Skip to content
Date and source

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

Oct 1Thu
  1. note · visiondesigning · 图像视频创作分享22

    ChatGPT with Runway and Midjourney generates a croissant ad: AI video can't be done in 10 minutes

    The author used ChatGPT to generate prompts, paired with Runway (Standard) and Midjourney (Basic) to generate ad-style short clips from multiple croissant photos, then stitched them together and added subtitles in Canva (Pro). For voiceover, ChatGPT (Plus) × HiggsField (Free) was used, but the voice did not meet expectations, so the final cut used Instagram with BGM and no narration. Runway's remaining credits were insufficient, and only 5 seconds of an ad of the same specification could be reproduced.

  2. note · eeeemo_japan · 图像视频创作分享66

    MiniMax open-sources video generation model H3: runs locally, supports Omni Reference

    MiniMax freely released the open-source video generation model MiniMax H3 in August 2026; it can be installed and run on your own computer, reducing the cost of repeated regeneration to electricity. It supports Omni Reference, allowing up to 9 images, 3 videos, and 3 music tracks as references to maintain character and scene consistency; according to ASCII.jp, its cloud version's performance is considered comparable to Seedance 2.0.

    Why it matters: The open-source video model pushes the cost of a single generation down to electricity, and the article gives VRAM thresholds and licensing regional restrictions to help assess the feasibility of local production.

  3. note · shiori_ai_diary · 图像视频创作分享22

    AI Image Generation Is So Fun That the Output Folder Completely Lost Control: Developer Casually Built MediaRanker and Listed It on the Microsoft Store

    Because Asakura Shiori had too many AI-generated images to choose from, the developer created a Windows app called MediaRanker that lets users browse images while rating them with ★ marks, and it has been listed on the Microsoft Store. The app supports continuous browsing of images and videos within a folder with direct marking, and the Free version is free with no time limit. The developer stated that more features will continue to be added.

  4. 逛逛GitHub70

    Writing Code to Make Videos with Claude Opus 5.5: 10 Finished Pieces and 5 Open-Source Projects

    The way to make videos with Claude Opus 5.5 is not for the model to directly generate frames, but to have Agent tools such as Claude Code and Codex write HTML, Canvas, WebGL, or Remotion animations, then export MP4 frame by frame, with subtitles, camera paths, and transitions all adjusted in code.

    Why it matters: A video production path using Agents to write HTML, Canvas, and WebGL code and export MP4 frame by frame, with 10 finished pieces and 5 open-source projects available for reproduction.

  5. Theoretically Media blog62

    Early Hands-On with Kling 4, Plus a Look at Gemini 4 Argon, Ideogram 4.5, and Eleven v4

    The author conducted hands-on testing of the Kling 4 early access version, which currently only offers the Flash model with 720p output, available to Ultra subscribers on annual plans; larger models are planned for October. Testing shows that Kling 4 appears to have resolved the lip-sync drift issue from 3.0, supports up to ten keyframe references, but performances are somewhat flat.

  6. SunoMV · AI音乐视频制作32

    Making Music Videos with HeyGen Video: Shots Come with Sound, Try One for 40 Credits

    HeyGen released HeyGen Video on September 30, 2026, supporting text, first frame, or up to 9 reference images as input, generating 5–15 second shots at 480P or 768P with built-in sound. The SunoMV selector deducts credits at list price: 40 credits per 5 seconds at 480P, 60 credits per 5 seconds at 720P; the October half-price promotion of approximately $0.01 per second is not reflected in the selector. This tier does not support first/last frames, 1080P, or native 2K; face locking requires reference images.

  7. SunoMV · AI音乐视频制作30

    SunoMV Shares MV Production Workflow: Storyboard First, Review Samples, Then Lock 1080P

    SunoMV proposes that AI music videos should be produced in the order of 'storyboard first, review samples, then lock 1080P' to avoid rendering shots that shouldn't be kept into clear final cuts. The fast default model does not offer 1080P; only Seedance 2.5 can produce a single segment in 1080P. The window for upgrading a sample to 1080P is 7 days, after which that segment must be reshoot.

  8. Runway48

    Runway releases world interface model Solaris

    At today's AI Summit, Runway CTO Kamil Sindi further introduced our first world interface model, Solaris. A new type of operating system that builds itself as you interact. Every frame is generated in real time based on your intent. In the keynote, Kamil shared a clear vision: in the future, all software will be generated. Without a single line of code. Learn more about Solaris: https://runway.com/news/research/introducing-solaris

Sep 30Wed
  1. LTX-2 官方发布17

    LTX-2 v1.4.1 released

    LTX-2 released v1.4.1, modifying the HDR video encoding process to output decoded data blocks directly as EXR and HLG, no longer retaining the full clip in memory. This version was released by lt-research-bot on September 30 and includes 1 commit to the main branch.

  2. 公众号:短剧自习室0

    Short Drama Weekly | Kling releases Kling 4.0; Douyin, Kuaishou, Volcano Engine, Huolong and other platforms increase short drama incentives

    Kling announced that Kling 4.0 will launch in October, supporting 4K and 1080p 10-bit HDR output and native video direct output of up to 30 seconds in a single generation, up to 15 multimodal reference materials and 10 multi-keyframe inputs, with continuation extending up to 2 minutes.

  3. note · synth_brain · 图像视频创作分享65

    Three ways to make MiniMax H3 high-speed and high-resolution: Fused-Turbo-Int8, Spectrum, and Latent Upscaler

    The author shared a high-speed, high-resolution all-in-one ComfyUI workflow for MiniMax H3, the core of which is replacing the base model with the minimax-h3-fused-turbo-int8-convrot model, which integrates FL2V and Ref2VA, has a built-in 4STEP TurboLoRA and Mystic V2 LoRA that suppresses jitter and ghosting, and is about 21GB in size.

    Why it matters: The author tested MiniMax H3's model replacement and speed-up nodes, providing a comparison showing an 800×800 eight-second video dropping from 7 minutes 13 seconds to 3 minutes 37 seconds, which can be transferred to existing video production workflows.

  4. 公众号:短剧自习室62

    Short Drama Copyright Center upgrades live-action combined with AI short drama incentive program

    The Short Drama Copyright Center upgraded its live-action combined with AI short drama incentive program, applicable to vertical-screen exclusive premiere live-action short dramas launched and released between October 1 and December 31, 2026. Works must have a total duration of no less than 100 minutes, with live-action footage featuring live-action leads accounting for no less than 50% of the total duration and AI-produced footage no less than 5%, with AI mainly used for visual spectacle expression such as special effects, special characters, and fantasy scenes. Qualifying dramas that meet the conditions within 30 calendar days of launch can receive post-verification cash incentives, and finished films can be submitted for evaluation through the short drama creator center's matchmaking model or non-matchmaking model.

  5. 可灵 Kling60

    Kling showcases a short film generated by the full version of Kling 4.0, launching in October

    Kling officially released a short film generated by the full-featured version of Kling 4.0 with all-around reference, and said this version will launch in October. The quoted content mentions that compared with Flash, the full version offers native 30-second direct output, clearer image and sound, more precise lip-sync matching, and a 21:9 cinematic aspect ratio.

  6. 公众号:娱乐资本论22

    Bilibili danmaku AI judges, NetEase group-chat automatic enforcement: September internet patent roundup

    In September, major internet companies published patents密集ly: Bilibili applied for a livestream interaction patent that uses large models combined with danmaku to generate virtual judge commentary; NetEase applied for a group management patent where, after the group owner writes group rules, the system automatically parses them and issues real-time warnings and mutes. Youku is working on one-click script-to-storyboard splitting and video character expression editing, Baidu's ERNIE large model uses multi-agent automatic drafting and revision, Alibaba's Tongyi Wanxiang accelerates AI image generation, and Kuaishou's Kling diagnoses text-to-image shortcomings through layered analysis.

  7. 新腕儿 · 短剧与漫剧行业报道42

    Spring Festival Gala dance "Tang Gong Ye Yan" adapted into a short drama launched on Hongguo, with AI building Tang dynasty scenes

    On September 28, the short drama "Tang Gong Ye Yan: In the Twenty-Fourth Year of Kaiyuan, the Sage's Thousand-Autumn Festival!" adapted from the Henan TV Spring Festival Gala dance of the same name, launched on Hongguo, jointly produced by Hongguo Short Drama, Hangzhou Ruxing Technology, and Henan Luming Pictures. Set against Emperor Xuanzong of Tang's Thousand-Autumn Festival, the drama unfolds along two threads: the palace night banquet and the assassination of An Lushan by Li Shiniang, a disciple of the Pear Garden, and uses AI technology to build Tang dynasty scenes such as palaces and night banquets. The drama is presented by Hongguo's premium short-drama "Guoran Plan."

  8. VibeClips · AI视频创作教程42

    Grok Imagine 1.5 AI Video Generator: Photos to Videos with Sound

    xAI's Grok Imagine 1.5 is a pure image-to-video model: input a single still image to generate a 4- to 15-second clip with synchronized sound, with audio always on and unable to be turned off. Compared with Grok Imagine 1.0, it adds audio generation but no longer supports text-to-video; duration options increase to 4, 6, 8, 10, 12, and 15 seconds, and both support 480p and 720p (720p by default) and seven aspect ratios.

  9. 可灵官方博客71

    Kling 4.0 multiple keyframes tutorial: how to control a 30-second AI video

    Kling officially released a guide to using Kling 4.0 Multiple Keyframes, supporting up to 10 keyframe images per generation, used to set visual nodes on the timeline such as character entrances, product reveals, and scene switches, with the model generating the motion and transitions between the nodes accordingly.

    Why it matters: Kling officially provides a complete method for controlling 30-second long videos with multiple keyframes, including timeline planning and common mistakes, which can be directly transferred to advertising and short-narrative workflows.

Sep 29Tue
  1. 短剧自习室 · 搜狐公开专栏36

    Hongguo Premium Short Drama "Tang Palace Night Banquet" Launches, Using AI to Build High Tang Scenes and Expand Traditional Cultural Expression

    On September 28, the Hongguo premium short drama "Tang Palace Night Banquet: In the 24th Year of Kaiyuan, Long Live the Sage!" launched. Adapted from the dance program of the same name from Henan TV's Spring Festival Gala, the drama was co-produced by Hongguo Short Drama, Hangzhou Ruxing Technology and Henan Luming Pictures. The producers used AI technology to build palace, night banquet and other High Tang scenes, transforming the original dance's visual imagery into character relationships and story threads, and the script was revised more than ten times. The drama was launched under Hongguo's "Guoran Plan."

  2. LTX-2 官方发布62

    LTX-2 Releases v1.4.0, Adding Chunked Long-Video Generation and Keyframe Decoding

    LTX-2 released v1.4.0, adding --chunked to Distilled, the two-stage TI2Vid, A2Vid, Dub-It and IC-LoRA, enabling ultra-long video generation with a default 97-frame window and 25-frame carry, without needing to set --chunk-pixel-frames or --chunk-carry-frames.

    Why it matters: LTX-2 v1.4.0 lists interface changes for long-video generation, chunked decoding and HDR workflows in one place, making it easier for existing workflows to assess migration costs.

  3. 公众号:短剧自习室62

    Exclusive Interview with Xuebao: Zombie Apocalypse — 2026 Through the Eyes of an AI Short-Drama Producer

    Xuebao, founder of Xuebao Studio, described the first half of 2026's AI short-drama industry as a zombie apocalypse in an exclusive interview. After the release of Seedance 2.0, the production process was greatly simplified and output surged, but a DataEye report shows that 221,900 new AI short dramas were added on Douyin in the first half of the year, with a hit rate of only 0.47%.

  4. 卡尔的AI沃茨 · 公众号公开订阅30

    Hands-On with Claude Sonnet 5.5: Code Animation Leads GPT-6 by a Wide Margin, but 3D Modeling Falls Short

    Anthropic has updated Claude Sonnet 5.5, positioning it as the high-speed, low-cost tier of Opus 5.5. Pricing is on par with the previous Sonnet 5, 50% cheaper than Opus 5.5, with output speed 30% faster and per-task costs reduced by up to 30%. In hands-on testing, code-generated 30-second promotional videos, HTML presentations, and 3D web pages showed that its code animation effects lead GPT-6 by a wide margin, but 3D modeling only approaches the level of GPT-6 Sol and falls short of Opus 5.5.

  5. Leeveo AI Tutorials · 创作教程与项目分享40

    How to Create Cinematic Storyboards with ChatGPT

    A creator used ChatGPT to design a professional storyboard for the *Man in the Iron Mask* story, featuring eight shots within 30 seconds — from the prisoner and rescue to the iron mask being revealed, the king's appearance, and the escape. Each shot is annotated with duration, lens focal length, camera angle, camera movement, and action, maintaining consistency in characters, costumes, and dungeon settings. It can be used directly as storyboard preparation before generating video with models such as Seedance, WAN, Kling, Veo, or Hailuo.

  6. Kyutai · 音视频模型20

    Kyutai Releases OVIE-ft-re10k: A Novel View Synthesis Fine-Tuned Model for RealEstate10K Scenes

    Kyutai has released OVIE-ft-re10k on Hugging Face. This is a checkpoint of OVIE fine-tuned for 50K steps on RealEstate10K multi-view data, accounting for only 2% of its 2-million-step pretraining budget. The architecture is identical to the base model, and it can be loaded directly by reusing the same code path.

  7. 毒眸 · 搜狐公开专栏22

    Jingrui AI Creation Contest's First Sharing Session Held at Communication University of China, Exploring the Transformation of AI in Film and Television Production

    China's first AI video creation contest with a total prize pool of ¥10 million, the 'Jingrui AI Creation Contest,' held its first sharing session on September 28 at Communication University of China, co-hosted by Hujing Entertainment Group and the School of Television at Communication University of China. The contest offers 265 award slots with a maximum single prize of ¥2 million, with no restrictions on AI creation tools or subject matter. Registration is open from September 17 to November 22 via the official website or by searching on Youku. Attendees believe that AI expands the boundaries of expression, but the core of telling a good story still lies with the creator.

  8. Leeveo AI Tutorials · 创作教程与项目分享60

    How to Generate a Complete AI Ad Storyboard from a Single Product Image

    The author uploaded a product image of a bag of Brets BBQ chips to ChatGPT, asking it to analyze the packaging, color scheme, and positioning from an advertising director's perspective, producing a 10-shot 9:16 storyboard in the order of: origin, ingredient transformation, production, signature flavor, sensory experience, product experience, lifestyle, product key visual, and brand closing.

  9. VibeClips · AI视频创作教程22

    Which AI Video Models Can Generate Voice and Sound Effects: A Complete Breakdown of VIBE's Audio Models

    Over half of the video models on VIBE can generate audio, divided into three categories: always-on native audio, toggleable audio, and support for uploading user-provided recordings. Sora 2, WAN 2.6/2.7, Veo 3 Fast, and Seedance 2.5 always produce audio; Veo 3.1, Kling 3, and PixVerse 6 feature audio toggles; WAN 2.7, PRUNA V, and Talking Avatar accept user-uploaded voice or music files.

  10. Pika20

    Pika API Club Focuses on Secret Level

    Today, we introduce another member of the Pika API Club—Secret Level @secret__level. As one of the earliest high-end creative studios offering AI-native and hybrid production, we have always been fans of their work. We are delighted to support them and their proprietary film and television production platform Liquid Engine. More about Secret Level 👇