Image, video and audio AI covers the software systems that generate, edit and analyze visual and auditory media. Truncated covers new model capabilities, industry releases, copyright debates, and the technical methods behind media synthesis.
AI-generated summary YouTuber sWooZie faced criticism after animator Ashley Nichols stated that her character design was used in an AI-assisted sequence in his latest video. Nichols clarified that she was paid for the original design work, but stated that she would not have wanted it used in that manner.
AI-generated summary Grimes will join the cast of the science-fiction film Gods Don’t Give Gifts, which has announced a U.S. theatrical release on December 4. The studio says the film has launched a campaign for Best Animated Feature Oscar consideration alongside plans for a BAFTA submission.
AI-generated summary SoundCloud rolls out a direct publishing integration allowing users to send generative AI music straight from ElevenLabs without exporting and downloading files first. SoundCloud Artist Pro subscribers receive three months of ElevenMusic Pro for free as part of the partnership, and published songs will be labeled with their AI origins.
AI-generated summary Vmake Labs rolls out an upgraded Subtitle Mode within its Video Watermark Remover designed for advanced subtitle and overlay removal. Vmake Labs states that the update enables teams to remove embedded dialogue text, stylized titles, and watermarks to prepare footage for translation, dubbing, and creative reuse.
AI-generated summary @OpenAI has launched GPT Image 2.6 Sunburst and Flare with enhanced speed running almost two times faster than GPT Image 2.5. @OpenAI reports that Sunburst Medium and Flare Medium deliver enhanced photorealism and greater editing consistency while maintaining the lead over competing labs.
AI-generated summary @OpenAIDevs makes GPT-Image-2.6 available today in Codex and through the API for developers. @OpenAIDevs says Image-2.6 Flare and Sunburst are two new API image models that generate images 50 percent faster than before.
AI-generated summary OpenAI rolls out an update to ChatGPT that lets users generate animated GIFs directly from a prompt or an uploaded photo. The new update also enables faster image generation across ChatGPT and its API alongside additional tools for developers.
AI-generated summary Google Photos version 8.0 code previews a redesigned conversational interface and new capabilities for Ask Photos. The updated feature could allow users to perform bulk actions and complex chained requests directly within the application.
AI-generated summary Walt Disney Co. is testing artificial intelligence video generation tools in a commercial deal with startup OpenArt. The collaboration allows creative teams to generate and evaluate multiple concepts for music lyric videos in hours.
AI-generated summary Whisper World and Rembrand announced their merger and the creation of WRLabs to develop cinematic-quality video editing tools. The combined company plans to offer its AI editing platform through an API and its upcoming VFXAgent.
AI-generated summary ElevenLabs releases SFX v3, its newest sound effects model in the Sound Effects API, which accepts multi-part prompts and handles vocals and music better. ElevenLabs says the model sounds more natural overall and is less likely to clip on high-frequency sounds like gongs, chimes, and kettle whistles.
AI-generated summary Adobe researchers are testing EditAgent, a new system designed to help artificial intelligence use editing tools like a professional working in Photoshop. The system pairs a general-purpose editor with specialized tools and uses measured data to evaluate the results.
AI-generated summary MicrosoftAI previews MAI Image 2.7, which climbed to the third spot on the arena image editing leaderboard. MicrosoftAI states that this represents a forty five point jump from the previous version 2.6.
AI-generated summary Granola launched a dictation feature today that works on Mac just like any other such tool. Users can press the Fn key to start speaking while the tool cleans up and formats their speech across all apps.
AI-generated summary Cartesia released Multilingual Voices, providing over fifty library voices that speak up to twenty-five languages natively and allowing users to make voice clones multilingual. Cartesia says customers can keep the same brand identity everywhere so listeners hear the same voice across different regions and languages.
The top AI news in your email delivered each morning. Choose categories