A new artificial intelligence startup founded by the creators of The world’s most widely used computer vision library emerged with technology that produces realistic human-centric videos up to five minutes long – a dramatic leap beyond the capabilities of rivals including OpenAI Sora and Google’s VO,
craftstoryLaunched on Tuesday with $2 million in funding, Model is introducing 2.0, a video generation system that addresses one of the most significant limitations of the emerging AI video industry: duration. While OpenAI sora 2 Topping out at 25 seconds and with most competing models producing clips 10 seconds or less, CraftStory’s system can produce a continuous, consistent video performance that lasts as long as a typical YouTube tutorial or product demonstration.
This breakthrough could unlock substantial business value for enterprises struggling to scale up video production for training, marketing and customer education – markets where brief AI-generated clips have proven inadequate despite their visual polish.
"If you actually try to create a video with one of these video creation systems, you’ll find that many times you want to implement a certain creative vision, and no matter how detailed the instructions are, the systems basically ignore a part of your instructions," Victor Erukhimov, Founder and CEO of CraftStory, said in an exclusive interview with VentureBeat. "We have developed a system that can seamlessly generate videos as long as you need them."
How parallel processing solves the long-form video problem
CraftStory’s advancements are based on what the company describes as parallel propagation architecture – a fundamentally different approach to how AI models generate video compared to the sequential methods employed by most competitors.
Traditional video generation models work by running propagation algorithms on large three-dimensional volumes where time represents the third axis. To generate longer videos, these models require proportionally larger networks, more training data, and significantly more computational resources.
craftstory Instead it runs several smaller propagation algorithms simultaneously over the entire duration of the video, with bidirectional constraints connecting them. "The latter part of the video may also affect the earlier part of the video," Erukhimov explained. "And this is very important, because if you do it one by one, an artifact that appears in the first part spreads to the second part, and then it accumulates."
Instead of generating eight seconds and then stitching on additional segments, CraftStory’s system processes all five minutes concurrently through interconnected diffusion processes.
Importantly, CraftStory trained its model on proprietary footage rather than relying solely on internet-scraped videos. The company hired studios to shoot the actors using high-frame-rate camera systems, which capture clear detail even in fast-moving elements like fingers – avoiding the motion blur inherent in standard 30-frames-per-second YouTube clips.
"What we showed is that you don’t need a lot of data and you don’t need a lot of training budget to create high quality videos," Erukhimov said. "All you need is high quality data."
Model 2.0 currently operates as a video-to-video system: users upload a still image to animate and a "driving video" Which involves a person whose activities the AI will replicate. CraftStory offers preset driving videos shot with professional actors, who receive revenue shares when their motion data is used, or users can upload their own footage.
The system produces a 30-second clip at low resolution in about 15 minutes. An advanced lip-sync system synchronizes mouth movements with the script or audio track, while gesture alignment algorithms ensure that body language matches speech rhythm and emotional tone.
Fighting a war chest with 2 million dollars against billions of dollars
CraftStory’s funding comes almost entirely from Andrew FilevWho sold his project management software company Wrike to Citrix $2.25 billion in 2021 and now runs zencoderAn AI coding company. The modest increase is in stark contrast to the billions flowing into competing efforts – OpenAI Raised over $6 billion In its latest funding round alone.
Erukhimov pushed back against the notion that huge capital was necessary for success. "I don’t necessarily subscribe to the thesis that calculation is the path to success," He said. "It definitely helps if you have calculations. But if you raise a billion dollars on PowerPoint, no one is happy in the end, neither the founders nor the investors."
Filev defended a David-versus-Goliath approach. "When you invest in a startup, you are basically betting on people," he said in an interview with VentureBeat. "To paraphrase Margaret Mead: Never underestimate what a small group of thoughtful, committed engineers and scientists can build."
He argued that CraftStory benefits from a focused strategy. "Large laboratories are in an arms race to create general-purpose video foundation models," Filev said. "CraftStory is riding that wave and delving much deeper into a specific format: long-form, engaging, human-centered video."
Why does computer vision expertise matter in generative AI video?
Erukhimov’s credibility stems from his deep roots in computer vision rather than the Transformer architecture that has dominated recent AI advances. His initial contribution was opencv – Open source computer vision library, which has become the de facto standard for computer vision applications 84,000 stars on GitHub,
When Intel reduced its support for OpenCV in the mid-2000s, Erukhimov co-founded Itsys with the express goal of maintaining and advancing the library. The company expanded OpenCV significantly before its acquisition by Intel in 2016 and turned to automotive security systems.
Filev said this background makes Erukhimov well-positioned for video production. "People sometimes forget that generative AI video isn’t just about the generative part. It’s about understanding motion, facial dynamics, temporal coherence and how humans actually move." Filev said. "Victor has spent his career overcoming exactly the same problems."
Enterprise focused training videos and product demos
While much of the public excitement around AI video generation has focused on creative tools for consumers, CraftStory is taking a decidedly enterprise-focused strategy.
"We’re definitely thinking more about B2B than consumer," Erukhimov said. "We’re looking for companies, especially software companies, to be able to create great training videos and product videos and launch videos."
The logic is straightforward: corporate training, product tutorials and customer education videos often last several minutes and require consistent quality throughout. A 10-second AI clip can’t effectively demonstrate how to use enterprise software or explain a complex product feature.
"If you need long format video, you should go with us," Erukhimov said. "We can create a consistent, high quality video of up to five minutes."
Filev repeated this assessment. "A major gap in this market is the lack of models that can generate continuous video over long sequences – and this is extremely important for real-world use," He said. "If you’re making an ad for your company, a 10-second video, no matter how good it sounds, is not enough. You need 30 seconds, you need two minutes – you need more."
The company expects cost savings for customers. Filev suggested this "A small business owner can create in minutes content that previously cost $20,000 and took two months to create."
CraftStory is also attracting creative agencies that produce video content for corporate clients with a value proposition focused on cost and speed: Agencies can record an actor on camera and turn that footage into a finished AI video, rather than managing an expensive multi-day shoot.
The next major development on CraftStory’s roadmap is a text-to-video model that will allow users to generate long-form content directly from scripts. The team is also developing support for moving-camera scenarios, including the popular "walk-and-talk" Common format in high-end advertising.
Where CraftStory fits into a fragmented competitive landscape
CraftStory enters a crowded and rapidly growing market. OpenAI sora 2While not yet publicly available, it has generated significant discussion. Google’s Vivo model Moving forward rapidly. route, pikaAnd sustainability ai All offer video generation tools with different capabilities.
Erukhimov acknowledged competitive pressure but emphasized that CraftStory serves a niche focused on human-centered video. He placed rapid innovation and market capture as the company’s primary strategy rather than relying on technological moats.
Filev believes that the market is divided into different layers, with large technology companies operating "API provider of powerful, general-purpose model generation" Whereas niche players like CraftStory focus on specific use cases. "If the big players are building the engines, CraftStory is building the production studios and assembly lines on top," He said.
Model 2.0 is now available at app.craftstory.com/model-2.0, with the company offering early access to users and enterprises interested in testing the technology. Whether the lightly funded startup can gain meaningful market share against deep-pocketed incumbents remains uncertain, but Erukhimov is particularly confident about the opportunity ahead.
"AI-generated video will soon become the primary way for companies to communicate their stories," He said.