OpenAI’s Sora text- and image-to-video tool isn’t publicly available yet, but the company is showing what it’s capable of by putting it in the hands of seven artists. The results — from a short film about a balloon man to a hybrid flamingo giraffe — are stirring excitement and priming the pump for what OpenAI CTO Mira Murati says will be a 2024 general release. Challenges include making it cheaper to run and enhancing guardrails. Since introducing Sora last month, OpenAI says it’s “been working with visual artists, designers, creative directors and filmmakers to learn how Sora might aid in their creative process.” Continue reading OpenAI Releases Early Demos of Sora Video Generation Tool

London-based AI video startup Haiper has emerged from stealth mode with $13.8 million in seed funding and a platform that generates up to two seconds of HD video from text prompts or images. Founded by alumni from Google DeepMind, TikTok and various academic research labs, Haiper is built around a bespoke foundation model that aims to serve the needs of the creative community while the company pursues a path to artificial general intelligence (AGI). Haiper is offering a free trial of what is currently a web-based user interface similar to offerings from Runway and Pika. Continue reading AI Video Startup Haiper Announces Funding and Plans for AGI

Lightricks, the company behind apps including Facetune, Photoleap and Videoleap, has come up with a text-to-video tool called LTX Studio that it is being positioned as a turnkey AI tool for filmmakers and other creators. “From concept to creation,” the new app aims to enable “the transformation of a single idea into a cohesive, AI-generated video.” Currently waitlisted, Lightricks says it will make the web-based tool available to the public for free, at least initially, beginning in April, allowing users to “direct each scene down to specific camera angles with specialized AI.” Continue reading Lightricks LTX Studio Is a Text-to-Video Filmmaking Platform

On the heels of ElevenLabs’ demo of a text-to-sound app unveiled using clips generated by OpenAI’s text-to-video artificial intelligence platform Sora, Pika Labs is releasing a feature called Lip Sync that lets its paid subscribers use the ElevenLabs app to add AI-generated voices and dialogue to Pika-generated videos and have the characters’ lips moving in sync with the speech. Pika Lip Sync supports both uploaded audio files and text-to-audio AI, allowing users to type or record dialogue, or use pre-existing sound files, then apply AI to change the voicing style. Continue reading Pika Taps ElevenLabs Audio App to Add Lip Sync to AI Video

OpenAI has debuted a generative video model called Sora that could be a game changer. In OpenAI’s demonstration clips, Sora depicts both fantasy and natural scenes with photorealistic intensity that makes the images appear to be photographed. Although Sora is said to be currently limited to one-minute clips, it is only a matter of time until that expands, which suggests the technology could have a significant impact on all aspects of production — from entertainment to advertising to education. Concerned about Sora’s disinformation potential, OpenAI is proceeding cautiously, and initially making it available only to a select group to help it troubleshoot. Continue reading OpenAI’s Generative Video Tech Is Described as ‘Eye-Popping’

Google has come up with a new approach to high resolution AI video generation with Lumiere. While most GenAI video models output individual high resolution frames at various points in the sequence (called “distant keyframes”), fill in the missing frames with low-res images to create motion (known as “temporal super-resolution,” or TSR), then up-res that connective tissue (“spatial super-resolution,” or SSR) of non-overlapping frames, Lumiere takes what Google calls a “Space-Time U-Net architecture,” which processes all frames at once, “without a cascade of TSR models, allowing us to learn globally coherent motion.” Continue reading Google Takes New Approach to Create Video with Lumiere AI

Google has unveiled a new large language model designed to advance video generation. VideoPoet is capable of text-to-video, image-to-video, video stylization, video inpainting and outpainting, and video-to-audio. “The leading video generation models are almost exclusively diffusion-based,” Google says, citing Imagen Video as an example. Google finds this counter intuitive, since “LLMs are widely recognized as the de facto standard due to their exceptional learning capabilities across various modalities.” VideoPoet eschews the diffusion approach of relying on separately trained tasks in favor of integrating many video generation capabilities in a single LLM. Continue reading VideoPoet: Google Launches a Multimodal AI Video Generator

Stability AI has opened research preview on its first foundation model for generative video, Stable Video Diffusion, offering text-to-video and image-to-video. Based on the company’s Stable Diffusion text-to-image model, the new open-source model generates video by animating existing still frames, including “multi-view synthesis.” While the company plans to enhance and extend the model’s capabilities, it currently comes in two versions: SVD, which transforms stills into 576×1024 videos of 14 frames, and SVD-XT that generates up to 24 frames — each at between three and 30 frames per second. Continue reading Stability Introduces GenAI Video Model: Stable Video Diffusion

Having made the leap from image generation to video generation over the course of a few months in 2022, Meta Platforms introduces Emu, its first visual foundational model, along with Emu Video and Emu Edit, positioned as milestones in the trek to AI moviemaking. Emu uses just two diffusion models to generate 512×512 four-second long videos at 16 frames per second, Meta said, comparing that to 2022’s Make-A-Video, which requires a “cascade” of five models. Internal research found Emu video generations were “strongly preferred” over the Make-A-Video model based on quality (96 percent) and prompt fidelity (85 percent). Continue reading Meta Touts Its Emu Foundational Model for Video and Editing

The entrepreneurs behind the Myspace social network and gaming company Jam City have shifted their focus to generative AI and web3 with a new venture, Plai Labs, a social platform that provides AI tools for collaboration and connectivity. Plai Labs has released a free text-to-video generator, PlaiDay, which will compete with other GenAI video tools from the likes of OpenAI (DALL-E 2), Google (Imagen), Meta Platforms (Make-A-Video) and Stable Diffusion. But PlaiDay hopes to set itself apart by offering the ability to personalize videos with selfie likenesses. Continue reading Social Startup Plai Labs Debuts Free Text-to-Video Generator

Kaiber, the AI-powered creative studio whose credits include music video collaborations with artists such as Kid Cudi and Linkin Park, has launched a mobile version of its creator tools designed to give musicians and graphic artists on-the-go access to its suite of GenAI tools offering text-to-video, image-to-video and video-to-video, “now with curated music to reimagine the music video creation process.” Users can select artist tracks to accompany visuals to build a music video “with as much or little AI collaboration as they wish.” Users can also upload their own music or audio and tap Kaiber for visuals. Continue reading Startup Kaiber Launches Mobile GenAI App for Music Videos

Seattle-area startup Irreverent Labs has shifted its focus from blockchain-based video games and NFTs to artificial intelligence. Specifically, it wants to build foundation models for text-to-video generation and related content creation tools. Text-to-video is being explored by several companies but is still in development. Samsung Next was intrigued enough with the proposition to invest an undisclosed sum in Irreverent. While there are several apps that output cartoonish results, ambitious efforts are limited. Animations that aim for photorealism, such as Meta’s Make-a-Video and Runway’s Gen-2, can output only four or five seconds of video at a time. Continue reading Samsung Next Invests in Irreverent Labs’ Text-to-Video Tech

Google-backed AI startup Runway has released Gen-2, an early entry among commercially available text-to-video models. Previously waitlisted in limited release, the commercial availability is impactful, since text-to-video is predicted as the next big bump in artificial intelligence, following the explosion of AI use generating text and images. While Runway’s solution may not be ready to serve as a professional video tool, this is the next step in development of tech expected to impact media and entertainment. Filmmaker Joe Russo recently predicted that within the next two years, AI may have the ability to create feature films. Continue reading Runway Makes Next Advance in Consumer Text-to-Video AI

New York-based Runway is releasing its Gen 2 system, which generates video clips of up to a few seconds from text or image-based user prompts. The company, which specializes in artificial intelligence-enhanced film and editing tools, has opened a waitlist for the new product that will be accessed through a private Discord channel by an audience grown over time. Last year, Meta Platforms and Google both previewed text-to-video software in the research stage, but neither detailed plans to make their platforms public. Bloomberg called Runway’s limited launch “the most high-profile instance of such text-to-video generation outside of a lab.” Continue reading Runway Opens Waitlist for Its Gen 2 Text-to-Video AI System

QuickVid is a new AI-driven text-to-video platform aiming for a mass market user base. The tool draws on various generative AI systems to automatically create short-form videos for YouTube, Instagram, TikTok and other platforms. Created by former Meta Platforms programmer Daniel Habib “in a matter of weeks,” QuickVid is quite rudimentary, though Habib says he plans to continue fine tuning and adding features. Unlike Google and Meta have done with their nascent text-to-video systems, QuickVid has bypassed the formalities of research papers and industry previews and jumped directly to a public-facing website. Continue reading QuickVid Uses AI to Create Short Videos from Text Prompts