Pika 2.0: A Game-Changer in AI Video Generation Challenges OpenAI's Sora

Pika 2 AI video generator is completely free for the next 5 days -- here's how to try it

Pika Labs is making its flagship Pika 2.0 AI video model available for free for the next few days to give people the chance to put one of the best AI video generators to the test. The "4-day Free-For-All" is a great chance to try out a model I personally think is better than OpenAI's recently unveiled Sora. Its powerhouse feature is the ability to give it an image or multiple images and use them to steer the video creation. This did lead to a significant slowdown in time to generate a video as the servers were over-taxed, but Pika confirmed it was adding new GPUs to meet demand. In the meantime:" Jobs will be prioritized based on subscription tiers, with higher-tier paid plans receiving priority over lower-tier plans." The quickest way to test Pika 2.0 is through the templates created by the team. These allow you to place yourself or someone else in different situations. Pika 2.0 is free until December 22 for all users, and those with a Pro subscription will have their credits frozen in place, as well as priority generations. The AI video lab is also removing all watermarks for Pro subscribers so they can share the clips they generate without branding it as Pika. I spend a lot of time generating videos in different AI products and so far Pika Labs Ingredients is my favorite feature. It solves one of the biggest problems in AI content -- character consistency. The model does a brilliant job of including multiple image elements within the video as well as creating camera movements during the 5 second clip. As its currently free, it is worth spending a few minutes crafting a handful of prompts and putting it to the test. The fact they are making it available for free also shows the confidence they have in how good it is to use.

I just Pika 2 to the test and it's the best AI video generator yet -- and better than Sora

Pika Labs unveiled version 2 of its powerful AI video model last week, bringing with it not just improved motion and realism but also a suite of tools that make it one of the best platforms of its type that I've tried during my time covering generative AI. No stranger to implementing features aimed at making the process of creating AI videos easier, the new features in Pika 2 include adding "ingredients" into the mix to create videos that more closely match your ideas, templates with pre-built structures, and more Pikaffects. Pikaffects was the AI lab's first foray into this type of improved controllability and saw companies like Fenty and Balenciaga, as well as celebrities and individuals, share videos of products, landmarks, and objects being squished, exploded, and blown up. On the surface, this might make it sound like Pika Labs is using tricks and gimmicks to disguise a lack of power in its underlying model, but nothing could be further from the truth. In tests I ran over the weekend, even without those features, Pika-generated videos are comparable with the best models on the scene, including Kling, MiniMax, Runway, and even Sora. Running tests on Pika 2.0 is slightly different from how I'd approach another model. Usually, when I put AI video tools to the test, I create a series of prompts -- some with images and some without -- and fire away. However, a lot of Pika's power comes from these additional features. I decided to start by seeing how well it handled a simple image-to-video prompt and then a text-to-video prompt. I gave it an image generated in Midjourney with a simple descriptive prompt and then used the same prompt I'd used in Midjourney to see how well Pika could create the visuals. My favorite test prompt for AI video is: "A dog wearing sunglasses traveling on a train." This is because most models handle it fairly well but interpret it in different ways. It also requires the model to create a realistic-looking dog with sunglasses -- something unusual. On top of that, it has to generate accurate rapid motion outside of the window while keeping it still inside. Unlike Sora or Kling, Pika kept the dog static, sitting on the seat. It also generated a second shot within the five-second video, zooming in on the dog's face to show off those sunglasses. It didn't do as well with a straight image-to-video prompt using a Midjourney picture, but when I tried the same prompt while using the image as an ingredient instead of the prompt, it worked significantly better. I wrote an article a while ago where I used FreePic's consistent character features to fine-tune the model with pictures of myself. I was able to use this to put myself in various situations by using image-to-video models, so I decided to try this out with Pika Labs 2.0. I started with a picture I generated of myself standing on a 1950s-style US high street with a stereotypical UFO visible in the background. I'm in a full suit, ready for action, and I gave it to Pika 2.0 as part of an ingredient in the scene. I wasn't sure how it would interpret it or whether it would just take my likeness while ignoring the rest of the visuals. The model did a brilliant job, creating two camera movements -- first focusing on me and then zooming out for a wide shot that captured the moving UFO. It managed to keep multiple individual elements moving while retaining the aesthetic of the image throughout the short video clip. I then tried something more complex, giving it a picture of AI-generated me against a white background (who needs to pose for photos when you can generate them?) and a generated image of the interior of a potential Mars base. I gave it the two images as ingredients along with the prompt "working on Mars." It created a video of me smiling and walking around. I then gave it an image of a potential clothing item that might be worn by Mars settlers, but the model interpreted it as a robot and gave the suit a head. It still looked cool, though. Finally, I decided to see how well it handled one of my first AI video prompts: "A cat on the moon wearing a spacesuit with Earthrise in the background." This is something all AI video models used to fail at miserably, and most image models also struggled with. First, I generated an image in Ideogram using that prompt. It's now one of my all-time favourite images and one I plan to print as a poster. I then gave it to Pika 2.0 as an ingredient for AI video generation with no additional prompt. It came out looking like a studio ident for a new movie. I tried the same prompt with text-to-video, and it didn't work as well, giving us a second super-Earth in the background, but it's still better than it used to be. Pika 2.0 isn't just a significant upgrade on the previous generation model, it's catapulted the AI video lab into prime position as one of the best platforms on the market. Last week when Sora was first announced I wrote a guide to best Sora alternatives and left Pika off the list. While the 1.5 model was good, especially when used with Pikaffects, it wasn't as good as the alternatives. Now I feel like I need to write a best alternative to Pika guide as in my view it's better than Sora. Competition aside, I think its amazing how far AI video has come in less than a year, going from 2 seconds of barely moving mush, to content resembling something actually filmed with a real camera -- and with near total control over output.

Pika challenges OpenAI and Sora with new AI video generator features

Pika 2.0 offers a contrast to OpenAI's Sora by aiming at individuals rather than big studios AI video creator Pika Labs is metaphorically elbowing OpenAI and Sora for some of the limelight with a new version of its platform. Pika 2.0 comes with a suite of new features for making custom videos with AI and arrives only weeks after the company released the Pika 1.5 model with its host of new visual effects. Pika is even taking unsubtle jabs at OpenAI by describing Pika 2.0 as "Not just for pros. For actual people. (Even Europeans!)" in reference to the enterprise focus of Sora and its limited global release that so far doesn't include European countries. Rivalry aside, Pika 2.0 has plenty of new perks, making it fairly appealing. The most notable is Scene Ingredients. Imagine a virtual kitchen with a pantry of video elements you can pick from. You choose the characters, props, backgrounds, and other bits you want to incorporate and let Pika's AI blend and bake them. Let's say you want to make a clip of a surfing cat in space. Until now, you'd need to write a prompt for the video, perhaps with an image reference for the cat. With Scene Ingredients, you can upload your favorite cat's photo, a stellar background image of the sky at night, and a picture of your dream surfboard, and Pika will mash it up into a delicious, cohesive scene. Even without images to embed in videos, Pika 2.0 better understands text prompts thanks to its upgraded text alignment. If you've ever typed a prompt into an AI tool and gotten something that only vaguely resembled what you wanted, you'll likely notice how Pika is less likely to mess up your idea when making the video. If you ask for a dragon to fly over a medieval castle during sunset, the AI will be much more likely to show a video with a dragon that actually flies, a castle that looks like a castle, and a sunset that doesn't look like a lava explosion. And with upgraded motion rendering, all the characters in the video will walk, fly, roller skate, or cartwheel without looking like they are floating or that their joints don't all connect. Pika's pitch is about giving the average person or small group control over making videos without making it too complicated. Hence, the deliberate, if oblique, mocking of OpenAI and Sora for their Hollywood-level focus projects. Pika 2.0 is aimed at those making clips for TikTok of marketing videos for side hustles. That doesn't mean Pika has no other competition besides OpenAI, though. There are AI video platforms for all kinds of projects: Pollo, Runway, Stability AI, Hotshot, and Luma Labs' Dream Machine have something to offer the average aspiring AI filmmaker. If you want to try out Pika 2.0, it's available to free and paid users, with limits on the free tier. You can also switch back to earlier models if you desire to.

Forget Sora -- Pika Labs drops v2 of its creative AI video model

Pika Labs v1.5 AI video model is used by more than 11 million people regularly. Many of its users turn to it for some fun, creative social clips. These include squishing faces and causing cakes to explode. Now, it's getting a huge upgrade with v2. With its last update, Pika unveiled its Pikaffects, making it easy to squish, melt and explode items within an image. It has been used by brands like Balenciaga, Fenty and Vogue, as well as celebrities and influencers. The new model still has those creative, social touches but more directly takes on the new powerhouse in AI video -- OpenAI's Sora (which has gone in at number one in the AI video leaderboard). While OpenAI spent 11 months slowly cooking Sora, Pika's small team has built two new models and some impressive features. The company says Pika 2's technical qualities rival Sora but offer better customization and control over its output. The biggest upgrade in Pika 2 seems to be how customizable it is compared to previous AI video models. The company said in a statement this would allow people to make "fun, hilarious, and engaging content they really want." One of the new elements is being able to control elements within the video by sharing your own images. These are called "scene ingredients" by the Pika team and let you build a shot from the exact character, object, clothing and setting shown in the images you shared with the model. "The model's advanced image recognition intuits the role of each reference, and combines them seamlessly into one shot," a spokesperson explained. According to Pika Labs the new model is also particularly good at following a prompt. It follows both the intent and detail of the text and uses that to generate the video. The company promises that it "can turn even the most complex prompts into clips without omitting important elements or breaking down." The most complex element for any video model is motion. Even Sora, which is one of the best I've seen struggles with particularly complex motion. I haven't tried Pika 2 myself yet but from the preview videos -- it may well have cracked it. The company promises it has an advanced understanding of physics, which allows it to make real motion more realistic and fantasy-like motion such as humans flying or elements on an alien world more believable. I don't have access to Sora yet as I'm in the UK but I may be more excited for Pika 2.0 than I am to get my hands on OpenAI's flagship video model.

Pika 2.0 launches in wake of Sora, integrating your own characters, objects, scenes in new AI videos

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Pika, the Palo Alto-based startup that was one of the early leaders in creating lifelike AI video generation tools, has introduced its latest AI video generator model, Pika 2.0, in what it's calling a significant update that promises far more user control and customizability for the generated video clips. The announcement comes just weeks after the successful release of Pika 1.5, which saw widespread adoption and user engagement, positioning the company as a leader in the creative AI space, and days after OpenAI finally released its own AI generator, Sora -- originally shown off 10 months ago -- to the masses. Pika 2.0 boasts improved text alignment, making it easier than ever to translate detailed prompts into cohesive and imaginative video clips. It enhances motion rendering, delivering naturalistic movement and believable fantastical physics -- areas where previous generative AI tools have struggled. The launch of Pika 2.0 underscores Pika's commitment to making AI video creation accessible, affordable, and user-friendly. With its focus on individuals and small creators rather than professional studios, Pika distinguishes itself from competitors like OpenAI, which recently debuted its Hollywood-focused Sora model. Pika 2.0 builds on the success of its predecessor, introducing several standout features designed to empower users to create more dynamic and engaging videos. Central to the update is the new "Scene Ingredients" feature, which allows users to upload and customize individual elements like characters, objects, and settings. Advanced image recognition technology ensures these components are seamlessly integrated into scenes, giving creators much more granular control over their content. These updates aim to make the platform more versatile for users seeking to create playful, shareable videos for social media, as well as for brands looking to produce high-quality advertising content without the cost and complexity of traditional production. Pika's appeal has already translated into impressive growth. Over five million users joined the platform in a single month following the release of Pika 1.5, bringing its total user base to over 11 million. Viral features like "Squish It," "Melt It," and "Explode It" have driven this surge, with videos generated on the platform amassing more than two billion views. Major brands including Balenciaga, Fenty, and Vogue have tapped into Pika's tools to create creative social advertisements, further boosting the platform's visibility. As Pika 2.0 rolls out, the company anticipates even greater adoption by influencers, advertisers, and everyday users alike. Pika 2.0 positions itself as a cost-effective alternative to other AI video solutions. While specific pricing details haven't been disclosed, the platform emphasizes accessibility for non-professionals. This affordability, combined with powerful new features, is expected to drive more users to explore their creativity through AI-generated content. With Pika's rapid growth and ongoing innovation, the company is poised to play a key role in the broader adoption of AI video technologies. The platform's user-first approach stands in contrast to the "pro" filmmaker focus of competitors, potentially giving it an edge in attracting a diverse and widespread audience. Founder and CEO Demi Guo has positioned Pika as a tool not just for making videos but for fostering creativity and storytelling in ways that are fun and engaging. As more brands and individuals turn to AI for content creation, platforms like Pika could pave the way for a new era of accessible and dynamic media.