ByteDance quietly upgraded its Seed 1.0 audio generation model with timestamp pinning for dialogue, allowing creators to lock spoken lines to exact timestamps instead of relying on the model's default…
Google DeepMind reconstructed Pelé's 1959 "lost goal" using Veo 3, Gemini Omni, and Nano Banana Pro, informed by nearly 2,000 historical records and eyewitness interviews. The project, built with Pelé…
A multi-agent AI video generation workflow can turn a single topic prompt into a scripted, voiced, and edited video in minutes, according to a guide that assigns dedicated AI agents to writing, voiceo…
Picturesque AI built a creative studio that integrates over 50 models for images, video, audio, editing, and motion control into a single interface with unified billing. The engineering team developed…
ByteDance is set to launch Dreamina Seedance 2.5, reportedly on July 9, enabling AI video generation up to three minutes. The update extends from short clips to 30-second standard and 180-second exten…
Google has introduced Gemini Omni Flash, a multimodal AI model that enables real-time conversational video editing, allowing users to swap elements, restyle scenes, and make edits through natural lang…
Google's Gemini Omni Flash and ByteDance's Seedance 2.5 take fundamentally different approaches to AI video, with Gemini excelling as a multimodal reasoning engine for video analysis and workflow orch…
Google's Gemini Omni Flash API enables conversational video editing through plain language prompts, allowing users to upload footage, analyze scenes, and generate edit instructions without traditional…
Google made Nano Banana 2 Lite (gemini-3.1-flash-lite-image) generally available and launched Gemini Omni Flash in public preview, expanding its lineup of fast, cost-efficient generative media tools. …
Elon Musk's xAI, now under the SpaceX umbrella, launched Grok Imagine Video 1.5 in early June 2026, offering 720p video generation with synchronized audio and competitive API pricing. The expansion co…
OpenAI signed a multi-year display deal with Getty Images to show licensed photos in ChatGPT, boosting Getty's stock by ~145%. ByteDance teased Seedance 2.5, a 30-second AI video generator with single…
Elon Musk's xAI plans to produce a full-length AI-generated movie by the end of 2026, starting with an Alice in Wonderland demo. The company's Grok Imagine Video 1.5 model, launched in June 2026, can …
OpenMontage, the first open-source agentic video production system, has been released, enabling AI coding assistants to handle research, scripting, asset generation, editing, and final composition fro…
Google released multiple Workspace updates on June 17, 2026, integrating Gemini with Google Classroom for education, enabling longer Veo videos and parallel generation in Google Vids, enhancing AI ava…
Google Vids announced that AI avatars are now available for free users, with the Workspace video creation tool serving 7 million monthly users. Free users get 10 video generations per month, and paid …
Google deprecated multiple Imagen 4 image generation models and Veo video generation models in the Gemini API on June 15, 2026, with shutdown dates of August 17, 2026 for Imagen 4 and June 30, 2026 fo…
Text-to-video AI has matured from experimental clips to hyper-realistic cinematic content, driven by a shift from U-Net to Diffusion Transformer (DiT) architectures. DiT offers linear scalability with…
YouTube's crackdown on AI-generated slop is inadvertently penalizing legitimate faceless creators who produce entirely human-made content, as the algorithm now favors videos with on-camera hosts. The …
Google DeepMind's animated short 'Dear Upstairs Neighbors' screened at the Tribeca Film Festival, showcasing a hybrid workflow where concept art fine-tuned custom builds of Google's Veo and Imagen mod…
Elon Musk's xAI released Grok Imagine Video 1.5 in preview, an image-to-video model that generates short 720p videos from a single still image. Users control camera movement, pacing, and atmosphere th…