Search “Video”

Ant Group's GuangJian team releases visual forensics model DefakerOne2

Ant Group's GuangJian team has open-sourced the visual forensics model DefakerOne2 on GitHub and released the model weights. The model is built on the Qwen3.5-2B multimodal backbone with 2B parameters, covering AI-generated content, DeepFake faces, document tampering, natural image tampering, face and ID anti-counterfeiting, and AI-generated video detection. The team says the model was trained on about 50 million samples, using a three-stage Tide-Style Tuning process from LoRA to full parameters and back to LoRA, and employs entropy-based test-time routing to choose between the video and frame pathways. The team also says it achieved 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.

Google DeepMind releases Gemini 4 Argon

On October 23, 2026, Google DeepMind released the frontier model Gemini 4 Argon. Google's official blog stated that the model performs outstandingly on complex tasks such as coding, mathematics, and 3D world building, and surpasses other frontier models on benchmarks across multiple domains; the company also showcased five community creative projects, including a 3D Earth that maps wildfires and seismic waves in real time, a turbofan engine simulation with live data, a 3D horse-drawn carriage generated from a single image, and a multiplayer capture-the-flag browser game, and said the model had already been made broadly available last week. On the same day, another report stated that Argon can learn physical tasks by watching videos and transfer them to Apptronik's Apollo humanoid robot, with Apollo hitting seven consecutive shots in internal tests; the report also said Argon scored 87% on the embodied reasoning benchmark ERQA. On October 24, the Gemini for Android app pushed a redesign of its sidebar and settings interface via a server-side update, and reports said the redesign had already arrived on iOS, macOS, and Web alongside Gemini 4 Argon last week.

Viggle AI releases world foundation model JST-2

Viggle AI announced the release of the world foundation model JST-2. According to its description, the model supports text, image, or video input and outputs 3D characters, motions, and scenes. The official side also compiled works created by community users using the model since its release. There is currently no further follow-up development information.

English translation is being prepared.

English translation is being prepared.

fal says FLUX 3 Max scored 1,139 Elo in third-party evaluation

fal says FLUX 3 Max achieved 1,139 Elo on a third-party benchmark, entering the top tier of frontier image-to-video models based on independent human preference evaluations. The model was launched through a collaboration between fal Research and bfl_ai. Earlier reports said that through dedicated post-training and inference optimization, the model tied for first place in image-to-video quality on an independent third-party benchmark, generating a 10-second 720/768p video in about 12 seconds; other reports said it scored 1,139 on the Artificial Analysis image-to-video index, with generation speeds up to 22 times faster than Seedance 2.5. fal Research says it is continuing to post-train the model and will subsequently improve quality and performance.

VAST open-sources real-time world model EdenLive

English text is being prepared.

English translation is being prepared.

fal says FLUX 3 Max is the fruit of a frontier collaboration between the two parties

On October 20, 2026, fal announced a collaboration with Black Forest Labs to launch the FLUX 3 Max video generation model, and said that FLUX 3 Max is the result of a collaboration between two frontier teams. According to fal, the model can generate a 10-second video in 12 seconds, is tied for first place in the image-to-video category, and is 22 times faster than Seedance 2.5 at the same quality. Black Forest Labs said that FLUX 3 is a model oriented toward customization, and fal adapted and optimized it into FLUX 3 Max. At present, this news has only been released by fal, with no subsequent independent developments yet.

Viggle AI Releases World Foundation Model JST-2

Viggle AI has released the world foundation model JST-2. According to the company, the model is described as the world's first full-stack physics-native world foundation model; rather than learning in pixel or video space, it builds the entire model stack in 3D space from first principles. It can generate 3D scenes in seconds and extend them in real time, and can also create characters with built-in motion through the same general architecture. This news currently comes from a single-source report, with no further independent evidence or follow-up developments yet.

Kling AI announces full availability of KLING 4.0

On October 15, 2026, Kling AI announced the full availability of KLING 4.0, which users can access through a redesigned creation interface and which supports integration into video creation workflows via MCP and CLI; the company also previewed upcoming 4K and 1080p 10-bit HDR video output, as well as API access for enterprise customers and developers. On October 17, fal previewed the imminent launch of Kling 4.0, saying it can generate videos up to 30 seconds long in a single pass, supports native audio, and can use up to 15 reference materials to guide characters, scenes, and camera movement. On October 20, according to The Decoder, Kling AI released version 4.0, which can generate videos up to 30 seconds long in a single pass, supports input of up to 10 keyframe images, extends prompt understanding to 8,000 tokens, adds dual-channel stereo audio and lip sync in more than ten languages, and introduces Kling 4.0 Flash, a lightweight version supporting up to 720p and 20 seconds. On October 22, Kling announced the official opening of the KLING 4.0 API, allowing developers to integrate it into their own products and workflows, but did not disclose details such as interface capabilities, pricing, or availability scope.

Elorian releases its first AI model, Glimpse

On October 17, 2026, Elorian released its first AI model, Glimpse. According to Testing Catalog, Glimpse can, during its thinking process, return to a specific point in a video, zoom in on details, or replay half a second of video at a higher frame rate before answering. Elorian's own testing shows that Glimpse outperforms GPT-6 Astra in reading scientific charts and describing short videos; in a simulated task of planning for a robotic arm to place cream cheese into a bowl, Glimpse cost $0.035, compared with $0.249 for GPT-6 Astra; in a demonstration, Glimpse solved 5 mazes of increasing difficulty, while Gemini 3.8 Flash solved 1/5. Another report the same day said that Elorian positions Glimpse as the first visual reasoning model, used to compare scene changes at different points in a video, and calls this frame-based reasoning visual thinking; during its reasoning process it can return to the source video, crop regions, extract specified frames, or run code to measure and compare what it sees, a mechanism called visual scratch space; co-founder Andrew M. Dai said it has frontier performance competitive with Astra on key public visual reasoning benchmarks. At present, there have been no further evidence-supported developments since the model's release.

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.

English translation is being prepared.