With the continued penetration of artificial intelligence into the creative field, Pika Labs, which has been established for six months, announced that its text-to-video AI platform, Pika 1.0, is now open to everyone.

Accessible through the web, Pika 1.0 allows users to generate and edit various styles of videos, such as 3D animation, cartoons, or movies, using simple text prompts.

Launching this tool at a time when other participants in the AI video field, including Stability AI and Runway, are trying to gain an advantage by offering products that make it easy for businesses and individuals to create video content. Stability recently launched an image-to-video service on its development platform.

What can we expect from Pika 1.0?

Pika 1.0, announced last month, offers an easy-to-use interface similar to ChatGPT, where users input their ideas for the desired video. After entering the prompts, the underlying model generates the results.

Pika states that the model can generate a wide range of content, including 3D animations, live-action video clips, and movie videos, and can modify moving objects (such as horses or clothing) with simple text prompts.

When we tested the platform, it did generate these results in about a minute, but the output was inconsistent in many cases. The 3-second clips generated from text prompts were sometimes blurry or inappropriate, and the subjects would become distorted or out of focus. However, some results were very accurate.

As this tool becomes mainstream, Pika is updating the model, and it is expected that these discrepancies will be resolved. However, for now, the extensive customization options provided by Pika 1.0 are more favored. When generating videos from text, the tool offers a range of options, including adjusting the frames per second (from 8 to 24) and the aspect ratio of the clips. Users can even adjust the motion elements, including camera panning, tilting, zooming, and the intensity of the motion.

In addition, after the clips are generated, users can further fine-tune them. The model provides options to regenerate using the same prompts, input new prompts, or edit the generated content. The editing feature allows you to modify specific areas of the clips with new objects and props, and expand the canvas to different aspect ratios. It is also possible to add four seconds to the generated clips or enhance their quality.

The editing intelligence of this tool is supported by the model's image-to-video and video-to-video capabilities. If needed, users can even upload their own photos/videos to make them come to life through these features.

How to get started with Pika 1.0?

To start generating videos on Pika, users must register on the company's dedicated web platform through Google or Discord. After creating an account, the company will add users to the waiting list. However, the waiting time is not long.

A few minutes after registration, Pika Labs will send an email confirming full access to Pika 1.0.

"Start using it to create videos on command. Unlimited access is still free, so feel free to unleash your creativity," the company stated in a statement last month.

CEO Demi Guo said, "We have personally experienced how difficult and expensive it is to produce high-quality content. We developed Pika to provide everyone, from home users to film professionals, with a tool to bring high-quality videos to life. Our vision is to enable anyone to become the director of their own story and inspire all of us as creators."

Intensifying competition in the AI video field

So far, Pika has raised $55 million in funding and is valued at nearly $200 million. However, the company is not alone in the AI video field. It competes with well-known and well-funded participants such as Adobe, Runway, and Stability AI.

Stability recently added its Stable Video Diffusion model to its AI platform for developers; Runway has been used to add dynamics to memes, driving viral spread, and Adobe is trying to provide video upgrades and object editing features for its Creative Cloud products. It has also reportedly acquired Rephrase AI to enhance its video generation game.