News from the AI & ML world
DeeperML - #videogeneration
|
Michael Nuñez@venturebeat.com
//
Google has unveiled Gemini 2.5 Flash, a new AI model designed to give businesses greater control over AI costs and performance. Available in preview through Google AI Studio and Vertex AI, Gemini 2.5 Flash introduces adjustable "thinking budgets," allowing developers to specify the amount of computational power the AI should use for reasoning. This innovative approach aims to strike a balance between advanced AI capabilities and cost-efficiency, addressing a key concern for businesses integrating AI into their operations. The model is also capable of generating SVGs.
The introduction of "thinking budgets" marks a strategic move by Google to deliver cost-effective AI solutions. Developers can now fine-tune the AI's processing power, allocating resources based on the complexity of the task at hand. With Gemini 2.5 Flash, the "thinking" capability can be turned on or off, creating a hybrid reasoning model that prioritizes speed and cost when needed. This flexibility allows businesses to optimize their AI usage and pay only for the brainpower they require. Benchmarks demonstrate significant improvements in Gemini 2.5 Flash compared to the older Gemini 2.0 Flash model. Google has stated that the latest version delivers a major upgrade in reasoning capabilities, while still prioritizing speed and cost. The "thinking budget" feature offers fine-grained control over the maximum number of tokens a model can generate while thinking, ranging from 0 to 24,576 tokens. A higher budget allows the model to reason further to improve quality, but the model automatically decides how much to think based on the perceived task complexity. Recommended read:
References :
@Google DeepMind Blog
//
Google has integrated its Veo 2 AI model into Gemini Advanced, allowing subscribers to generate 8-second, 720p videos directly from text prompts. Gemini Advanced users can now select Veo 2 to create dynamic videos, which can be shared on platforms like TikTok and YouTube. These videos are downloaded as MP4 files with a SynthID watermark, ensuring authenticity and traceability. This integration is currently available to Gemini Advanced subscribers and does not extend to Google Workspace business and educational plans.
Google is also adding Veo 2 to Whisk, an experimental tool in Google Labs, where users can create videos from image prompts using the new Whisk Animate feature. With Veo 2, users can create detailed videos with cinematic realism from text prompts. The model is designed to better understand real-world physics and human motion, delivering fluid character movement, lifelike scenes, and finer visual details across diverse subjects and styles. You can create up to eight-second-long video clips in a 720p resolution, which will then generate an MP4 in a 16:9 aspect ratio. The new video model allows you to create what Google calls “detailed videos with cinematic realism” from text prompts. You can create up to eight-second-long video clips in a 720p resolution, which will then generate an MP4 in a 16:9 aspect ratio."By better understanding real-world physics and human motion, it delivers fluid character movement, lifelike scenes, and finer visual details across diverse subjects and styles," Google says. Veo 2 was previously available in early access, allowing users to create 1080p video for 50 cents per second of video generated. Clips are now free to produce for those on Advanced plans, but as with most AI video-generation tools, there’s a limit to how many you can request each month. Google didn't share that limit; it says it will tell users as they approach it. Along with the Veo 2 video tool, Google is also introducing Whisk Animate, which allows you to make your images into 8-second videos using the same tech as Veo 2. This feature isn't as readily available as Veo 2, but if you're in the US, you can access it through Google Labs. Recommended read:
References :
@Google DeepMind Blog
//
Google is integrating its Veo 2 video-generating AI model into Gemini Advanced, allowing subscribers to create short, cinematic videos from text prompts. The new feature, launched on April 15, 2025, enables Gemini Advanced users to generate 8-second, 720p videos in a 16:9 aspect ratio, suitable for sharing on platforms like TikTok and YouTube. These videos can be downloaded as MP4 files and include Google's SynthID watermark, ensuring transparency regarding AI-generated content. Currently, this offering is exclusively for Google One AI Premium subscribers and does not extend to Google Workspace business and educational plans.
Veo 2 is also being integrated into Whisk, an experimental tool within Google Labs. This integration includes a new feature called "Whisk Animate" that transforms uploaded images into animated video clips, also utilizing the Veo 2 model. Similar to Gemini, the video output in Whisk is limited to eight seconds and is accessible only to Premium subscribers. The integration of Veo 2 into Gemini Advanced and Whisk represents Google's efforts to compete with other AI video generation platforms. Google's Veo 2 is designed to turn detailed text prompts into cinematic-quality videos with lifelike motion, natural physics, and visually rich scenes. The system is able to interpret detailed text prompts and turn them into fully animated clips with lifelike elements and a strong visual narrative. To ensure responsible use and transparency, Google employs its proprietary SynthID technology, which embeds an invisible watermark into each video frame. The company also implements red-teaming and additional review processes to prevent the creation of content that violates its content policies. The new video generation features are being rolled out globally and support all languages currently available in Gemini. Recommended read:
References :
@Google DeepMind Blog
//
Google is expanding its AI video generation capabilities by integrating Veo 2, its most advanced generative video model, into the Gemini app and the experimental Whisk platform. This new functionality allows users to create short, high-resolution videos directly from text prompts, opening up new avenues for creative expression and content creation. Veo 2 is designed to produce realistic motion, natural physics, and visually rich scenes, making it a powerful tool for generating cinematic-quality content.
Currently, access to Veo 2 is primarily available to Google One AI Premium subscribers, who can generate eight-second, 720p videos in MP4 format within Gemini Advanced. The Whisk platform also incorporates Veo 2 through its "Whisk Animate" feature, enabling users to transform uploaded images into animated video clips. Google emphasizes that more detailed and descriptive text prompts generally yield better results, allowing users to fine-tune their creations and explore a wide range of styles, from realistic nature scenes to stylized and surreal sequences. To ensure responsible AI development, Google is implementing several safeguards. All AI-generated videos created with Veo 2 will feature an invisible watermark embedded using SynthID technology, helping to identify them as AI-generated. Additionally, Google is employing red-teaming and review processes to prevent the creation of content that violates its policies. These new video generation features are being rolled out globally and support all languages currently available in Gemini, although standard Gemini users do not have access at this time. Recommended read:
References :
Jonathan Kemper@THE DECODER
//
References:
THE DECODER
, MarkTechPost
,
Meta and University of Waterloo researchers have developed MoCha, an AI system capable of generating complete character animations with synchronized speech and natural movements. Unlike previous models that primarily focused on facial animation, MoCha can render full-body movements from various camera angles. This includes lip synchronization, gestures, and interactions between multiple characters.
Early demonstrations of MoCha feature close-up and semi-close-up shots, showcasing the system's ability to generate upper body movements and gestures that align with spoken dialogue. MoCha utilizes a diffusion transformer model with 30 billion parameters to produce HD video clips approximately five seconds long at 24 frames per second. For scenes with multiple characters, users can define characters once and refer to them with simple tags, streamlining the prompting process. Recommended read:
References :
Kara Sherrer@eWEEK
//
Runway AI Inc. has launched Gen-4, its latest AI video generation model, addressing the significant challenge of maintaining consistent characters and objects across different scenes. This new model represents a considerable advancement in AI video technology and improves the realism and usability of AI-generated videos. Gen-4 allows users to upload a reference image of an object to be included in a video, along with design instructions, and ensures that the object maintains a consistent look throughout the entire clip.
The Gen-4 model empowers users to place any object or subject in different locations while maintaining consistency, and even allows for modifications such as changing camera angles or lighting conditions. The model combines visual references with text instructions to preserve styles throughout videos. Gen-4 is currently available to paying subscribers and Enterprise customers, with additional features planned for future updates. Recommended read:
References :
Ashutosh Singh@The Tech Portal
//
Elon Musk's xAI has acquired Hotshot, a startup specializing in AI-powered video generation. Hotshot, founded by Aakash Sastry and John Mullan, has developed three video foundation models: Hotshot-XL, Hotshot Act One, and Hotshot. The move signals xAI's intention to enter the AI video generation market, potentially competing with OpenAI's Sora and Google's Veo 2.
The acquisition will see Hotshot's models scaled on xAI's supercomputer, Colossus, which utilizes a vast number of Nvidia chips. Hotshot trained its models on 600 million video clips, employing techniques like neural networks for automatic captioning and the bfloat16 data format to accelerate AI training. The company discontinued new video creation on March 14, 2025, and allowed existing users to download their content until March 30. Recommended read:
References :
Emily Forlini@PCMag Middle East ai
//
Google DeepMind has announced the pricing for its Veo 2 AI video generation model, making it available through its cloud API platform. The cost is set at $0.50 per second, which translates to $30 per minute or $1,800 per hour. While this may seem expensive, Google DeepMind researcher Jon Barron compared it to the cost of traditional filmmaking, noting that the blockbuster "Avengers: Endgame" cost around $32,000 per second to produce.
Veo 2 aims to create videos with realistic motion and high-quality output, up to 4K resolution, based on simple text prompts. While it's not the cheapest option compared to alternatives like OpenAI's Sora, which costs $200 per month, Google is targeting filmmakers and studios with larger budgets. The primary customers for Veo are filmmakers and studios, who typically have bigger budgets than film hobbyists. They would run Veo throughVertexAI, Google's platform for training and deploying advanced AI models."Veo 2 understands the unique language of cinematography: ask it for a genre, specify a lens, suggest cinematic effects and Veo 2 will deliver," Google says. Recommended read:
References :
Emily Forlini@PCMag Middle East ai
//
Google is enhancing its Workspace platform, with Google Drive now offering searchable video transcripts. This new feature, rolling out to all Google Workspace users by March 26th, allows users to access and search transcripts for videos stored in Drive. The transcripts appear in a sidebar next to the video player, highlighting the currently spoken text, making it easier to find specific moments. Users can enable transcripts by clicking the settings icon and selecting "Transcript," provided the video already has captions, indicated by the "CC" button.
Google DeepMind has announced pricing for its Veo 2 video generation model, setting the cost at $0.50 per second of generated video, translating to $30 per minute or $1,800 per hour. Veo 2 creates videos with realistic motion and high-quality output, up to 4K, from a simple text prompt. This pricing positions Veo 2 as a premium service targeted towards professionals and enterprises, offering a competitive alternative compared to conventional filmmaking methods, despite additional expenses like human labor. Recommended read:
References :
|
BenchmarksBlogsResearch Tools |