Search “Video”

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

SenseTime Open-Sources SenseNova 6.8 Code2Video Model and Skill

SenseTime has released and open-sourced SenseNova 6.8 Code2Video, a lightweight model that creates and renders short videos by generating executable code, and has already achieved preliminary results in visual composition and motion design. The accompanying Skill supports turning ideas into videos and modifying them through follow-up instructions, and can also reconstruct reference videos into editable code. SenseTime has also open-sourced the model weights, the Skill, and the prompts and complete generation trajectories behind each demo video; these videos were all generated in a single run from a single prompt.

OpenAI Releases GPT-6.1 Terra, Priced 50% Lower Than the Previous Version

OpenAI has released a new model, GPT-6.1 Terra, priced at $1 per million input tokens and $5 per million output tokens, 50% cheaper than GPT-6.1 Sol's $2 and $10. OpenAI says the model is fast and efficient, combining visual reasoning with precise computer operation, and excels at tasks such as drafting proposals, filling out forms, and editing videos. This is OpenAI's fourth consecutive model price cut, and Anthropic also cut the price of Haiku 5.5 by 90% in October.

Google DeepMind Releases Genie 4 Real-Time World Model with Native Audio Generation

Google DeepMind has released the Genie 4 world model as a research preview to trusted testers; it can generate explorable worlds in real time from text and image prompts, and natively generate ambient sound, music, and character dialogue. The model introduces Gemini 3.8 Flash as a planner within the simulation loop, responsible for breaking down goals, inspecting frames, and replanning, which DeepMind calls an early step toward hybrid world models. Genie 4 is hosted only on Google's platform and will later be opened to AI Ultra users and Gemini API partners; all video and audio carry SynthID watermarks.

Google DeepMind Releases World Model Genie 4

Google DeepMind has released the world model Genie 4, which supports real-time text-based scene modification, native ambient sound, and interactive dialogue, with Gemini 3.8 Flash serving as the real-time director in the background. The author says it no longer pre-renders video, but instead simulates physical collisions in real time and dynamically loads scenes as the player acts. Currently, the limit for a single simulation is about two minutes; over time, details will drift, and it is only a research preview available to a small number of testers.

Google DeepMind releases the world model Genie 4, supporting real-time text-based scene changes and native ambient sound

Google DeepMind has officially released the world model Genie 4, which supports real-time text-based scene changes, comes with native ambient sound and interactive dialogue, and has Gemini 3.8 Flash serving as the behind-the-scenes director. Unlike pre-rendered video models, Genie 4 simulates physical collisions in real time as the player acts within the scene, and a single simulation can remain continuously stable for about two minutes. The author believes its real purpose is to provide a low-cost physical training ground for embodied agents, but it is currently still a research preview available to only a few testers, and details drift over time.

Google DeepMind releases Gemini 4 Carbon, topping Artificial…

Google DeepMind has released Gemini 4 Carbon, which ranks first on the Artificial Analysis Intelligence Index v5 with a score of 59 and leads in 4 of 9 evaluations including HLE-Diamond and TB-Science. The model focuses on cybersecurity and long-horizon tasks, claiming 88.2% on SEC-bench Pro, 54.8% on ExploitGym, and 71.0% on CWE-bench, and is initially available only to trusted cybersecurity personnel through the Fairwind Program. In terms of specifications, it supports a 1M token context and 1M maximum output, with input covering text, images, video, and speech, and output in text; Artificial Analysis lists a standard price of $4/$20 per million input/output tokens, plus a 50% launch discount.

Ant Group's inclusionAI Open-Sources 2B Visual Forensics Model DefakerOne2

Ant Group's GuangJian team has open-sourced DefakerOne2 on GitHub, a 2B-parameter unified visual forensics model built on the Qwen3.5-2B multimodal backbone, covering AI-generated content, DeepFake faces, document tampering, natural image tampering, face and ID anti-counterfeiting, and AI-generated video detection. The model was trained on approximately 50 million samples, employs a three-stage Tide-Style Tuning process from LoRA to full parameters and back to LoRA, and uses entropy-based test-time routing to select between the video and frame pathways. The team claims that it achieves SOTA on 40 of 53 detection benchmarks and on 11 of 14 localization benchmarks, and that the weights and the RRVBench benchmark have been released on ModelScope.

OpenAI Releases GPT-6.1 Terra Model

OpenAI has released a new model, GPT-6.1 Terra, which focuses on speed and efficiency, strengthens visual reasoning and precise computer operation, and writes more clearly and naturally. Starting today, the model is being rolled out to Plus, Pro, Enterprise and Edu users in ChatGPT Work and Codex; the company says it can cover work scenarios ranging from interpreting technical drawings and drafting proposals to filling out forms and editing videos.

Moonshot AI releases Kimi K3.1 Pro, calling it the strongest 3T-class model

Moonshot AI releases Kimi K3.1 Pro, which the company calls its most capable 3T-class model. The tweet only gives the model name and scale positioning, along with a video link, and does not disclose specific parameters, evaluation results, or release method.

Kling 4.0 launches on fal and opens its API

Kling 4.0 has publicly launched on the fal platform, with its API open to all customers. The model supports native video generation with audio up to 30 seconds, up to 15 image/video/element references, and precise control of up to 10 keyframes, and improves motion, character consistency, and cinematic storytelling.

Viggle AI releases world foundation model JST-2

Viggle AI announced that the world foundation model JST-2 was released three days ago, supporting text, image, or video input and outputting 3D characters, motions, and scenes. The official release also compiles works created by community users with it since its release.

Kling 4.0 Launches on the fal Platform

Kling 4.0 is now available on the fal platform. It is a new-generation native multimodal video model that improves the stability of complex motion, reference consistency for characters and scenes, and control precision for cinematic storytelling. It is currently available only through fal UX and fal Agent, with API access coming soon.

English translation is being prepared.