Image, Video & Audio

AIAI-generated summary Dior debuted an animated holiday short film titled Christian Dior's Night in Color that Dior Creative Director Jonathan Anderson stated was entirely hand-drawn using techniques from the 1940s. Viewers and digital artists subsequently spotted potential artificial intelligence errors in the video, prompting backlash and skepticism regarding the luxury brand's craftsmanship claims.

AIAI-generated summary Researchers combine video generation with 3D reconstruction to create environments along a chosen camera path using Lyra 2.0. Lyra draws on earlier views to correct visual errors and help the world stay consistent during exploration.

AIAI-generated summary Maket has launched a feature called Text to Furniture that lets users build 3D furniture objects. Users can describe items to have Maket create a 3D model that accounts for height, width, and depth.

AIAI-generated summary Mito describes orchestrating over 5,000 AI assets for a 120-second national television campaign for Movistar Plus+ during the World Cup. Mito says the production workflow utilized Google Cloud infrastructure including Cloud Run and Vertex AI to handle rendering and model disparity challenges.

AIAI-generated summary Voxtral 3 features end-of-turn detection to help developers identify when a user has finished speaking. According to @MistralAI, the tool makes it easier to build responsive voice interactions.

AIAI-generated summary GPT Image 2.6 is now available for users inside Runway. Runway says the integration lets users generate images 50% faster, create GIFs, export SVG vectors, and make precise edits while maintaining consistent characters, products, and brand details.

AIAI-generated summary Unite.AI evaluated platforms including OpenAI, Google, BytePlus Seedream, and Black Forest Labs for developer use cases such as generation, editing, and integration requirements. The guide notes that OpenAI leads for general applications, Google suits multimodal workflows, and BytePlus Seedream focuses on reference editing and structured asset creation.

AIAI-generated summary Wizstar has announced the release of Wizshot 1.0, its first in-house reference-to-video model designed to balance high visual quality with lower generation costs. The new model supports multiple reference images, generates videos up to fifteen seconds long, and is now available to logged-in users.

AIAI-generated summary Max Richter told Mishal Husain that artificial intelligence systems were built using stolen data. Richter stated that human composers ought to receive payment when artificial intelligence utilizes their work to create music.

AIAI-generated summary Startup Underdog released a browser-based game called Woof to showcase its new 32MB frontier text-to-speech model. Underdog says the model runs on most devices without an internet connection and contains 31 million parameters.

AIAI-generated summary YouTuber Mark Rober told Business Insider that creators can combat generic automated videos by going out in the real world and performing real actions. Rober also stated that his company, CrunchLabs, earned around $17 million in revenue last year while breaking even on its YouTube channels.

AIAI-generated summary An eight-person team used the NadouPro platform to reconstruct a lost 1938 film titled Visiting Shanghai after Sixty Years, iQIYI announced on November 6, 2026. iQIYI says the NadouPro platform helped keep character appearances consistent and allowed the team to control camera angles and positioning during the two-month production.

AIAI-generated summary Google is rolling out an image editing tool called Google Pics within Google Docs and Slides for users with specific accounts and subscriptions. Users can access the desktop-specific feature to edit specific image elements or generate new images using plain-English instructions and Workspace collaboration.

AIAI-generated summary AnyToSpeech is a web-based artificial intelligence text-to-speech and voice cloning platform available through PCWorld. A lifetime subscription to AnyToSpeech is currently on sale for $34.97 using the promo code SAVE5.

AIAI-generated summary Select WhatsApp users can now access a Meta AI-powered photo expansion tool inside the app's photo editor. According to WABetaInfo, the feature is currently rolling out primarily to select users in the beta program via TestFlight.

AIAI-generated summary Meta announced that Muse Voice is now available to users in the U.S. for video chatting and calling with the consumer AI agent. The feature uses Muse Realtime Avatar and Muse Realtime Voice technology to power an animated character that interacts with users.

AIAI-generated summary OpenAI launched its next-generation image generation model called Images 2.6 on Wednesday, bringing updates that include quicker use of reference images and the ability to create GIFs from text. OpenAI says that image creation is up to 50% faster than before, and the model is now available in ChatGPT, Codex, and the API.

AIAI-generated summary Google states that Gemini Omni 1.2 Flash is rolling out starting today to all Google AI subscribers. Google states that Google AI Ultra subscribers can now create and edit videos up to 15 seconds long.

AIAI-generated summary Meta announces the rollout of real-time voice conversations and expressive avatars in the Muse app on mobile, web, and Mac in the US. Meta says the new features allow users to talk through ideas, practice for interviews, and choose from hundreds of different voices.

AIAI-generated summary Suno says users can now start a song by dragging and dropping a MIDI file onto the Create page or choosing MIDI from the menu. Suno says the feature uses Simple Create mode with v6-wild at launch and is available to all Pro and Premier subscribers.