Adobe has launched a major update to its Firefly AI platform, including new image generation models and a redesigned web app that now features AI models from competitors. The company introduced Firefly Image Model 4, which Adobe claims offers improved quality, speed, and greater control over image outputs with resolutions up to 2K. A more …
Character.AI has announced AvatarFX, a new video generation model that can animate both AI characters and uploaded images. According to the company, the technology can generate photorealistic videos with audio that maintain consistency in face, hand, and body movements, even for long-form content. The system builds on diffusion model architecture with a parameter-efficient training pipeline …
Google has released Veo 2, its text-to-video AI model, to Gemini Advanced subscribers globally. Starting April 15, 2025, users can generate eight-second videos in 720p resolution by entering text prompts in the Gemini app. The feature, which Google claims delivers “cinematic realism” with improved physics and human motion understanding, is available through a dropdown menu …
Adobe has released version 25.2 of Premiere Pro, featuring new AI-powered tools including Generative Extend. This feature, powered by Adobe’s Firefly AI model, allows editors to extend video clips by up to two seconds and ambient audio by up to ten seconds. As Jess Weatherbed reports, the tool is free for a limited time before …
Runway has unveiled its latest AI video generation model, Gen-4, touting significant improvements in character and scene consistency. According to Kyle Wiggers, who reported on the release, the model is now available to Runway’s individual and enterprise customers. The company claims Gen-4 can maintain coherent environments and characters across different scenes while accurately simulating real-world …
Moonvalley has introduced Marey, a new AI video model trained solely on legally acquired and licensed content. According to Carl Franzen of VentureBeat, this approach addresses copyright concerns plaguing many competing AI video models that use scraped web content. Moonvalley CEO Naeem Talukdar stated, “People said it wasn’t technically feasible to build a cutting-edge AI …
Snapchat has launched its first AI Video Lenses powered by its in-house generative video model. According to Aisha Malik at TechCrunch, these new features are exclusively available to Snapchat+ subscribers who pay $15.99 monthly. The initial release includes three lenses: “Raccoon,” “Fox,” and “Spring Flowers,” with more planned weekly. Users can access these lenses through …
Poe, a platform for exploring and comparing AI models, has released its “Early 2025 AI Ecosystem Trends” report revealing significant shifts in user preferences across text, image, and video generation models. According to the report, OpenAI and Anthropic dominate text generation with approximately 85% of message share, while newcomers like DeepSeek and Google’s Gemini are …
OpenAI plans to incorporate its AI video generation tool Sora directly into ChatGPT, according to company leaders during a Friday Discord session. As reported by Maxwell Zeff, Sora is currently only available through a dedicated web app launched in December. Rohan Sahai, OpenAI’s product lead for Sora, indicated that while the ChatGPT integration is being …
Alibaba Group has made its video and image generation AI model Wan 2.1 publicly available as open source. Reuters reports that four variants of the model are now accessible globally through Alibaba Cloud’s ModelScope and HuggingFace platforms for academic, research, and commercial use. The most powerful variants can process up to 14 billion parameters, enabling …