ByteDance, the company behind TikTok, just unveiled their latest leap into the AI video space: Seaweed-7B. Don’t let the name fool you — “Seaweed” is short for Seed-Video, and the “7B” refers to its ~7 billion parameter diffusion transformer architecture. Like most modern AI video models, Seaweed-7B handles the usual suspects: Image-to-video generation Video from reference images Semi-realistic human characters...

n a stunning display of technological prowess, Chinese AI startup Kling AI has unveiled Kling 2.0, a cutting-edge video generation platform that is currently taking the internet by storm. Social media platform X (formerly Twitter) is overflowing with jaw-dropping video clips that showcase a level of visual fidelity and cinematic quality previously reserved for big-budget Hollywood productions. Following in the...

Alex Mashrabov, the former head of generative AI at Snap, saw a growing opportunity in the world of personalized video creation — and he ran with it. Enter Higgsfield AI, a new video generation platform aimed at helping creators of all types produce high-quality, customized content with just a few taps. At the heart of Higgsfield is its first app...

Runways unnaounces Gen-4 Turbo — the fastest and most powerful video model we’ve ever released. Whether you're a filmmaker, content creator, designer, or just someone who loves to experiment with AI, Gen-4 Turbo is here to supercharge your creative workflow. 🚀 What’s New with Gen-4 Turbo? The name says it all. Gen-4 Turbo is the next evolution in AI video...

ByteDance has introduced its latest innovation in generative AI — DreamActor-M1, a powerful video generation model that pushes the boundaries of animation creation. The model blends a static photo with a reference action video to produce dynamic, high-definition footage where the subject from the photo is seamlessly animated within the video scene. The result: lifelike expressions, natural body movements, and...

Tencent has recently unveiled HunyuanVideo, an open-source AI model designed to transform static images into dynamic videos, marking a significant advancement in AI-driven content creation. With 13 billion parameters, HunyuanVideo stands as the largest publicly available model of its kind, capable of generating videos that exhibit high physical accuracy and scene consistency, thereby actualizing conceptual visions and fostering creative expression...

Runway has unveiled its latest innovation, the Gen-3 Alpha Video-to-Video update, now available in early access for Creative Partners. This cutting-edge tool offers creators an unprecedented level of control and versatility in video editing, enabling a wide array of modifications to existing footage. Key Features of Gen-3 Alpha Video-to-Video: Restyle Your Video with Enhanced Control: Users can transform the aesthetic...

Microsoft has unveiled a new small language model (SLM) designed to help developers build multimodal AI applications that can operate efficiently on lightweight computing devices. The company emphasizes that this model can process speech, vision, and text locally on-device, consuming significantly less computational power than previous iterations. The Rise of Small Language Models (SLMs) While much of the innovation in...

OpenAI has officially unveiled GPT-4.5, internally codenamed ‘Orion,’ marking a significant milestone in its language model development. This release represents the final iteration under OpenAI’s traditional scaling paradigm before shifting towards more advanced reasoning-based architectures. CEO Sam Altman described GPT-4.5 as the first model that “feels like talking to a thoughtful person,” emphasizing its enhanced ability to engage users in...

Alibaba has announced the open-sourcing of four advanced AI models from its Wan2.1 series, the latest iteration of its foundational artificial intelligence technology capable of generating high-quality images and videos from textual and image-based prompts. This move intensifies global competition in AI video generation, positioning Alibaba as a significant player against proprietary AI developers such as OpenAI. The Significance of...

Google is poised to take its AI capabilities to new heights with the development of advanced video creation features for its Gemini app, a groundbreaking revelation that surfaced in a recent report. Known for its ability to generate high-quality still images from text prompts, Gemini could soon expand its repertoire to include the creation of realistic video clips—all driven by...

Pikaswaps, the groundbreaking feature developed by Pika Labs, is set to redefine the landscape of video editing. This cutting-edge technology allows users to effortlessly replace any element within their video content, simply by using photos or text prompts. Whether you're a beginner or a seasoned professional, Pikaswaps unlocks a world of creative possibilities, making it easier than ever to edit...

Google’s cutting-edge AI video generation model, Veo 2, is now available to the public on the Freepik platform, marking a significant milestone in AI-driven content creation. Freepik, known for its extensive stock image library and innovative AI tools, has become the first platform to offer users access to Google’s most advanced video generation technology. In an announcement on X (formerly...

The gig marketplace Fiverr is taking a bold step to help freelancers stay ahead of the curve in an era increasingly dominated by generative AI. In a major announcement at an event on Tuesday, Fiverr revealed a suite of new initiatives aimed at equipping gig workers with cutting-edge AI tools, enabling them to not only adapt to the evolving market...

Microsoft Corporation has taken a significant leap forward in the world of artificial intelligence with the debut of "Muse," an advanced generative AI model capable of creating video-game scenes that would traditionally require extensive programming and animation by human developers. This innovative technology, designed to streamline and revolutionize game development, leverages data collected over years from Xbox gamers and their...

Elon Musk’s AI startup, xAI, has unveiled its latest artificial intelligence model, Grok 3, claiming it surpasses top competitors, including OpenAI and China’s DeepSeek. According to xAI, early testing—including evaluations in math, science, and coding—suggests Grok 3 has achieved superior performance compared to existing models. Grok 3 Launch and Features The new AI model will be rolled out starting Tuesday...