Skip to content
Date and source

Dates follow the news timeline in Beijing time and include both endpoints.

Feb 18Wed
Feb 3Tue
Jan 27Tue
  1. Hugging Face Blog22

    Architecture Choices in China's Open-Source AI Ecosystem: How MoE, Multimodality, and Domestic Hardware Can Surpass DeepSeek

    Chinese open-source models have nearly unanimously shifted to MoE architecture, with Kimi K2, MiniMax M2, and Qwen3 all adopting this approach, aiming for sustainable deployment at controlled costs. Open-source activity expanded to multimodality and agents starting February 2025, with StepFun's Step-Audio-R1.1 voice model outperforming closed-source models, and Tencent open-sourcing Hunyuan Video and Hunyuan 3D.

Jan 21Wed
Jan 20Tue
  1. Hugging Face Blog65

    Overworld Releases Real-Time Interactive Video Diffusion Model Waypoint-1

    Overworld releases the real-time interactive video diffusion model Waypoint-1, controllable via text, mouse, and keyboard. Weights are now available on Hugging Face Hub, including Waypoint-1-Small, with Waypoint-1-Medium coming soon.

    Why it matters: The real-time interactive video diffusion model is open-sourced, allowing evaluation of its real-world performance in interactive world generation on consumer-grade hardware.

Jan 14Wed
  1. Google DeepMind82

    Google DeepMind Updates Veo 3.1 Ingredients to Video with Native Vertical Output and 1080p/4K Upscaling

    Google DeepMind updates Veo 3.1 Ingredients to Video, making reference-image-based video generation more expressive and adding native 9:16 vertical output for the first time, targeting mobile short-form content such as YouTube Shorts.

    Why it matters: The Veo 3.1 Ingredients to Video update brings native vertical output and 1080p/4K upscaling, enabling creators to evaluate short-drama production workflows.

Jan 6Tue
Dec 24Wed
Dec 12Fri
Dec 11Thu
  1. OpenAI News62

    Disney and OpenAI Reach Agreement: Over 200 Characters to Enter Sora

    Disney and OpenAI reach an agreement to bring over 200 characters from Disney, Marvel, Pixar, and Star Wars into Sora for fan-created short videos. The agreement emphasizes responsible AI in entertainment and includes Disney's company-wide use of ChatGPT Enterprise and the OpenAI API.

    Why it matters: Disney and OpenAI reach a character licensing agreement, offering a window into how mainstream film and TV IP and video generation platforms are implementing copyright collaborations.

Sep 30Tue
  1. OpenAI News80

    OpenAI Releases the System Card for the Sora 2 Video and Audio Generation Model

    OpenAI releases the next-generation video and audio generation model Sora 2 and publishes its system card. Compared to Sora, the new model shows improvements in physical accuracy, realism, synchronized audio, controllability, and style range; the official statement notes that these capabilities were difficult for previous video models to achieve.

    Why it matters: OpenAI publishes the system card for Sora 2, listing capability changes such as physical accuracy and synchronized audio, allowing comparison with the previous generation to assess the upgrade magnitude.

  2. OpenAI News70

    OpenAI Releases Sora 2 and the Sora App, Emphasizing Safety First

    OpenAI releases Sora 2 and the Sora app, calling it the most advanced video model and a new social creation platform, and in response to the new safety challenges it brings, builds safety into the foundation and takes specific protective measures.

    Why it matters: OpenAI simultaneously explains its safety design approach when releasing Sora 2 and the Sora app, providing insight into the official framework for addressing safety challenges in video models.

Jul 23Wed
  1. Hugging Face Blog29

    TimeScope: How Long of a Video Can Video Large Models Actually Understand?

    The long-video understanding benchmark TimeScope has been open-sourced on Hugging Face. By inserting 5–10 second "needle" segments into videos ranging from 1 minute to 8 hours, it evaluates three capabilities: local retrieval, information synthesis, and fine-grained temporal awareness. Results show that leading vision-language models, including Gemini 2.5-Pro, still struggle significantly with true long-video temporal understanding, and performance degrades more noticeably as video length increases.

Jul 17Thu
Apr 11Fri
  1. Hugging Face Blog22

    Visual Salamandra Released: Extending 7B Multimodal Understanding to Images and Video

    The Language Technology Lab releases Visual Salamandra, extending the capabilities of the Salamandra large model to images and video. Based on a 7-billion-parameter foundation model, it integrates the Google SigLIP-So400m encoder with a 2-layer MLP projector, employing a four-stage training process and a late-fusion architecture.

Feb 24Mon
Feb 20Thu
Feb 12Wed
Jan 31Fri
  1. Hugging Face Blog22

    AI Art Tools Monthly Report Issue 1: A Review of Key Advances in Image and Video Generation in 2024

    The Hugging Face blog launches the first issue of the AI Art Tools Monthly Report, reviewing key releases in the creative AI space in 2024. In image generation, diffusion models have shifted from U-Net architectures to DiT and flow matching. Flux.1 surpasses Midjourney v6.0 and DALL·E 3 (HD) on multiple benchmarks, while SDXL remains the mainstream foundation for personalized and controllable generation.

Jan 27Mon
  1. Hugging Face Blog60

    The Diffusers Team Surveys the State of Open-Source Video Generation Models and Optimization Approaches

    The Hugging Face Diffusers team publishes an article surveying the state of open-source video generation models and introducing how Diffusers supports these models. The article lists open-source models such as CogVideoX, Mochi-1, HunyuanVideo, Allegro, and LTX-Video, noting that high resource requirements, generalization ability, and latency are the main limitations.

    Why it matters: The Diffusers team systematically surveys the state of open-source video models and provides an optimization combination that reduces HunyuanVideo's VRAM usage to approximately 6.5GB.

Dec 9Mon
  1. OpenAI News82

    OpenAI's Video Generation Model Sora Officially Launches

    OpenAI's video generation model Sora is now available at sora.com. Users can generate videos up to 1080p resolution and up to 20 seconds in length, supporting widescreen, portrait, and square aspect ratios. Users can import their own assets for extension, remixing, and blending, or generate entirely new content from text.

    Why it matters: Sora is now officially available, and creators can learn about its basic generation specifications including resolution, duration, and aspect ratio.

Oct 23Wed
  1. Hugging Face Blog22

    CinePile 2.0: Building a stronger long-form video QA dataset with adversarial refinement

    CinePile 2.0 is released, an upgraded version of the long-form video QA dataset CinePile, using a newly proposed adversarial refinement method to improve data quality. The original CinePile was released in May 2024, containing approximately 300,000 training samples and 5,000 test samples. Humans outperform the best commercial vision models by 25% and open-source models by 65% on this benchmark. The team also open-sourced the implementation of the adversarial refinement method, which can be used to enhance existing datasets.

Sep 23Mon
  1. Hugging Face Blog34

    FineVideo: How the open-source video dataset with 43k videos and 3.4k hours was built

    To address the scarcity of open-source video datasets, the team built FineVideo, which contains 43k videos totaling 3.4k hours, annotated with rich descriptions, narrative details, scene segmentation, and QA pairs. The dataset starts from 1.9M English videos from YouTube-Commons, filtered by word density and visual dynamism, with content annotation and structured output completed using Gemini 1.5 Pro and GPT-4o.

Jun 20Thu
Mar 25Mon
Feb 15Thu
  1. OpenAI News82

    OpenAI Research: Video Generation Models as World Simulators

    OpenAI explores large-scale training of generative models on video data, jointly training text-conditioned diffusion models on videos and images of varying durations, resolutions, and aspect ratios, using a transformer architecture that operates on spatiotemporal patches of video and image latent codes. Its largest model, Sora, can generate one-minute high-fidelity videos. Results indicate that scaling video generation models is a promising path toward building general-purpose physical world simulators.

    Why it matters: OpenAI publicly reveals Sora's technical roadmap for the first time, explaining how video generation models can be scaled into physical world simulators.

Jul 20Thu
  1. Hugging Face Blog22

    One year of the Hugging Face Diffusers library: a look back at progress in text-to-image, video, and 3D models

    Hugging Face's Diffusers library has reached its one-year anniversary, having expanded from text-to-image to video, 3D, and image editing. The library has added support for models such as DeepFloyd IF, SDXL, VideoFusion, Text2Video-Zero, and OpenAI Shap-E, and integrates LoRA, Torch 2.0 optimizations, and safety checking components.

Jul 17Mon
  1. Hugging Face Blog60

    Hugging Face builds an AI WebTV video stream with Zeroscope and MusicGen

    Hugging Face released an experimental AI WebTV demo that uses the open-source text-to-video model Zeroscope and the music generation model MusicGen to automatically generate and stream short videos.

    Why it matters: It breaks down the complete pipeline for building an automatically generated video stream with Zeroscope, MusicGen, and FILM, and includes failure cases and prompt suggestions.

May 8Mon
  1. Hugging Face Blog30

    A deep dive into text-to-video models: development and challenges from GANs to diffusion models

    A Hugging Face blog post traces the development of text-to-video models: early GAN- and VAE-based methods were limited by low resolution and short duration, after which Phenaki, Make-A-Video, NUWA, VideoGPT, CogVideo, and others shifted to transformer architectures, while current mainstream approaches use diffusion models. Text-to-video must ensure spatiotemporal consistency across frames and faces three major challenges: high compute costs, scarce high-quality datasets, and vague video descriptions; models can typically generate only very short clips.

Jan 3Tue
Nov 25Fri
  1. Hugging Face Blog12

    Hugging Face and Jonathan Whitaker Launch Diffusion Models Course and Host Livestream Event

    The diffusion models course by Hugging Face and Jonathan Whitaker will be released on November 28, offering free instruction on diffusion model theory and applications. To accompany the course launch, a community livestream event will be held on November 30, featuring talks by the creator of Stable Diffusion and researchers from Stability AI, Meta, and other organizations, focusing on high-level introductions to diffusion models and tools for building applications.