Are you ready to increase brand awareness? Consider becoming a sponsor of the AI Impact Tour. Learn more about opportunities here.
As AI continues to penetrate the creative space, creating value as well as concerns among many, six-month-old Pika Labs announced that its text-to-video AI platform, Pika 1.0 , is now available to everyone.
Accessible via the web, Pika 1.0 allows users to generate and edit videos in various styles such as 3D animation, anime or cinema – from simple text prompts.
The decision to launch the tool comes as other players in the AI video space, including Stability AI and Runway, attempt to move forward with their respective offerings to give businesses and individuals a way to easily create video content. Stability recently launched its image-video offering on its development platform.
What to expect from Pika 1.0?
Announced last month, Pika 1.0 comes with an easy-to-use conversational interface (similar to ChatGPT), where a user enters the idea for the video they are considering. Once the prompt is entered, the underlying model will produce the results.
The AI Impact Tour
Access an AI Governance Plan – Request an invitation to the January 10 event.
Pika claims the model can produce a wide range of content, including 3D animations, live action clips and cinematic videos, as well as modify moving objects (like a horse or an outfit) with simple text prompts .
When we tested the platform, it produced these results in about a minute, but the result was inconsistent on several occasions. The 3-second clips resulting from the text prompts were sometimes blurry or out of place, with the subject distorted or blurred. Some results were correct, however, including this rottweiler wearing a Santa hat.
As the tool becomes more widespread and Pika updates the model, we hope these shortcomings will be resolved. However, at this point, what we like about Pika 1.0 is the wide range of customizations the company offers. When producing a video from text, the tool offers a range of options to work with, including a way to adjust frames per second between 8 and 24 and the aspect ratio of the clip. Users can even adjust motion elements including pan, tilt, zoom, and strength of camera movement.
Additionally, when a clip has been produced, users can tweak it further. The template provides options to regenerate with the same prompt, enter a new prompt, or modify what was produced. The edit feature allows you to edit a specific region of the clip (with new objects and props) and extend the canvas to a different aspect ratio. It can also add four extra seconds to the produced clip or improve its quality.
The tool’s editing intelligence is powered by the model’s image-to-video and video-to-video capabilities. If necessary, users can even upload their own photos/videos to bring them to life with these features. Imagine being able to convert a static meme into a cinematic clip.
How to get started with Pika 1.0?
To start generating videos on Pika, users must register through Google or Discord on the company’s dedicated web platform. Once the account is created, the company places the user on a waiting list. However, the wait is not that long.
A few minutes after registration, Pika Labs sends an email confirming full access to Pika 1.0.
“Start using it to create videos on command. Unlimited access is always free, so don’t hesitate,” the company notes in the email. Users can then launch the platform and start describing their stories to produce video content in varying styles.
“We know that creating high-quality content is difficult and expensive, and we designed Pika to give everyone, from home users to film professionals, the tools to bring high-quality videos to life. Our vision is to empower everyone to become the director of their story and bring out the creator in each of us,” Demi Guo, the company’s CEO, said in a statement last month.
Growing competition for AI videos
So far, Pika has raised $55 million at a valuation of nearly $200 million. However, the company is not alone in the AI video space. It competes with well-known and heavily funded players like Adobe, Runway and Stability AI.
Stability recently added its Stable Video Diffusion model to its developer AI platform; Runway is already used to add movement to memes that generate virality, while Adobe is experimenting with features like video scaling and object editing for its Creative Cloud products. It also reportedly acquired Rephrase AI to improve its video generation game.
VentureBeat’s mission is to be a digital town square for technical decision-makers to gain knowledge about technology and transformative business transactions. Discover our Briefings.
Gn En tech