Ruby takes a finished SDR clip and converts it up to 16-bit HDR, exporting ProRes files and EXR sequences instead of a flat 8-bit master. Runway says the model, announced on X, works on any uploaded video or generated…
Atlas turns footage from a few ordinary cameras into a space-time capture that can freeze action and generate new viewpoints after filming. In its Atlas launch post, World Labs says the model reconstructs spatial stru…
Adobe announced a generative media tool for Premiere that lets editors select a gap in the timeline, describe the video or audio they need, and generate a clip the company says fits the surrounding shots. The same ann…
Danny Boyle used roughly 30 seconds of generative AI in Ink, his drama about the launch of The Sun, to animate a pair of old photographs and to add mice running through the tabloid's newsroom. He laid out the specific…
The Gemini API can now read long video by letting the model jump around the timeline and pull only the frames, audio, and transcript it needs, rather than sampling the whole clip up front. Google's video understanding…
Runway's Solaris renders an interactive interface as a live visual stream, generating each frame in response to clicks and drags instead of converting a design into code first. The company introduced it as its first I…
WorldClaw, a new paper from Tencent Hunyuan, describes a text-to-3D system that builds large, explorable scenes and returns editable, instance-level assets rather than a single locked render. The method leans on plann…
LTX-2.5 generates connected shots that hold character, environment, lighting, and voice across cuts, then outputs native 4K HDR and a RAW workflow for professional color and finishing. The open-weights model runs on h…
Custom LoRA training for MiniMax H3 is now live on fal, and the company demonstrated it with Realism People, an open-source LoRA it says pushes the model toward photorealistic humans.
MiniMax detailed H3, a general-purpose omni-modal model that the company says understands text, images, video, and audio in a single system, then generates video with native stereo audio at up to 2K resolution and 15…
Dreamina has launched Seedance 2.5, which it calls a new cinematic video model, in an announcement on X. The company positions the release around native long-form generation and direct plugins for two core 3D applicat…
Ideogram launched P-Image, a family of image models co-developed with PrunaAI, according to the company's announcement on X. The company says pricing starts at $0.003 per image, the models render native 1K and 2K outp…
Anthropic released Claude Opus 5, a new top-tier model built to run long, multi-step agents, and it lands at the same price as the previous Opus model. Opus 5 is available now across Claude.ai, the Claude API, Claude…
NVIDIA used its SIGGRAPH announcements to line up a wave of creative software behind Model Context Protocol (MCP), the open standard that lets an AI agent read an application
NVIDIA's Synthetic Video Detector Puts a Deepfake Score Inside Newsroom Workflows July 20, 2026 NVIDIA introduced the Synthetic Video Detector NIM microservice at SIGGRAPH, adding an AI-assisted signal that flags whether a video clip contains synthetic content. It is part of
Alibaba's Qwen team has opened preview access to Qwen3.8-Max , a 2.4-trillion-parameter model the company describes as its most capable system yet, with open weig
Google has open-sourced GNM Head , a parametric 3D statistical model of the human head that gives artists slider-level control over facial identity and expression. The release is th
Moonshot AI’s Kimi K3 is a 2.8-trillion-parameter mixture-of-experts model with a 1-million-token context window and native multimodal input. The important detail for produc
NVIDIA's ARDY Generates Controllable Human Motion in Real Time, and Releases the Code and Weights July 17, 2026 NVIDIA's Spatial Intelligence Lab published ARDY , a framework that generates 3D human motion in real time from text prompts a user can change while the charact
Thinking Machines Lab released Inkling , its first in-house AI model, and put the full weights up for download. It is an open-weights, multimodal Mixture-of-Experts model that ta
Foundry launched Griptape Enterprise, a new license tier of its Griptape AI workflow orchestration platform built to run generative pipelines entirely inside a studio'
Mirelo AI and Kyutai open-sourced MuScriptor , an audio-to-MIDI model that takes a finished music mix and transcribes every instrument at once into separate MIDI tracks. Mos
Robbyant, an embodied AI company inside Ant Group, released LingBot-World 2.0 , an open-source real-time world model that builds an explorable environment from a single image. The model is liv
Shanda's Alaya Lab released AlayaWorld , an interactive world model that generates video environments you can steer in real time, and published it as a full-stack open-source framewo
