OpenAI’s Sora is one of the most impressive AI tools I’ve seen in years of covering the technology. Even in its 'Turbo' form at sora.com, limited to up to 20 seconds of video at 1080p it brings improved realism and motion compared to others.
First announced in February this year, OpenAI spent the past nine months fine-tuning the model with the help of filmmakers, creatives and industry insiders.
The result is an impressive model and feature set built into an entirely new product for OpenAI. The Sora website seems to be modeled on the Midjourney interface and includes some unique features such as remixing and blending videos. The most useful add-on, and one not seen elsewhere is Storyboard.
With Storyboard you can place images or text prompts on a timeline and have Sora fill in the gaps between different points — to give you more control. This is similar to the keyframing feature announced by Runway but not yet released.
There are some limitations to the Sora rollout though. Unless you want to spend $200 per month on ChatGPT Pro you'll only get 50 videos per month for $20 per month and they will be limited to 720p and 5 seconds duration. You can't create video of people without a Pro plan and it isn't available in the EU or UK.
Alternatives to Sora
Since Sora was first announced nine months ago the entire AI video landscape has changed with the launch of three big Chinese models and major upgrades to the likes of Runway and Pika Labs. We've also seen newcomers like Haiper and Luma Labs Dream Machine enter the space, as well as the open-source Mochi-1.
All of the platforms have their own unique features, models have their own quirks and capabilities and they all come at different price points. Some are almost indistinguishable in performance to what we're seeing from Sora Turbo, others have a more consumer focus.
1. Runway
Runway is one of the biggest players in this space. It was the first to launch a commercial synthetic video model and has been adding new features and improvements ever since. This includes very accurate lip-synching, motion control and the recently launched Act-1 for 'puppetering AI people'.
With the launch of Gen-3 you can now create videos starting at ten seconds long. Since the launch of Gen-3 as a text-to-video model Runway has added image and video-to-video as well as clip extensions and lip-synching.
In an increasingly crowded market Runway is still one of the best AI video platforms, and on top of generative content it has good collaboration tools and other image-based AI features such as upscaling and text-to-image.
Runway has a free plan with 125 credits. The standard plan is $15 per month.
2. Luma Labs Dream Machine
Luma Labs released Dream Machine seemingly came out of nowhere earlier this year offering impressive levels of realism, prompt following and natural motion. It also has an initial 5-second video generation. keyframes and extensions.
The latest version goes beyond simple video generation, turning Dream Machine into a creative partner. It is a chatbot-style interface where you can collaborate with the AI on creating images, videos and projects.
The quality is just as good as its always been with a significant improvement in visual realism thanks to the new Photon AI image generator. It can use this to create the videos or you can still give it an image of your own.
Other features such as prompt enhancement and keyframes are still very much in place, allowing you to use images at different points in the generation process.
Being able to extend clips is also particularly powerful in Dream Machine as this allows for character following and fresh scenes. It continues from the final frame of your last video and you can change the motion description for each extension.
Dream Machine has a free plan with 30 generations per month. Lite Plan is $9 per month for 3,200 credits, 1080p video and high-resolution images but it is non-commercial.
3. Kling
Kling AI is a Chinese generative video product from video platform company Kuaishou, its features include longer video generations, improved movement, better prompt following and multi-shot sequences.
Its interface is simple and easy to learn, offering image-to-video and text-to-video with automatic upscaling options and clips starting at 5 or 10 seconds.
I've used it to make multiple videos and in every case it captures human and animal motion in a way no other platform I've tried has achieved. It also seems to be able to depict emotion with both camera movement and within the characters it generates.
The company recently added lip-syncing and clip extensions. With clip extensions, you can define how to extend the clip or leave it automatic. There are also new community features to showcase the best output.
Kling is free to use with 66 credits per day and between 5 and 10 credits per generation. There isn't a subscription plan as such but it offers memberships starting at $10 per month for 660 monthly credits.
4. Hailuo MiniMax
Hailuo MiniMax launched earlier this year and very quickly became one of the best text-to-video artificial intelligence models on the market, offering realistic motion and high-quality video rendering. It has since launched image-to-video, text and sound generation models as well as a fresh interface.
It has been continuously improved since it launched and in a short time has quickly become one of the most realistic models on the market. It is particularly good at depicting human emotion.
The new interface includes a side menu with options to explore other users' clips, as well as a simple way to generate videos. One of my favorite features is image-to-video live which allows you to generate animations and anime.
Hailuo Video gives you a handful of videos for free and the ability to buy extra credits. The base plan is $9 per month for 1,m000 credits, no watermarks and bonus credits for daily login.
5. Haiper
Haiper takes a slightly different approach from other AI video tools, building out an underlying model and training dataset that is better at following the prompt rather than offering fine-tuned control over the motion.
It has rapidly improved since launch and is now on Model v2.5, including enhancements, motion smoothing and other customizations such as keyframing.
Prompting is easy and it was the first to add a floating prompt box over the top of the underlying videos — something copied by OpenAI with Sora.
It offers text-to-video, text-to-image, image-to-video and templates where you can meme-ify your ideas including a kissing and Great Gatsby offering.
Haiper You get 100 credits for free and for $10 per month, you get 1,500 credits to use on the latest model as well as unlimited generations on the previous model.
Honorable mention: Genmo Mochi-1
All of the models above are their own dedicated platforms with additional features and pricing structures. Mochi-1 is an open-source model that has been adapted and refined by the community since released by Genmo.
The model allows for fairly quick video generation and can run on a high-end gaming PC — the others all run on the cloud. It can also be customized and adapted to work for specific brands and requirements.
Mochi-1 is available for free at Genmo.ai or to download and run yourself.
