The demand for scalable video content is surging, but production remains a bottleneck between expensive live shoots and limited AI solutions. CraftStory addresses this core challenge with the release of Model 2.0, a next-generation AI model that generates expressive, human-centric videos of up to five minutes in length. This breakthrough sets a new industry standard for realism and duration, enabling businesses to produce studio-quality performances for training, demos, and marketing at unprecedented speed and scale.
CraftStory Model 2.0 generates realistic AI human videos up to five minutes long.
It solves the scalability gap between costly live shoots and short, inconsistent AI clips.
The model uses a video-to-video approach, animating a reference image with motion from a driving video.
A new parallelized diffusion pipeline ensures visual coherence across long sequences.
Features include advanced lip-sync and gesture alignment for natural expressiveness.
The company was founded by the creators of OpenCV and is backed by $2M in funding.
Businesses and studios face a significant hurdle in scaling video content for product education, training, and localization. Traditional methods are slow and costly, while existing AI video tools often produce short clips that lack the consistency for professional use. Model 2.0 is designed specifically to fill this gap, transforming scripts or reference footage into long-form, studio-quality videos that maintain character identity and continuity, eliminating the need for constant reshoots.
Model 2.0 is currently a video-to-video model that animates a source image using the motion from a driving video. The key to its performance is a novel parallelized diffusion pipeline developed by CraftStory's research team. This innovation processes different video segments simultaneously while maintaining flawless visual coherence across frames, a critical advancement for long-form synthesis. The model was refined on high-frame-rate footage of real people, ensuring lifelike motion, natural facial dynamics, and expressive hand and body movements. Output is available in landscape or portrait formats at 480p and 720p, with optional upscaling to 1080p.
"AI-generated video will soon become the primary way companies communicate their stories," said Victor Erukhimov, Founder and CEO of CraftStory. "With Model 2.0, we're making it possible to create long-form, studio-quality videos that truly engage audiences. We believe our model provides an unprecedented level of control over content — including the movement and expressiveness of the person on screen."
The model also includes an advanced lip-sync system that matches any audio track and a gesture alignment algorithm that ensures body movements naturally correspond to speech rhythm and emotion.
CraftStory's credibility is bolstered by its founding team, who are the creators of the renowned Open Source Computer Vision Library (OpenCV). The company launched after raising a $2M round led by Andrew Filev, founder of Wrike. Filev highlighted the critical market need Model 2.0 addresses, stating, "One huge gap in this market is the lack of models that can generate consistent videos over longer sequences... You need 30 seconds, you need 2 minutes — you need more."
The company's future development is focused on a text-to-video model for generating long-form content directly from a script and adding support for moving-camera scenarios like "walk-and-talk" formats.
CraftStory Model 2.0 represents a significant leap forward in generative video technology. By solving the critical challenges of duration and consistency, it moves AI video from a novelty to a practical, scalable production tool, empowering businesses to tell longer, more engaging stories without the traditional constraints of time and budget.
About CraftStory
CraftStory is a pioneer in realistic AI-generated human video, founded by the creators of OpenCV. The company enables businesses to create studio-quality, long-form videos at scale using AI.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.