Latest news with #Kling2
Tom's Guide
4 days ago
- Entertainment
- Tom's Guide
Midjourney video generation is here — but there's a problem holding it back
Midjourney, one of the oldest and best-known AI image generators, is taking a new direction. Following in the footsteps of its competitors, Midjourney is now also offering AI video generation. Known as V1 Video, this new model allows users to upload an image or use an image generated by Midjourney's V7 image generator, creating a set of short videos from it. Announced in a post on X and a blog post, David Holz, Midjourney CEO, stated, 'Introducing our V1 Video Model. It's fun, easy, and beautiful. Available at $10/month, it's the first video model for *everyone* and it's available now.' Unlike some of the other competitors in the AI video world, Midjourney can't make a video from a prompt alone. While this will likely change in the future, it does put Midjourney a few steps behind the likes of Sora and Kling 2. Introducing our V1 Video Model. It's fun, easy, and beautiful. Available at 10$/month, it's the first video model for *everyone* and it's available now. 18, 2025 Launching the product, the Midjourney CEO went on to explain, 'Today's Video workflow will be called 'Image-to-Video'. This means that you still make images in Midjourney, as normal, but now you can press 'Animate' to make them move.' There is an automatic animation setting that will create a random motion prompt for you. For those wanting more control, there is also the option to manually choose an animation move for the video. When generating a video, you can choose if it is low or high motion (how much movement happens in the video). Once the video is created, you can extend it, adding four seconds at a time. You can do this up to four times. Get instant access to breaking news, the hottest reviews, great deals and helpful tips. While you can add images from outside of Midjourney to animate, Holz added, 'We ask that you please use these technologies responsibly. Properly utilized, it's not just fun, it can also be really useful, or even profound - to make old and new worlds suddenly alive.' This lines up with Midjourney's recent legal battle with Disney, raising concerns over the use of external copyright in the training model. As mentioned above, you can currently use Midjourney V1 on the $10 per month plan. However, that could well change pretty soon. 'The actual costs to produce these models and the prices we charge for them are challenging to predict,' Holz added in the announcement post. 'We're going to do our best to give you access right now, and then over the next month, as we watch everyone use the technology (or possibly entirely run out of servers) we'll adjust everything to ensure that we're operating a sustainable business.' The problem is that the starting cost is already much higher than an image. Midjourney will be charging 8x more for a video creation than for an image. While that is still less than the average competitor, that amount is likely to change. While you can make videos on the cheapest plan, they will quickly eat up your credits. There will also be a slower but less expensive version of video generation available on the Pro model.
Tom's Guide
07-06-2025
- Entertainment
- Tom's Guide
This AI video generator is going viral, and it's completely free to use
AI video generators are having a bit of a moment. Whether it's Google's Veo 3, complete with audio integration, or something like Kling 2 or Runway that are creating movie-quality clips with ease, the technology has come a long way. But along with the big-name companies vying for the best AI video generator, there are some smaller underdogs of the AI video world. One that recently caught my eye was Hailouai. I kept seeing videos generated by the model popping up on sites like X, with users showing off their impressive generations. This isn't the first time we've talked about Haliuo, in fact, we were impressed by a major update it revealed late last year. But the AI company is back in people's minds with its most recent updated called the Director model. In this version, like a few other big AI video generators, you can input camera angles and movements, to give your videos a bit more action. This new update gives users on Hailuo a bit more control over what they are producing. It allows for the alteration of camera angles in prompts in two ways. Users can either choose from a pre-selection of options like 'downward tilt' or 'right walking' or they can come up with their own. Like most video generation experiences, creativity can either reward or hinder you. Sometimes, getting too complicated with camera angle suggestions resulted in a complete mess of an experience, or the model would ignore it completely. I found more success when using Hailuo by focusing on the options I had been given. Get instant access to breaking news, the hottest reviews, great deals and helpful tips. You can choose to either make a video from scratch with a text prompt or use an existing image that you want to edit. You can also add an image of someone and ask for them to be dropped into a scene. This option comes with an incredibly long list of warnings about use of that image and follows the same concerns that come with deepfakes on any platform. All of this technology can be found in competitors like Runway, Kling and Higgsfield. One of the major benefits of Haliuo is how good the free version of its software is. The load times are slightly slower, and you are still limited in credits, but that limit is pretty high. You will be able to get 20 to 30 videos generated before you near the end of your credit limit and there are ways to get more without having to sign up for a paid plan. However, on the free plan, your images and videos will have watermarks on them - something to keep in mind if you plan to use these videos commercially. Once you've made an account on Hailuai, you'll land on the homescreen. You should have roughly 1,000 credits at this point. Videos cost around 30 credits and images just 1. On the left hand side there are four ways to interact with the AI generation. For this particular activity, we want the 'create video' section. Here, you can choose to turn images into video, text to video or input your subject reference (an image of a person to edit). Most importantly here, you want to change your model at the bottom to T2V-01-Director to add the camera angles change. Then, by clicking the small camera in the bottom right corner, you'll be able to choose the camera angle style for your video. Once that's all selected, and you've put your prompt in, click the generate button in the bottom right. It will take a few minutes to generate but compared to other free video generators is actually quite fast. This isn't the best AI video generator on the market, but considering how good its free plan is (and then how affordable the paid plans are) its a great choice for those not wanting to fork out large amounts of money to generate a few videos. Hailuo offers all of the same features you'd see in leading models and, quite frankly, in some ways more. You can even ask Deepseek for assistance on your prompt directly from the Hailouai app. With such stiff competition in this market, Hailoai is keeping up surprisingly well with the likes of OpenAI and Gemini, even offering the ability to add sound (at the expense of more credits of course).
