Skip to content
Date and source

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

TodayNov 19Thu2 items
  1. Google DeepMind68

    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.

    Why it matters: Genie 4 is available to Google AI Ultra subscribers, supporting real-time world editing during sessions and real-time native audio, allowing creators to evaluate its interactive world generation, sharing, and re-creation capabilities.

  2. Comfy 官方博客74

    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.

    Why it matters: Teams can run custom ComfyUI setups in the browser without local configuration, with GPU billed per second, suitable for evaluating cloud collaboration and large-scale image generation.

Nov 18Wed
  1. Recraft 官方博客65

    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.

    Why it matters: Recraft officially compared Seedance 2.5 Flash with the flagship Seedance 2.5 using the same set of prompts, so creators can judge how to divide work between exploration and final output.

  2. Krea 官方博客62

    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.

    Why it matters: The eight video face swap tools are compared side by side by free quota, duration, resolution, and price, with recommendations for use cases such as full-character replacement, long videos, and free trials.

  3. Higgsfield 官方博客57

    Higgsfield Short Drama Studio: How to Make an AI Short Drama Series (Complete Guide)

    Higgsfield officially released a complete guide for Short Drama Studio to create AI short drama series, covering script upload, visual style selection, character and scene references, storyboard planning, generation, and export. The tool supports 480p draft, 720p and 1080p quality, and the MCP workflow generates one episode at a time via /short-drama, up to 180 seconds.

  4. 可灵官方博客65

    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.

    Why it matters: The new model unifies visual understanding and image generation in the same autoregressive framework, and its native 8K and long-text rendering capabilities are worth creators evaluating as a replacement for existing image generation workflows.

  5. HeyGen Updates67

    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.

    Why it matters: The new version enhances realism, with 84% of testers unable to distinguish, and creators can use this to evaluate whether to replace their existing digital human production workflow.

Nov 17Tue
  1. 可灵官方博客32

    What is a static shot? Film examples and a Kling 4.0 creation guide

    Kling 4.0 supports static shot creation: Text-to-Video uses prompt formulas to generate fixed-camera scenes, Omni Reference can combine up to 15 reference assets to maintain consistency of characters and scenes, and Creative Recreation can reconstruct fixed-camera concepts based on existing videos. A static shot keeps camera position, angle, and composition unchanged; classic films such as The Searchers and Tokyo Story demonstrate its role in directing attention and creating mood.

  2. 可灵官方博客22

    Kling explores anime style and brings it to life

    Kling AI offers Kling IMAGE 3.0 Omni and Kling 4.0, helping users transform anime style into dynamic videos. Kling 4.0 supports generating 3–30 second videos in a single run; Omni Reference can combine up to 15 references and use up to 10 keyframes to guide motion and camera. Users can create anime characters, backgrounds, and consistent image series through text and visual references.

  3. 可灵官方博客29

    What is a Sizzle Reel? Examples and how to make one with Kling 4.0

    A sizzle reel is a short promotional video that uses footage, images, music, and brief information to spark interest in a brand, product, event, or creative project. Kling 4.0, the video generation and editing model from Kling, can refine existing footage or create new shots. Omni Reference supports combining up to 15 assets to guide subject consistency, camera movement, and pacing, with a single generation lasting up to 30 seconds and producing up to 10 keyframe images.

  4. Kapwing 创作指南58

    Sheru Bhai AI video production tutorial: Prompt and complete workflow

    Kapwing published a Sheru Bhai AI video production tutorial, using Claude Skill to generate character reference images and a complete video prompt, then generating a 15-second vertical video with dialogue in one pass in Seedance 2.5. The tutorial also includes environment reference images, a second-by-second storyboard for an auction scene, AI photo generation methods, and a troubleshooting checklist for character consistency issues.

Nov 16Mon
  1. WaveSpeedAI 官方博客69

    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.

    Why it matters: This workflow provides specific practices for character reference kits, fixed identity details, and two-pass review, and can be directly transferred to multi-shot AI video production.

  2. Zyphra · Zonos 语音模型66

    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.

    Why it matters: ZONOS3-Mini is released as a native transformers port, supporting 43 languages and voice cloning, facilitating evaluation of its suitability as a multilingual TTS baseline.

Nov 15Sun
  1. Higgsfield 官方博客52

    Higgsfield becomes the most adopted image and video AI platform on Ramp

    Higgsfield became the most adopted platform in the image and video AI category in the Ramp Rate November 2026 ranking, with 42% of businesses that purchased such software through Ramp in the past 12 months choosing Higgsfield. Its adoption rate increased by 33 percentage points in a year, ranking first in six of seven rankings; Midjourney ranked second with 35%.

Nov 14Sat
  1. Luma News44

    Recommended Native Audio AI Video Generators: Luma and Google Veo

    Native audio AI video generators can synchronously output dialogue, sound effects, and ambient sound in a single generation; Luma and Google Veo are representative platforms. Luma's Ray 3.2 supports multiple keyframes, HDR, EXR export, and Motion Transfer, and uses Uni-1 to maintain project context. Google Veo is positioned as an enterprise solution with broad platform access capabilities.

  2. Synthesia · 官方博客22

    Synthesia: How to Speed Up eLearning Content Production (While Maintaining Quality)

    Synthesia recommends using a unified intake form, prioritizing requests by scores for business impact, evidence, workload, and urgency, and using AI drafting to speed up eLearning content production while maintaining quality. Its 2027 AI in L&D report shows that 75% of learning professionals believe AI leads to faster content creation, but only 11% mention improved job performance and 35% continuously measure it.

Nov 13Fri
  1. Higgsfield 官方博客67

    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.

    Why it matters: This guide compares the billing rules and capability differences of 17 video apps in the ChatGPT plugin directory, and provides reusable prompt templates to help creators choose tools and control costs.

  2. 美团 LongCat · 创作模型70

    Meituan LongCat releases LongCat-Video-Avatar 1.6, an audio-driven human video generation model.

    Meituan LongCat releases the open-source audio-driven human video generation framework LongCat-Video-Avatar 1.6, which improves lip-sync, coordinated facial and body movements, and long-video consistency compared to 1.5, supports video generation over 10 minutes, and optimizes inference speed.

    Why it matters: The new version improves long-video stability and inference efficiency, and in human preference evaluation it ranks second only to OmniHuman-2.0, providing a reference for selecting digital human video generation solutions.

  3. Podcastle55

    Async Hands-On Test: Comparing Text Editing and Chat Editing AI Video Editing Workflows

    The author tested both text editing and chat editing AI video editing workflows with Async on the same footage, and found chat editing to be generally easier and more flexible, while text editing is better suited for cleaning up long recordings. Text editing involves modifying the transcript to delete or reorder corresponding video clips, whereas chat editing uses natural language commands to change backgrounds, remove objects, add subtitles, and so on. The author did not time the process, and the conclusions are based on actual editing experience.

  4. Higgsfield 官方博客65

    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.

    Why it matters: This guide provides a complete process from topic selection to monetization, and clarifies YouTube's disclosure boundaries for AI-generated content and the new YPP thresholds for 2027.

  5. Synthesia · 官方博客41

    Synthesia Selected for Inaugural 2026 AI 100

    Synthesia has been selected for the inaugural AI 100 list, becoming one of the top 100 private AI companies globally. In 2026, the company completed a $200 million Series E funding round at a $4 billion valuation, and launched Syren, an AI video agent that can turn prompts into brand videos; it also brought video creation into ChatGPT and Claude through MCP integration. The company has over 65,000 customers, including 90% of the Fortune 100.

  6. Luma News21

    Best AI Cartoon Generator: Convert Photos and Prompts into Cartoons and Animate Them

    Luma's AI cartoon generator guide introduces three types of tools: photo-to-cartoon, text-to-cartoon, and animation, emphasizing cross-scene character consistency. Luma's Ray 3.2 supports multi-keyframe sequencing and HDR workflows, and Layers driven by Uni-1 allow individual element editing. Cartoonize.ai offers over 20 art styles, suitable for quick photo-to-cartoon conversion.

Nov 12Thu
  1. Luma News42

    Best AI Character Generator: Maintaining Character Consistency Across Images and Videos

    AI character generators maintain character consistency through reference images, custom model training, and editing workflows. Among them, Luma AI's Uni-1 maintains image character consistency, and Ray 3.2 achieves frame-level identity stability in videos. Reference image workflows can reduce repeated generation, and editing workflows better preserve approved features than full regeneration. A unified platform reduces tool-switching friction and is suitable for cross-scene projects such as brand campaigns, animation, and illustration.

  2. 番茄小说 · 短剧漫剧改编公告21

    Fanqie Novel's 2026 'Wanxiang New Chapter' Creation Plan Officially Launches

    Fanqie Novel officially launches its 2026 'Wanxiang New Chapter' Creation Plan. The page body of this short-drama and comic-drama adaptation announcement consists mainly of footer information such as the Fanqie Novel Network User Agreement, the Fanqie Novel Network Privacy Policy, and copyright inquiry and reporting contact details. It does not disclose specific creation requirements, rights, or schedule.

  3. WaveSpeedAI 官方博客50

    Higgsfield Cinema Studio 4.0 Review: Control and Workflow

    WaveSpeedAI, based on Higgsfield's official documentation, reviews Cinema Studio 4.0, clarifying the division of labor among its control panel, reference images, and prompts, and noting that Web and API capabilities differ. The review recommends that teams first conduct small-scale trials before deciding whether to adopt it.

  4. HeyGen Updates64

    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.

    Why it matters: The HeyGen enterprise API update unifies video, voice, and image models, increases rate limits, and requires migration to v3 after v1/v2 retirement.

Nov 11Wed
  1. Recraft 官方博客68

    Gemini Omni Flash 1.2 launches on Recraft Studio, supporting 15-second video generation.

    Google released the Gemini Omni Flash 1.2 video model on November 5, 2026, and it is now available on Recraft Studio. Compared to 1.1, the single generation duration has increased from 10 seconds to 15 seconds, consistency and lip-sync are clearer, and Gemini API prices have dropped by about 30%.

    Why it matters: The new version increases the single generation duration from 10 seconds to 15 seconds and improves cross-segment consistency and lip-sync, making it suitable for short ad scenarios that need a complete mini-story.

  2. Adobe · 官方创作与影视博客19

    Behind the scenes of Adobe's 'Made to Create' film

    Adobe releases 'Made to Create' film, directed by Santiago Carrasquilla, marking the platform's first cinematic expression. The film brings together over 30 artists from 18 countries, using tools such as Firefly, Acrobat, Frame.io, and Workfront, and went from shooting to final cut in less than a month. The film pays tribute to the creative community and encourages people to turn their ideas into reality with Adobe solutions.

  3. WellSaid · 官方博客55

    WellSaid launches Producer, bringing voice production into the MCP era.

    WellSaid launches Producer, embedding professional voice production into agent workflows such as Claude, Copilot, and ChatGPT via an MCP server, and natively generates 48kHz audio. The platform supports agent style guides based on over 500,000 Oxford Languages transcriptions, open design, and digital human replication, with the license retained with the final audio.

Nov 10Tue
  1. MiniMax · 音视频模型58

    MiniMax releases MiniMax-H3-Image-PE prompt expansion model

    MiniMax releases MiniMax-H3-Image-PE, fine-tuned from Qwen3.8-27B, providing prompt expansion and aspect ratio recommendations for MiniMax-H3-Image. It supports two workflows: text-to-image and image editing. The image editing PE is still under development; only its prompt is released this time. The model runs with FP4 weights and can be deployed via SGLang or Diffusers, requiring approximately 19 GiB of GPU memory.

  2. Zyphra · Zonos 语音模型65

    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.

    Why it matters: With 100M active parameters, it can synthesize speech in real time in the browser, providing a locally runnable open-source solution for localized dubbing and character voices, supporting voice cloning and word-by-word emotion control.

  3. Comfy 官方博客63

    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.

    Why it matters: ComfyUI's October update brings multiple efficiency improvements such as branch nodes, LoRA stacking, and link organization, allowing creators to optimize workflows, reduce repetitive operations, and improve creative efficiency.

Nov 9Mon
  1. 字节 Seed 官方博客63

    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%.

    Why it matters: Seedream 5.5 focuses on 100 rounds of stable editing and native RGBA output. Evaluations show the severe text corruption rate dropped to 0.4%, providing more reliable image assets for professional visual production.

  2. InvokeAI 官方发布75

    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.

    Why it matters: InvokeAI 7.0.0 enters beta, adding projects, a video panel, and multi-model support, giving creators a basis to evaluate the upgrade.

Nov 8Sun
  1. Luma News18

    Midjourney's Limitations: What It Cannot Do

    Midjourney has notable limitations in brand consistency, text rendering, enterprise integration, and professional video production. It lacks a public API, generates images publicly by default, and standard access requires a paid subscription. Text rendering may produce inconsistent characters, character consistency is difficult to maintain, and video output lacks cinematic-level controls such as multiple keyframes and professional export formats.

  2. Luma News16

    Synthesia's limitations: what it cannot do

    Synthesia can only generate digital human broadcast videos, cannot output professional post-production formats such as HDR/EXR, and cannot produce cinematic shots. Script changes require regenerating the entire segment, and it cannot make local edits to already approved elements, making it difficult to meet creative needs such as product launches and brand advertising. Luma's Ray 3.2 provides native HDR and 16-bit EXR export, and Layers allows changing the product, title, or background while preserving other elements.