movie magic”.
When then see a montage of food, monsters and a racoon at a food truck, and we’re told that we can “start just by typing” – and we see the words “robot walking” being typed, and the “generate button” being pressed.
We then see a large robot walking in the suburbs.
Next the words “blonde girl in a candy shop, gaming style” is typed, and we see just that, and it’s animated – it’s not just a photo.
After this is the face of a pig, except it is clearly wearing a white shirt and black jacket, with the text “a pig in a tuxedo, photorealistic style.”
Then we see the prompt “A girl smiling in a forest, anime style” and it looks a little like a female version of the boy from The Jungle Book, and this is immediately followed up with the prompt “cinematic, a dog and a cat in a boxing ring”, and we see vision of that appearing before our eyes, with the dog woofing.
Then we’re told “or just drop in image”, and we see an image of The Last Supper, with Jesus and his disciples. The text is typed to have this image, but have the “dolly out” which means the video camera that would be there in real life is being moved backwards to show a wider image – and we see an animated version of just that appearing.
Then the text “an even a video” appears, and we see a version of the famous horse galloping video that was one of the first things ever captured as a moving picture over 100 years ago.
In the text box, we see “a cowboy riding a horse in the desert” typed, and the generate button pressed, and suddenly the crude animated horse and rider turns into just what was asked – a cowboy riding a horse in the desert.
It then turns into a boy riding a white horse at hight, and then a knight in shining armour riding a reddish brown horse in the forest.
Then the image turns into a pixellated 8-bit graphic of a jockey riding a race horse.
The qusetion “Need to expand your video’s canvas?” Appears, and the button “expand” is shown on screen, and tapped, with the options to expand into the various screen ratios of 16:9, 9:16, 1:1 or 5:2, with 1:1 tapped and suddenly the video expands, and the missing bits are automatically generated on the fly, which is truly remarkable.
The buttons 9:16 and then 16:9 are tapped, the video size changes, and the video is again automatically generated, even though that video was never captured. It really is something you need to see for yourself to be visually blown away.
So, in answer to the question as to if you want to expand your video’s canvas, the text “no problem” appears on the screen.
Then you’re asked: “Want to change something?”. Here we see a woman in a sparkly red crop top with sunglasses walking in what looks like a Los Angeles street with tall palm trees in the background.
A text box appears, and the words “denim crop top” are typed, and as soon as the “generate” button is tapped, the red crop top instantly changes into a blue one, naturally with denim material.
Then the crop top is changed into a black leather outfit.
Then we see what I think is a Macaque monkey, and the words “cool sunglasses” are typed in, and of course, these appear in the right spot on the monkey’s face, one the mouse draws a quick rectangle around its eyes.
Then the sunglasses turn into another style.
The words “Get It” appear on the screen, with the words “Just type it”, and the name of the tool, Pika, appears, with the video ending with the words “Pika.Art”.
