Skip to main content

How to make AI videos from just text

how to make ai videos pika pikathumb
Pika

Pika is an incredible artificial intelligence tool that takes text and images and creates impressive, believable, and often beautiful multi-second video clips. Like any generative AI tool, though, Pika Labs requires the right kind of prompt to make the most of it. Here, we'll show you how to get set up using Pika and how to use it to make you amazing videos.

Difficulty

Easy

Duration

15 minutes

Sign up to Pika

Pika Labs used to have a waiting list, but that's no longer the case. Navigate to the Pika website and sign in with either a Google account or Discord account. With the Discord account, you can access the Pika Discord server, which has its own bot and additional features, but the Google account will still give you full access to the free online tool.

Introducing Pika 1.0, An Idea-to-Video Platform

How to use Pika

Using Pika is as straightforward as typing your prompt into the text box at the bottom of the main page and pressing the Enter key. The prompt and the options you select can have a big impact on what the tool ends up outputting back to you.

You can also select the Image or video button and attach an image or video to provide additional context or data for the AI to use.

The prompt can take a minute or two to generate in busy times, so be sure to wait for it to complete.

Prompt Tips

  • Use a basic prompt structure: The most effective prompt structures are simple and direct. Give Pika a subject, shot type, description of the scene, and a lighting effect. You can also choose a style like anime, cinematic, or pixel art.
  • Use an image you generated in a separate text-to-image generator: Midjourney and Dall-E are great tools for creating a base model for Pika to animate. Try importing something you made there. Need help? Check out our guide on how to use Dall-E.
  • Use negative prompts: If you find Pika keeps outputting certain video types you don't like, or they have something in them you would rather wasn't there, try using the negative prompts in the Parameters menu (the two lines with circles at opposite ends). You can input things like, "low resolution," or "morphing," or "blurry background," depending on what you're looking for.
Choosing aspect ratio in Pika.
Jon Martindale / DigitalTrends

How to change aspect ratio in Pika

Whether you're creating a video from scratch or want to use Pika's AI to alter an existing video, you can adjust the aspect ratio with just a few clicks.

Step 1: Write or upload your prompt, but before you hit Enter, select the Video options icon -- it looks like the four disconnected corners of a square.

Step 2: Select the aspect ratio that you want the output video to be in. You can choose from 16:9, 9:16, 1:1, 4:5, and a few other options.

This is also where you can adjust the frames per second (fps), if you want to.

Step 3: When ready, close the menu and hit the Enter key to upload your prompt.

Choosing camera controls in Pika.
Jon Martindale / DigitalTrends

How to use motion controls in Pika

Pika responds well to prompts related to filmmaking and cinematography, but there's a handy tool to make it easy to have the video pan, tilt, zoom, or rotate in a direction you want. You can also specify the strength of motion within the scene.

Step 1: After you've finished inputting your prompt, but before you submit it, select the Motion control menu icon under the prompt area. It looks like a classic camera icon.

Step 2: Choose from the menu options how you want the scene in the eventual video to be captured. Camera panning and tilting can help make a video look far more cinematic or realistic.

Step 3: When ready, close the menu and hit the Enter key to upload your prompt.

Adding 4s to a Pika video.
Jon Martindale / DigitalTrends

How to make Pika videos longer

The one downside to Pika's videos is that they're frustratingly short. Although you could probably cut together a short video using t3-second clips, that's a lot of cuts. You can make Pika videos longer, though. Here's how.

Step 1: Choose your favorite video that Pika has generated or altered for you. Select the three-dot menu icon under the video, and select Add 4s. This will add your prompt to the input box, along with your video as a base and a command to add an additional four seconds.

Step 2: Make any further adjustments to your prompt, then select the input button or press Enter on your keyboard.

Like most image generators, Pika is a little random and quite temperamental. While there are some basic tips for improving your time with Pika, it's all a little bit of a guessing game. Play around with the options or try prompting the tool with the same text but in a different order -- it can all produce widely different effects.

Want some help? ChatGPT is great at suggesting ways to better talk to other AI.

Jon Martindale
Jon Martindale is the Evergreen Coordinator for Computing, overseeing a team of writers addressing all the latest how to…
Nvidia just released an open-source LLM to rival GPT-4
Nvidia CEO Jensen in front of a background.

Nvidia, which builds some of the most highly sought-after GPUs in the AI industry, has announced that it has released an open-source large language model that reportedly performs on par with leading proprietary models from OpenAI, Anthropic, Meta, and Google.

The company introduced its new NVLM 1.0 family in a recently released white paper, and it's spearheaded by the 72 billion-parameter NVLM-D-72B model. “We introduce NVLM 1.0, a family of frontier-class multimodal large language models that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary models (e.g., GPT-4o) and open-access models,” the researchers wrote.

Read more
Microsoft is finally making Copilot+ laptops useful for AI
Microsoft Surface Pro 11 front view in tablet mode.

Microsoft's Copilot+ PC initiative has been a smash hit, with many of them landing among the best laptops, but not for the AI hardware inside. Now, finally, Microsoft is putting the neural processing unit (NPU) inside Copilot+ PCs to good use. Starting today and going throughout the next two months, Microsoft will begin rolling out the 24H2 update for all Windows 11 PCs, and in the process, unlock several features for Copilot+ PCs, including the highly controversial Recall.

Recall is definitely the star of the show here, which will start showing up on Copilot+ laptops with a Snapdragon X chipset throughout October. Last week, Microsoft laid the groundwork for the release of Recall, detailing the security architecture of the feature and addressing some major criticisms of it. Now, for example, Recall is turned off instead of on by default. Microsoft is also allowing users to filter websites and giving users more control over their snapshots, including deleting them all.

Read more
Meta and Google made AI news this week. Here were the biggest announcements
Ray-Ban Meta Smart Glasses will be available in clear frames.

From Meta's AI-empowered AR glasses to its new Natural Voice Interactions feature to Google's AlphaChip breakthrough and ChromaLock's chatbot-on-a-graphing calculator mod, this week has been packed with jaw-dropping developments in the AI space. Here are a few of the biggest headlines.

Google taught an AI to design computer chips
Deciding how and where all the bits and bobs go into today's leading-edge computer chips is a massive undertaking, often requiring agonizingly precise work before fabrication can even begin. Or it did, at least, before Google released its AlphaChip AI this week. Similar to AlphaFold, which generates potential protein structures for drug discovery, AlphaChip uses reinforcement learning to generate new chip designs in a matter of hours, rather than months. The company has reportedly been using the AI to design layouts for the past three generations of Google’s Tensor Processing Units (TPUs), and is now sharing the technology with companies like MediaTek, which builds chipsets for mobile phones and other handheld devices.

Read more