OpenAI's Sora: A Promising but Imperfect AI Video Generation Tool

I Tried OpenAI's Sora, And It's Cool I Guess

Summary ChatGPT Plus subscribers get 5-second Sora taste tests, not full 20-second clips. Sora's videos remain hit-or-miss due to coherence issues and visualizing prompts. Sora's video technology feels less mature than image generation, lagging behind Veo 2. After months of teasing, OpenAI's Sora video generation technology is available to the public. I spent some time playing with this much-anticipated tech, and honestly came away a little underwhelmed. ✕ Remove Ads ChatGPT Plus Subscribers Get a 5-Second Taste Test of Sora Like every other ChatGPT Plus subscriber, once Sora rolled out to the public, I got access to make my own videos. However, this is more like a taste tester than the real deal. People who specifically pay for Sora can make clips up to 20-seconds long and access the higher 1080p resolution. For Plus subscribers, you get 5-second clips, and up to 720p quality. All you have to do is put your prompt into the text box, and a few seconds later you have a video clip, pretty much how Midjourney or other AI image generators work from the user's perspective. Even Short Clips Are Very Hit-and-Miss One of the main reasons that the "full" Sora experience is limited to 20 seconds is that there are still significant issues with this technology when it comes to coherence. The longer the video goes on, the more mistakes and weird tangents it takes. That issue aside, it had a hard time visualizing what I put in my prompts. For example, I asked it for a clip of a starship going into warp, which is a pretty common sci-fi trope. ✕ Remove Ads Well, it's sort of what I had in mind, but I wouldn't put that in my half-baked YouTube talking head video. At other times, it's pretty spot-on. Such as when I asked for a spinning chrome HTG logo. The last bit of trouble Sora currently has is with any sort of physics. I've seen plenty of videos featuring animals that just don't move in a believable way, and when I asked for something simple -- a ball bearing running on a rail, it gave me this strange video. Even when videos are visually perfect, it's usually the motion that gives it away as an AI-generated clip. Sora Feels Much Less Mature Than Image Generation I don't want to create the impression that Sora isn't impressive. It's a major achievement, but actually using it feels like the early days of image generation. This wouldn't be so apparent if not for Google's precisely-timed announcement of Veo 2. The videos from that system look so much better than Sora, particularly when it comes to the physics of moving objects looking correct. Just check out this official compilation from Google. ✕ Remove Ads While one might argue these are cherry-picked, a few YouTubers have had access to Veo 2, and the opinion seems to be that Veo 2 comes out on top by quite a margin. For Now, It's Just a Fun Toy Getting to play around with Sora for a bit thanks to a subscription I already have was fun, but I certainly wouldn't want to pay the $200 a month fee for this product in its current state. You'd be much better off simply subscribing to a stock video service. Looking at what Google's cooked up, and considering that there are other competitors in this space like HeyGen and Runway ML, I expect updates and improvements to be fast and frequent. If for no other reason than OpenAI being relentless in its improvement of ChatGPT. ✕ Remove Ads I still see a medium-term future where AI video generation will be capable of so much more, and even allow for longer-form content to be generated with precise prompt adherence, and the ability to edit elements within a scene. However, that day is still likely a few years away, and for now it's an interesting if impractical curiosity.

OpenAI Sora AI Video Generation Tool - Is It Worth the Hype and Price?

OpenAI has introduced Sora, an advanced AI-powered video generation platform designed to simplify the creation of high-quality videos. By integrating sophisticated features into a user-friendly interface, Sora aims to assist both beginners and professionals in video production. While it does not claim to transform the market, its robust capabilities and streamlined workflow position it as a noteworthy contender in the growing field of AI video tools. Below is an in-depth look by AI Advantage at Sora's offerings, potential limitations, and how it aligns with creative or professional needs. Creating videos can feel overwhelming, especially when juggling tight deadlines, limited resources, or trying to bring a creative vision to life without spending hours on editing. If you've wished for a tool that simplifies the process while delivering professional-quality results, OpenAI's Sora might be the solution. This AI-powered platform merges innovative technology with user-friendly features. But with many AI tools flooding the market, you might wonder: is Sora worth the investment, or is it just another overhyped product? Sora is available globally, with one significant exception: users in Europe and the UK are currently restricted from accessing the platform due to regulatory challenges. While some users in these regions might consider using a VPN to bypass these restrictions, OpenAI explicitly warns that such actions could result in account bans, making this an unviable option for most. Additionally, Sora is only accessible through paid subscriptions, as there is no free-tier option available. This exclusivity may deter casual users who prefer to experiment with AI tools before committing financially. For those willing to invest, however, Sora offers a range of features designed to enhance the video creation process. Sora provides two subscription tiers, each tailored to different user needs and budgets: While the Pro Plan delivers superior quality and functionality, its steep price point may deter budget-conscious users. Many competitors offer similar services at lower costs, which could make Sora's pricing a potential drawback for those exploring more affordable options. Explore further guides and articles from our vast library that you may find relevant to your interests in AI video generator. Sora combines a variety of advanced tools to streamline and enhance the video creation process. Its standout features include: In addition to these core features, Sora includes organizational tools such as folders, prompt presets, and favorites, which help users manage their projects more efficiently. These capabilities make the platform suitable for a wide range of users, from novice creators exploring AI tools to experienced video editors seeking to optimize their workflow. Sora sets itself apart by integrating features from leading AI video platforms, such as Runway and Luma Labs, into a single, comprehensive tool. Its ability to generate videos in 1080p resolution surpasses many competitors, which often cap their output quality at lower resolutions. Additionally, Sora's intuitive interface ensures that users of varying skill levels can navigate the platform with ease. However, Sora's lack of a free plan and the watermarked output on the Plus Plan may limit its appeal to users seeking affordable or professional-grade solutions. The Pro Plan's $200 monthly fee is significantly higher than many alternatives, which could make it less competitive in the broader market. For users prioritizing cost-effectiveness, these factors may outweigh the platform's advanced features and high-quality output. Despite its strengths, Sora has several notable limitations that may impact its appeal to certain users: These limitations highlight the need for OpenAI to address pricing and accessibility concerns to make Sora a more viable option for a broader audience. Sora's comprehensive feature set and high-quality output position it as a strong player in the AI video generation market. By combining the best practices and tools from competitors, OpenAI has created a platform that appeals to a wide range of users, from beginners to professionals. However, its pricing structure, lack of a free tier, and regional restrictions could hinder its broader adoption. As AI video tools continue to evolve, Sora's long-term success will depend on its ability to balance innovation with accessibility. For now, it serves as a powerful option for those willing to invest in premium AI video production software. Whether it's the right choice for you will depend on your budget, creative needs, and willingness to commit to a paid subscription.

Sora AI Video Generator Walkthrough Tutorial - Video

OpenAI has released its highly anticipated Sora AI video generator which can produce video from text prompts, images, and video inputs. I'm gonna walk you through the Sora interface and show off some of the features that come with a chat GBT plus subscription which currently costs $20 a month. You can also sign up for the Sora Pro model which offers. 10 times more video generations, higher resolution up to 1080p, and longer video durations for $200 a month. Upon logging into Sora, you're greeted with the featured window showing examples of AI generated videos under the Explore section. Above featured is recent AI generated videos produced by other users. Below recent and featured videos are your saved videos. I haven't created any videos yet, so mine is empty. If you hover over a video in the featured or recent sections, you will see options appear on the bottom of the video to remix, loop, and save the video. Below the explore section of the interface is your library, which includes all videos, your favorites, uploads, and an option to create a new folder. At the bottom of the screen, you have a toolbar to describe your video, which is where you can write. You're prompt to generate an AI video. On the bottom left there's a plus symbol to upload an image or a video. Next to upload is a preset button which I'm only able to access using a PC. For some reason when I'm using my MacBook Pro, which is what I recorded this video with, the preset button is not available. Click on preset and you will see options to set a preset video style such as stop motion and film noir. Next to preset is your aspect ratio, which includes 16 by +91 by. 1 and 9 by 16 for vertical videos. Next you have video resolution which includes 480p, 720p, and 1080p, which is currently grayed out because I'm not subscribed to the Pro version. There is no 4K option in Sora yet, as you can see, 720p says it's 4 times slower than 480p. I'll test that out later to let you see the total amount of time it takes to generate a 5 2nd 720p video file. Next you have duration which is currently limited to 5 seconds and 10 seconds. You can go up to 15 seconds and 20 seconds with the Sora Pro model. Next to duration is variations which allow you to choose the number of variations you'd like Sora to create for each video generation. The maximum number of variations I have with Chat GPT Plus is 2. On the far right hand side is an option to create a storyboard which allows you to generate multiple parts of a scene by generating multiple videos on a timeline. So let's generate our first AI video with Sora and see how it comes out. Since this is CNET, I'd like to generate a man. Holding a high-tech smartphone that is projecting a three dimensional hologram of an alien from outer space delivering a message. I'm gonna do this at 16 by 9, 480p at 5 seconds and let's see how long this takes to generate. Click Create video. And now it's added to my queue so I can click on activity. And see my cue. It's generating two video variations. Let's see what it comes up with. 45% done. 68% it's going pretty quick. It named the video for me Alien hologram Message. It's 480p on December 13th at 12:59 p.m. Let's see what's gonna happen here. Yes. It's pretty good. It's not exactly what I was picturing in my mind. I was thinking the hologram was gonna be like projected off of the phone. Maybe if I put a little more detail into my prompt, it'll do that, but this is pretty good. The man looks real. Now down below I have options to edit my prompt, view my story, recut, remix, blend, and loop. Now if I go to my library back on the main interface and click on all videos, it's gonna show my videos, and I guess I could scroll through them just by moving my mouse across them. Otherwise they're just gonna sit static and not play. So that's kind of interesting. If I click on it, it'll open that one video, and then I have options to favorite it, share it, download it. Add it to a folder, report a problem, delete it, and then I can also go back to my activity page. And then here is my account information. So pretty cool. So I think I like this one is my favorite, so I'm gonna click on it. I'm gonna click favorite. And then I'm gonna go back and if I go to my favorites, there it is in my favorites. Then if I click on the menu, I can remove from favorites, download, add to folder, view variations, and delete. So pretty good so far, so good. So now I'm going to generate another video file and increase the parameters to 720p and see how long it takes to generate that video file. Let's generate a black cat attacking a Christmas tree and see what we get. So I'm gonna put that in there, 720p 16 by 9. I only am able to have one variation in 720p, which is a bummer, but let's go for it. Now it's generating my video of a black cat attacking a Christmas tree. It's going pretty fast and I think that's because it's only allowing me one variation at 7:20p in 5 seconds. And it named it Cat's festive Leap, which is pretty clever. Oh, that looks pretty good. Well, it generated two cats. It looks like my cat Iya. It's funny because as the cat jumps, it's butt turns into the head, as you can see. The cat's doing some weird morphing as it jumps on the tree, but the movement on the tree looks real. I like that it put a fireplace on the left side that is lit with some other Christmassy sort of decorations on it. I think that's really clever. It looks kind of real, but it looks silly, very interesting result. Uh, I dig it though, it's cool. So now let's try uploading a static image and have Sora animate the image based on what it sees in the photo. This is a picture my wife took in Oahuo last year, my son walking on the beach, so I'm gonna say upload an image or video. It's gonna ask me to agree to a bunch of stuff. I'm just gonna accept all, got it. Let's see whatora can do with this image. Animate this image of my son walking on the beach. I'm just gonna click go for it and let's see what happens. So now it's in the queue. Now this was a vertical image, so I think what So is gonna do is convert it into 16 by 9 and generate some stuff on the left and right hand side of the photo. So let's see what it does. So it actually like cut it into two shots, which is interesting, because that's kind of the main image. And then it cut to a separate shot where it's like zooming out and he's wearing like a hoodie for some reason and the second one it looks like so that's pretty cool that did not exist before and now we have this AI generated image which kind of brings it to life and makes it look real it looks real that looks very real. Let's try another image of both my sons building a snowman in South Lake Tahoe last winter and see what Sora can do with this image. So I wrote animate the snowman waving to the boys who built him. Now let's see what it's gonna do. As you can see it, it cropped them. It's gonna take that center piece of them. Can I move the crop around? I can sort of. Not really, but anyway, so I'm gonna give it a try. Let's go create video. I'm really interested to see what it's gonna do with the snowman because um every year we, we build a snowman, but I've never seen one of them come to life. OK, so the snowman is not waving to them as I requested. But they're kind of going around the snowman. Putting the finishing touches on him, he does move a little bit. And as you can see, like the stick kind of sticks to my son with the red sweater's arm. It's kind of interesting. Again, this never happened, but it looks pretty real. It look like my kids building the snowman so I'm tripping out on this. It's so strange. Anyway, that's what you could do with static images that you have. You can animate them and bring them to life with Sora and it's pretty amazing what it could do. I'm gonna favorite that one cause that is pretty awesome. So let's talk about video generation limitations in Sora. Currently with Chat GPT Plus subscription, you are allowed to produce 50 priority videos a month or 1000 credits. As mentioned earlier, you're limited to 720p resolution with a maximum of a 5 2nd video duration. With the Chat GBT Pro subscription, you are capped at 500 priority video generations a month or 10,000 credits and unlimited relaxed videos. Relax mode allows. you to continue to generate videos when site traffic is low and you have run out of credits in your pro subscription. According to OpenAI, video generations will take longer and relaxed mode and are not considered priority videos. You also have 1080p resolution up to 20 seconds in duration, and you can create up to 5 concurrent video generations. The watermark will also be removed in the pro version. So here are my final thoughts on Sora. Sora is a very. Powerful tool for creators, but right now it's kind of random and might take a few tries to perfect exactly what you're trying to accomplish. The output is limited, with short video durations and no 4K options. That said, I could see how this could be awesome for short films and illustrations, as well as all kinds of applications. Some of the video generations look very real and could potentially trick people into believing it's a real person, place, or thing on the screen. I love how simple. Interface is set up and that you can save and organize your work into folders. I also like the options for creating different aspect ratios and storyboards, which will be super handy for any producer or filmmaker. So has been let out of Pandora's box, and it's here to stay. So like any new technology, we might as well embrace it and try to harness its power. There are a ton of other similar competing AI video generators on the web to choose from like Synthesia. Runway and Google's DeepMind AI video generator VAO, which should be arriving any day. I wanted to cover Sora because Chat GBT was one of the first AIs to hit the mainstream a few years ago, and it has the name cachet and reputation to draw attention from CNET's vast audience. What AI video generators have you played with? Make sure to leave a comment below and subscribe to CNET for more AI news, reviews and how-tos, and thanks for watching.