Skip to content

Latest picks

  1. Video modelsGoogle DeepMind

    Genie 4 is now available.

    Genie 4 is now available to Google AI Ultra subscribers, supporting real-time world editing during sessions and real-time native audio. Genie 3 has been updated in sync, with single generations up to 3 minutes long, supporting 360-degree panorama seeds and real-time world events; new Project Genie agent and community gallery have been added.

  2. ToolsComfy 官方博客

    Custom ComfyUI is now available on Comfy Cloud

    Comfy officially announced that Comfy Cloud now supports custom ComfyUI setups (Custom Builds) for teams, allowing custom nodes, models, and LoRAs to run in the browser.

  1. ToolsRecraft 官方博客

    Recraft Studio launches Seedance 2.5 Flash: faster speed, with a 720p resolution cap.

    Recraft Studio has launched ByteDance's Seedance 2.5 Flash, which generates about twice as fast as Seedance 2.5 and supports 480p/720p, 4–30 second videos with audio, at 15–32 credits per second. Compared with Seedance 2.5, Flash is capped at 720p and costs fewer credits, making it suitable for storyboarding and exploration; final rendering still uses Seedance 2.5.

  2. TutorialsKrea 官方博客

    2026 Review of the 8 Best AI Video Face Swap Tools, Prices Verified

    Krea's official comparison of 8 AI video face swap tools, with selection recommendations based on free quota, maximum duration, resolution, watermark, and price. Krea Video Swap and Higgsfield Genjutsu are suitable for full-character replacement, Magic Hour offers 3 free face swaps per day, and Vidnoz supports videos up to 50 minutes long. All data comes from the official websites of the respective vendors, verified on November 17, 2026.

  3. ToolsHeyGen Updates

    HeyGen releases Avatar 6 personal digital human.

    HeyGen releases Avatar 6 personal digital human, which can perform according to scripts, and 84% of testers could not distinguish real from fake. Avatar 6 supports script-driven gestures and expressions, learned from up to 30 seconds of video and one photo, and existing Avatars and Looks can be used directly.

  1. Video models可灵官方博客

    Kling releases Kling Image 4.0, focusing on realism and native 8K generation.

    Kling has released its next-generation image generation model, Kling Image 4.0, now available on Kling Creative Studio and open to enterprises and developers via API. The model is based on a native unified understanding and generation architecture, supporting native 8K image generation, text rendering of up to 2000 characters per image, generation of up to 10 consistent-style images from a single prompt, and long-image generation such as e-commerce detail pages. It also offers 110+ preset color grading styles, 70+ preset commercial fonts, and support for seven languages.

  1. TutorialsWaveSpeedAI 官方博客

    AI Video Character Consistency: A Single-Shot Workflow

    WaveSpeedAI's Dora shares an AI video character consistency shot workflow, using character reference kits, fixed identity details, and two-pass review to avoid character drift. Vidu 2.0 accepts 1-3 reference images, MiniMax H3 Highspeed accepts up to 9 reference images and 3 reference videos; when fixing drift, change only one input at a time.

  2. Video modelsZyphra · Zonos 语音模型

    Zyphra releases ZONOS3-Mini multilingual TTS model

    Zyphra releases compact multilingual TTS model ZONOS3-Mini, supporting 43 languages, with approximately 100 million active parameters per token, and provides a native transformers port. The model uses ZAC-1 codec as audio tokenizer, includes 27 built-in release voices, supports voice cloning from short audio, and is licensed under Apache-2.0.

  1. TutorialsHiggsfield 官方博客

    How to Create AI Videos Directly in ChatGPT (Complete Guide)

    Creating AI videos in ChatGPT requires connecting video apps through the plugin directory. This guide covers the categories and billing rules of 17 plugins, including Higgsfield, Runway, HeyGen, and invideo.

  2. TutorialsHiggsfield 官方博客

    How to Create a Faceless YouTube Channel with AI (Complete Guide)

    Higgsfield's official blog published a complete guide teaching creators how to create a faceless YouTube channel from scratch using AI, with the example channel being Statues With a Story. The guide clarifies YouTube's requirement to disclose realistic AI-generated content and lists the new thresholds for new applicants to enter full YPP starting February 1, 2027: 8,000 hours of watch time or 20 million Shorts views.

  1. ToolsHeyGen Updates

    HeyGen Releases November 2026 Enterprise API Update

    HeyGen releases November 2026 enterprise API update: Video 1, Voice 1, and Image 1 are now available via API, enterprise rate limits have been increased, zero data retention coverage has been expanded, and v1/v2 will be retired on November 7, 2026. Video 1 supports text/image/reference video to video and generates dialogue and sound effects, Voice 1 supports Instant Clone and voice-to-voice, and Avatar V adds more natural blinking.

  1. Video modelsZyphra · Zonos 语音模型

    Zyphra releases open-source speech model ZONOS3-Mini

    Zyphra releases open-source compact speech model ZONOS3-Mini, with approximately 100M active parameters, capable of real-time operation on phones, laptops, and browsers. The model supports cloning voices from audio samples, designing characters by age/accent/timbre, and word-by-word control of emotion, speaking rate, and expression. Weights are open-sourced under Apache 2.0, and it can be served via SGLang-Omni on NVIDIA GPUs with an OpenAI-compatible interface.

  2. ToolsComfy 官方博客

    ComfyUI October Update: Multiple Improvements Including Branch Nodes, LoRA Stacking, and Link Organization

    ComfyUI's October update brings multiple efficiency improvements including branch nodes, LoRA stacking, automatic template downloads, multi-output zip export, EXR/HDR/ProRes support, link organization, and in-widget undo/redo, all included in v0.44. Branch Node supports up to 32 inputs, LoRA stacking node supports up to 20 LoRAs, and template downloads are limited to official templates.

  1. Video models字节 Seed 官方博客

    Seedream 5.5 released: supports 100 rounds of stable editing and native RGBA output.

    ByteDance released the next-generation image generation model Seedream 5.5, which supports 100 rounds of multi-round editing, native RGBA transparent background output, and improved image realism and text rendering. Compared with Seedream 5.0 Pro, the usability rate across six production scenarios has improved, with film/TV and office scenarios exceeding twice the previous version; the severe text corruption rate dropped to 0.4%.

  2. ToolsInvokeAI 官方发布

    InvokeAI 7.0.0 beta 1 released

    InvokeAI 7.0.0 enters beta 1, its largest version update. It adds projects, a single workbench, and video panel support for MiniMax H3, LTX-2.5, and Wan 2.2. Official warning: v7 database migration is irreversible; back up before upgrading.

  1. TutorialsHiggsfield 官方博客

    Cinema Studio 4.0: The Complete Guide to Cinematic AI Video Production

    Higgsfield releases Cinema Studio 4.0: The Complete Guide to Cinematic AI Video Production, explaining through aperture, lighting, and camera movement settings how to make the visuals serve the scene's objective. The guide uses same-scene comparison tests to show the differences between f/1.4 and f/11, Contre jour and Soft cross, Handheld and Static shot, and provides reusable prompt structures and setting combinations.

  1. TutorialsKapwing 创作指南

    7 video editing tasks that can be automated with ChatGPT or Claude

    Kapwing tested automating seven types of video editing tasks with ChatGPT or Claude, covering editing planning, subtitle generation, translation dubbing, and B-roll production. In the test, Claude Code with FFmpeg built and rendered a 70.7-second YouTube Short, while Kapwing MCP completed AI dubbing in five languages. The article notes that standard chat interfaces cannot directly edit videos; actual editing requires a coding agent or an editor connected via MCP.

Browse all news