Skip to content
Date and source

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

Oct 15Thu
  1. 可灵官方博客15

    How Kling IMAGE 3.0 Omni uses AI for virtual try-on of wedding veils

    Kling IMAGE 3.0 Omni supports multi-image reference generation, combining a user's wedding photo with veil reference images to preview different veil lengths, lace and wearing positions while preserving the face, hairstyle and wedding dress, and outputs 2K or 4K images. This feature only shows appearance; it cannot reflect fabric weight, the drape when walking, or wearing comfort, and is suitable for narrowing down choices before a fitting.

  2. 可灵官方博客62

    Kling breaks down the 5M+ view short film "The Beat," detailing five capabilities of Kling 4.0

    Kling's official blog breaks down the production process of its short film "The Beat," which has surpassed 5 million views on social platforms. The article explains Kling 4.0's capabilities item by item: native 30-second continuous shot generation, Omni Reference supporting up to 15 multimodal references in a single task, Multi-Keyframe supporting up to 10 keyframes, 10-bit HDR output, and upgraded stereo audio with lip-sync.

    Why it matters: The official blog breaks down the production process of a short film with over 5 million views, explaining Kling 4.0's 30-second native generation, Omni Reference, and 10-bit HDR usage in photorealistic shots.

  3. Higgsfield 官方博客22

    Best AI Product Video Generators for E-Commerce in 2026: Comparing Higgsfield, Creatify, Pippit, and More

    Higgsfield's official blog reviewed the best AI product video generators for e-commerce in 2026, with the core capability being automatically converting product URLs into video ads. Higgsfield Click to Ad generates an 8-second 720p video for approximately $2, automatically scraping product names, descriptions, up to 8 images, brand colors, and logos, and integrating with Marketing Studio's 1500+ templates.

  4. HeyGen Updates78

    HeyGen releases the HeyGen Voice speech model

    HeyGen releases a new speech model, HeyGen Voice, which it calls the first speech model built for video adaptation and which ranks first on the Artificial Analysis speech leaderboard; it is already included in every HeyGen video at no extra charge.

    Why it matters: HeyGen launches its first speech model for video adaptation, allowing creators to assess the room for replacing dubbing and multilingual lip-sync workflows.

  5. Fish Audio · 语音模型54

    Fish Audio releases Drama 3 int4 quantized version, reducing size to 22.1 GB and publishing WER evaluations

    An unofficial int4 quantized version, drama-3-int4, has appeared for Fish Audio's 35B (3B active) multi-speaker TTS model Drama 3, with a download size of 22.1 GB, lower than the original 41.5 GB. The expert layers, attention, and deltanet layers are quantized to int4, while the shared expert MLP remains in bf16.

Oct 14Wed
  1. PixVerse 中文官方博客38

    Kling AI 4.0 prompt guide: camera, motion, and examples

    The Kling AI 4.0 prompt guide proposes a four-part structure: subject, action, scene, camera and style, and emphasizes writing the subject and main action first, with camera and emotion serving the action. The guide recommends writing camera movement instructions with specific terminology, such as "camera slowly pushes in to the subject's face" and "shoulder-height tracking shot," and pairing speed limits with physical cues to control motion. Cross-shot character consistency requires reusing a fixed character block verbatim; text-to-video and image-to-video prompts are written differently, with the latter focusing on directing motion.

  2. PixVerse 中文官方博客30

    Kling 4.0 vs Seedance 2.5: AI video model comparison

    Kling 4.0 and Seedance 2.5 target demanding AI video workflows but have different emphases: Kling 4.0 focuses on cinematic control, longer shots, and high-resolution delivery, suitable for single-subject cinematic shots and brand key visuals; Seedance 2.5 is designed for multimodal reference packs, suitable for reference-heavy material, multi-subject consistency, and iterative work driven by source material.

  3. PixVerse 中文官方博客38

    Kling 4.0 vs Kling 3.0: detailed breakdown of core differences

    Kling 4.0 extends single-generation duration from Kling 3.0's 15 seconds to 30 seconds, expands keyframes from start/end frames to up to 10, and adds multi-reference Omni Reference control plus stereo audio and improved lip sync. Kling 3.0 remains suitable for cost-sensitive short social media videos under 15 seconds and dialogue-driven clips, while Kling 4.0 targets commercial and narrative content requiring longer shots, multiple beats, and high brand consistency.

  4. PixVerse 中文官方博客22

    Is Kling 4.0 free? Credits, limits, and alternatives

    Kling 4.0 is not free for everyone; it is being rolled out in phases, first opening Kling 4.0 Flash to eligible higher-tier members, while free users still mainly use earlier Kling models. Free accounts typically offer one-time sign-up credits and daily refreshed credits, but differ from paid plans in model access, resolution, duration, audio, watermarks, queues, and commercial usage rights. Free access is better suited for testing and learning; before using it for client delivery or paid marketing, check the commercial use terms of the current plan.

  5. PixVerse 中文官方博客22

    How to use Kling 4.0: a step-by-step guide to AI video generation

    Kling 4.0 can generate short AI videos from text ideas or still images, and the guide provides step-by-step workflows for text-to-video and image-to-video. Prompts are organized in four layers: subject, action, scene, camera and style; first validate the idea with the shortest duration, then generate the final long shot. Image-to-video should focus on describing motion rather than restating the image, and the first version should avoid stacking advanced controls such as lip sync and motion brush.

  6. OpenAI News60

    Higgsfield uses GPT-6 Astra to extend AI video from 1 minute to over 10 minutes

    Higgsfield extends AI video generation length from 1 minute to over 10 minutes, powered by GPT-6 Astra. At the same time, it uses GPT-Image-2.5 to improve image precision and GPT-Live to provide a path toward voice-driven filmmaking.

    Why it matters: Higgsfield uses GPT-6 Astra to push AI video length from 1 minute to over 10 minutes, which can be used to assess its usability for feature-length creation.

  7. Comfy 官方博客71

    ComfyUI adds NVIDIA VFX nodes, supporting video super-resolution, frame interpolation, and SDR-to-HDR conversion

    ComfyUI turns NVIDIA RTX video effects into custom nodes, including RTX Video Super Resolution, RTX Video Frame Generation, and RTX Video HDR; the models come with the nodes and run locally on RTX GPUs.

    Why it matters: ComfyUI turns NVIDIA RTX video super-resolution, frame interpolation, and SDR-to-HDR into nodes and improves EXR support, which can be evaluated against existing VFX workflows.

  8. HeyGen Updates22

    HeyGen October 2026 enterprise edition update: member usage limits, Video Agent collaboration, and Brand Glossary rebuild

    HeyGen's enterprise edition this month adds member usage limits and request features; administrators can set each member's usage quota, and members can directly request more quota within HeyGen with one-click approval. Video Agent supports team collaboration in the same session, with multiple people able to send prompts simultaneously while only one person edits at a time. Brand Glossary has been rebuilt, supporting per-language pronunciation and translation rules and CSV/Excel import and export; ElevenLabs is integrated as a single engine with a new v4 model option.

  9. HeyGen Updates42

    HeyGen October 2026 enterprise API update: Video 1.0 API, ElevenLabs v4, and Professional Voice Clone launch

    HeyGen released its October enterprise API update: the HeyGen Video 1.0 API is live, supporting short video generation from prompts, images, or reference materials. ElevenLabs v4 can be used for speech synthesis with per-request model selection, and Professional Voice Clone trains studio-grade voice clones based on HeyGen's proprietary speech model, supporting full-file or streaming output.

  10. Fish Speech 官方发布72

    Fish Audio releases the open-source speech generation model Drama 3 pre-release version

    Fish Audio releases the open-source speech generation model Drama 3 pre-release version, which can convert text into performed speech. The model uses a 35B-A3B hybrid linear attention MoE backbone (initialized from Qwen3.5) and a new codebook-MTP audio decoder; pretraining covers about 80 languages and dialects and hundreds of billions of tokens, and it supports multi-reference voice cloning, natural language instructions, multi-round revisions, multi-character scenes, speech infill editing, and long-audio and streaming synthesis.

    Why it matters: Open-source speech models put multi-character scenes, multi-round script revisions, and voice editing into the same model, allowing dubbing workflows to assess replacement potential accordingly.

Oct 13Tue
  1. Higgsfield 官方博客36

    Which is cheaper: per-second AI video API pricing or subscription plans: 2026 scaled cost comparison

    Higgsfield compared the cost differences between per-second AI video API pricing and credit-based subscription plans at scale. Using a baseline of 300 usable 8-second 720p clips per month with two generations per clip, Kling 3.0 on the Higgsfield API costs $0.084/second, totaling $403.20, while the Ultra subscription at $129 includes 3,000 credits, with each 8-second clip costing 16 credits.

  2. Black Forest Labs · FLUX 模型78

    Black Forest Labs releases FLUX 3 Image Klein open-weight model

    Black Forest Labs Releases FLUX 3 Image Klein, a 5.6B Open-Weight Model That Simultaneously Supports Text-to-Image, Single-Reference Image Editing, and Multi-Reference Image Combination Generation, with Qwen3-VL-4B-Instruct as the text encoder.

    Why it matters: The 5.6B open-weight model unifies text-to-image, single-image editing, and multi-image combination into a single model, and provides quantized versions with VRAM usage details, making it easier for self-deployers to assess implementation costs.

  3. Black Forest Labs · FLUX 模型76

    Black Forest Labs Open-Sources FLUX 3 Image Klein Base, 5.6B Weights Support Text-to-Image and Multi-Image Editing

    Black Forest Labs has released FLUX 3 Image Klein Base on Hugging Face, an open-weight model with 5.6B parameters. Text-to-image, single-reference image editing, and multi-reference image composition share the same model, with the text encoder being Qwen3-VL-4B-Instruct.

    Why it matters: The 5.6B open weights cover text-to-image, single-image editing, and multi-image composition simultaneously, and provide three tiers of VRAM usage—BF16, FP8, and NVFP4—making it easy to evaluate self-hosting costs.

  4. 辽宁省广电局 · 通知公告8

    Liaoning Provincial Radio and Television Bureau Announces 16 Outstanding Works from the First Batch of the 2026 "Liaoning Stories · Era of Light and Shadow" Micro Short Drama Script Call

    The Liaoning Provincial Radio and Television Bureau and the Liaoning Writers Association announced the first batch of review results for the 2026 "Liaoning Stories · Era of Light and Shadow" micro short drama script call. After preliminary review, re-review, and public notice, 16 outstanding works were selected. The complete list is available in the notice attachment.

  5. 辽宁省广电局 · 通知公告22

    Liaoning Province Announces 2026 "Micro Short Drama+" Key Project Review Results: 30 Selected, Including 10 AI Dramas

    The Liaoning Provincial Party Committee Propaganda Department and the Provincial Radio and Television Bureau announced the 2026 Liaoning Province "Micro Short Drama+" key project review results. A total of 30 key projects were selected, including 20 live-action dramas and 10 AI dramas. Selected projects went through preliminary review, re-review, and public notice. Relevant departments require production agencies to advance creation and provide guidance and support for project filming.

  6. pyvideotrans 官方发布40

    pyvideotrans v4.16 Released: Fixes Edge-TTS 403, Adds audio.cpp and fish.audio Dubbing Channels

    pyvideotrans released v4.16, fixing the Edge-TTS 403 issue and adding two new dubbing channels: audio.cpp and fish.audio API. This version also adds the Atlas Cloud translation channel, a French WebUI interface, and includes "use LLM to re-segment sentences instead of LLM error correction" in the advanced options for subtitle translation.

  7. Descript · 官方产品更新22

    Descript October update: global search, asynchronous recording requests, and ElevenLabs v4 voice cloning

    Descript released its October update, adding a search bar and a full results page to the entire cloud drive, and supporting Underlord in finding files, folders, projects, and layout packs. Enterprise cloud drives can send asynchronous recording requests, letting guests record on their own schedule and read scripts with a teleprompter; AI Speech has been upgraded to ElevenLabs v4, making voice clones closer to the real person.

  8. Synthesia · 官方博客22

    Best AI training and onboarding video tools of 2026: Synthesia, Colossyan, HeyGen, Elai, Vyond compared

    Synthesia was rated the top AI video tool for enterprise training and onboarding scenarios in 2026, followed by Colossyan, HeyGen, Elai and Vyond. Synthesia's Enterprise plan offers unlimited duration, but SCORM and glossary features require the Enterprise plan; HeyGen suits translating existing live-action footage, with the Creator plan at $29/month and the Business plan at $149/month plus $20 per seat.

Oct 12Mon
  1. 腾讯 ARC · 创作模型60

    Tencent ARC Open-Sources Multi-Person Video Generation Model Multics

    Tencent ARC released Multics on Hugging Face, achieving scalable multi-person video generation through layered communication. The repository includes the complete 4-player Multics DiT checkpoint, configuration, Wan2.2 VAE, UMT5 text encoder, and tokenizer; the same checkpoint supports 6-, 8-, and 10-person generation without retraining. The weights are distributed under the Apache 2.0 license.

    Why it matters: Tencent ARC open-sources the multi-person video generation model Multics, where the same weights can scale to 10 people, letting creators evaluate generation options for multi-person scenes.

  2. Higgsfield 官方博客62

    Higgsfield launches Katana: replicating edits inside Claude based on a reference video

    Higgsfield released Katana, an editing skill that runs inside Claude, calling Higgsfield models through the Higgsfield MCP connector; using a reference video or a preset from the preset library plus up to 5 photos of people, products, or clothing, it reconstructs a new video that preserves the reference clip's shot order, duration, and audio track, with results appearing in the conversation and in Higgsfield Assets.

    Why it matters: Hand the reference clip's shot order, rhythm, and audio-track structure to Katana inside Claude to replicate it, so creators can judge whether manual matching cuts can be skipped.

  3. 昆仑万维 · SkyReels8

    Kunlun Wanwei SkyReels releases Matrix-Game-4.0

    Kunlun Wanwei SkyReels launched Matrix-Game-4.0. The model is currently not deployed by any Inference Provider and does not yet support online inference calls. The README on its model page is empty, and the platform does not track download counts for the model.