AI Film Monthly · October 2026
AITVHOT
This month saw intensive updates to video models. Kling 4.0 supports direct generation up to 30 seconds and multimodal reference, while FLUX 3 Klein achieves 4K generation and multi-image editing with 5.6B open-source weights. The share of AI-generated vertical short dramas overseas jumped to two-thirds, with market size expected to exceed $6 billion. Short drama platforms are accelerating consolidation, with TikTok and WeChat ramping up free short dramas, and Hongguo centrally processing over 20,000 low-quality content pieces. ComfyUI nodes and workflows continue to expand, and Runway launched a no-code creative app building tool.
Kling Releases Kling 4.0, Supporting 3–30 Second Generation and Omni Reference
Kling officially released Kling 4.0 on October 15, 2026, supporting single generations of 3–30 seconds, more stable large-scale motion and complex camera movements, and up to 10 keyframe inputs. Omni Reference can combine up to 15 reference assets in a single generation, including 10 images, 5 videos totaling no more than 30 seconds, and 7 elements, and prompts can be used to make targeted modifications to existing assets' subject, background, expression, camera position, and style.
Model releases/updates
In this sectionOpen-source weight video models are increasing, and synchronized audio and multi-reference are becoming standard.
Black Forest Labs releases FLUX 3 Image Klein open-weight model
Black Forest Labs releases FLUX 3 Image Klein, a 5.6B-parameter open-weight model that supports text-to-image, image editing, and multi-reference generation with up to 10 reference images, and features native 4K generation, pixel-level editing, and bounding-box control.
Hao AI Lab open-sources FastH3 OmniRef, with ComfyUI support on day one
The FastVideo team at Hao AI Lab has open-sourced FastH3 OmniRef, which generates video with synchronized audio from a prompt plus reference images, short video clips, or sound. The model needs only 8 steps instead of 50, is up to 11.9 times faster than the base MiniMax-H3, has entered the ComfyUI 0.42.2 workflow templates, and has open weights and training code.
Kling 4.0 officially launched, supporting 30-second single-take shots and multi-frame references
Kling AI officially launches the video model Kling 4.0, supporting direct output up to 30 seconds; previously, in late September, 4.0 Flash early access was opened to some Black Gold annual card and Ultra annual subscribers. The author tested scenarios including city chases, circuses, elevator fights, and figure skating, and believes it has improved in understanding physical laws, complex action transitions, and camera scheduling.
Tencent Hunyuan open-sources world model Hy-Nomas, supporting interactive video generation from text and camera trajectories
Tencent Hunyuan has open-sourced its world model Hy-Nomas, which supports free interaction using text prompts and camera trajectories and has long-horizon generation capability with world memory. The model provides lightweight LoRA adaptation for vertical domains such as robotics; after 8-step distillation it can generate 720p@24FPS video on a single RTX 4090. The weights are now available on Hugging Face and GitHub, along with an online Demo.
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.
ComfyUI launches FLUX 3 Max, supporting image-to-video and text-to-video workflows
ComfyUI launched FLUX 3 Max, a latency-optimized version of FLUX 3 Video that can generate 10-second 720/768p clips with native audio in about 12 seconds. The official release also provides links to two workflows, image-to-video and text-to-video, and lists use cases such as comparing multiple candidates, previewing motion while tuning parameters, batch-producing ad variants, and keyframe-guided storyboards.
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.
LTX 2.5 Explained: An Open-Weight Video Model Supporting Synchronized Audio and Native Multi-Shot
LTX 2.5 is an open-weight AI video model that produces audio and video in the same generation pass and supports multiple coherent shots within a single generation. The model is available in standard and distilled versions; weights can be downloaded, called via a hosted API, or deployed on your own GPU. The official team says the new diffusion video decoder improves performance on faces, textures, on-screen text, and fast motion. The article also documents the process of self-hosting on a remote Nvidia GPU and testing lip-sync and facial consistency with dialogue shots.
Tools and Workflows
In this sectionComfyUI nodes and workflows continue to expand, and Runway launched no-code App Studio.
ComfyUI-RMBG releases v3.3.0, adding interactive canvas compositing and VRMBG video matting nodes
ComfyUI-RMBG releases v3.3.0, adding a Canvas interactive multi-layer compositing node, temporal video matting based on BRIA AI VRMBG-3.0, FeyNoBg fine matting for hair strands and glass, and YOLO26-seg and YOLO11-seg segmentation support.
Flux 3 Klein tutorial: image generation and editing with 10 reference images (BF16/FP8/NVFP4/GGUF)
Flux 3 Klein is a 5.6B-parameter open-weight model that merges text-to-image and image editing into a single model, accepting text prompts and up to 10 reference images and outputting a single image, supporting bounding-box instructions and 4K resolution, with Qwen3-VL-4B-Instruct as the text encoder.
Tencent's video world model Hy-Nomas ported to native ComfyUI nodes, runs on 12GB VRAM
The author ported Tencent's video world model Hy-Nomas to native ComfyUI nodes, with the DiT used as a regular ComfyUI MODEL sampled by the native KSampler, and it runs on just 12GB VRAM.
Runway launches App Studio, enabling no-code creation of custom creative apps.
Runway launches App Studio, allowing users to describe their needs in natural language and build custom creative apps with standalone interfaces without code, generating images, videos, and audio. App Studio includes built-in apps such as Character Swap, AutoComp, and Product Portfolio, built on Brand Kits, Workflows, and Assets. It is included in all paid plans and consumes existing Runway credits.
Hands-on test of Jimeng Short Drama Studio, this may be the most cost-effective use of Seedance 2.5
ifanr hands-on tested Jimeng Short Drama Studio and found that it integrates scripts, assets, storyboards, previsualization, and modifications into a complete short drama creation workflow. Among them, DreamScript handles scripts, Anycook generates characters and scenes, DreamShot breaks down storyboards, the 3D director's stage and intelligent previsualization validate the direction before generation, and segment reshoots and frame capture annotations support local modifications. Seedance 2.5's 720P with reference video generation is equivalent to as low as approximately 0.19 yuan per second.
Stubelius Ultimate H3 0.13 released: chunked generation of MiniMax H3 long videos in ComfyUI, with individual chunks redoable
Stubelius Ultimate H3 0.13 is the author's open-source MiniMax H3 ComfyUI workflow, under the MIT license, made public on GitHub on 2026-10-18.
Platforms and Regulation
In this sectionShort drama platforms are accelerating consolidation, while regulatory governance and distribution licensing are tightening simultaneously.
ByteDance is embedding short-drama feeds into TikTok's main app, using traffic to rewrite the rules of overseas expansion.
ByteDance is embedding short-drama feeds into TikTok's main app in beta testing, and its PineDrama has entered the top 10 of the free iPhone charts in the US, Brazil, and Thailand, using free distribution plus main-app traffic to rewrite the customer acquisition and monetization model for overseas short dramas.
WeChat launches the "Lüpaopao Short Drama" mini program, with all episodes free to watch
Tencent's WeChat quietly launched the "Lüpaopao Short Drama" mini program, whose pages are divided into three main sections: "Free Theater," "Swipe," and "Me." The Free Theater includes categories such as AI dramas, live-action dramas, and animated dramas; all episodes are currently free to watch, with ads inserted between episodes.
Q3 Micro-Drama and Animation Distribution: Taihua Mark Implementation and License Replacement, China Publishing Group Surpasses Tencent
National Radio and Television Administration announced the Q3 2026 distribution licenses for domestic micro-dramas and online animations nationwide, with a total of 338 titles approved for distribution, including 158 micro-dramas with 5,369 episodes and 180 online animations with 1,731 episodes. After the Measures for the Development and Management of Micro-Dramas took effect on September 1, 67 micro-dramas switched to new licenses bearing the Taihua mark. Zhongtu New Reading, with 23 animation licenses, surpassed the Tencent group to become the top licensor for the quarter. AIGC micro-dramas such as Mango TV's 'Never Fall Behind' have launched, and AI companies are beginning to become the main licensed content entities.
Hongguo Short Drama Announcement on Continuously Strengthening Governance of Low-Quality and Homogenized Content
Hongguo Short Drama issued an announcement, declaring further strengthening of governance over low-quality and homogenized content, with focus on excessive emotional rendering and homogenized use of plot structure, core settings, key scenes, character relationships, and audiovisual expression elements. As of October 27, 2026, the platform has centrally handled 20,426 micro short dramas including 《别*****女》.
Industry News
In this sectionThe overseas short drama market is growing rapidly, and investment in AI film and television infrastructure is heating up.
Owl & Co. report: two-thirds of overseas vertical-drama releases in Q3 were AI-generated
Owl & Co.'s latest "What We Watched on Vertical" report shows that in Q3 2026, two-thirds of the vertical dramas released outside China on 20 leading platforms were AI-generated, compared with 3% in Q1 and 28% in Q2.
NRTA report: Overseas micro-drama market size to exceed $6 billion in 2026, up 67% year-on-year
The National Radio and Television Administration released the 'China-ASEAN Micro-Drama International Communication Development Report', which projects that the overseas micro-drama market outside China will exceed $6 billion (approximately 40.162 billion yuan) in 2026, a 67% increase from 2025. The report shows that from January to September 2026, the top 10 micro-drama apps by overseas downloads were all of Chinese background, and 9 of the top 10 by in-app purchase revenue were of Chinese background; among micro-dramas going overseas, the share of AI dramas rose from 15.57% at the end of May to 61.39% at the end of September.
Hengdian joins hands with Volcano Engine on a 235 million yuan AI film and television service platform, while the number of offline film crews drops sharply over the same period
The consortium of Dongyang Deep Space Engine and Volcano Engine won the bid for the Hengdian Film and Television AI Service Platform construction project at 235 million yuan; the tender was launched in July. The project is centered on the Hengdian Film and Television large model and includes 7 deeply enhanced vertical-scenario models, 20 specialized scenario enhancement models, 17 film and television industry professional agents, as well as capabilities such as digital crowd extra generation, actor style transfer, and AI-assisted dubbing, along with a consumer-facing Hengdian Film and Television App.
Tips and Opinions
In this sectionComfyUI tutorials focus on synchronized audio generation, and Google Flow reviews spark discussions on short film creation.
$3.6 billion, top five, 46% local dramas: the short drama overseas market has been reshuffled.
The overseas short drama market landscape has been reshaped: an MPA report set the market size for micro-short dramas outside China in 2026 at $3.6 billion, with the top five platforms accounting for nearly 80%. TikTok launched a paid short drama app, LimeShorts, in the US, forming a three-matrix closed loop with free PineDrama and the main site's Mini Dramas. The share of locally produced dramas overseas rose from 27% to 46%, and AI-simulated human short dramas' share in the top 100 comic drama list surged from 7% to over 60%.
Running MiniMax H3 Fun ControlNet Union video-to-video with synchronized audio in ComfyUI
Stable Diffusion Art released a tutorial introducing how to use MiniMax H3 Fun ControlNet Union in ComfyUI to copy body movements from a driving video while generating 24fps video and stereo audio.
Implementing MiniMax H3 multi-keyframe video and audio generation with a ComfyUI workflow
Stable Diffusion Art released a tutorial on how to use MiniMax H3's Add Guide node in ComfyUI to lock multiple keyframe images, video clips, and audio to specific frame positions on a 24fps timeline, generating a video with stereo dialogue, sound effects, and music in one pass.
Kandinsky 6.0 in ComfyUI: Generating Video with Synchronized Audio and Lip Sync (Including Workflow)
Kandinsky 6.0 is an open-weight multimodal diffusion model released by Kandinsky Lab in October 2026, capable of generating 5-second videos with synchronized 44.1 kHz audio in a single pass, and using <S>...<E> tags to control character lip sync.
Multi-image editing, text-to-image, and native transparent background workflows for Qwen Image 2.1 in ComfyUI
The author tested Alibaba Qwen team's Qwen Image 2.1 in ComfyUI, using a single 7B model to perform text-to-image generation, multi-image editing with up to 10 reference images, and native RGBA transparent cutouts.
Using ComfyUI to Generate Audio-Enabled Videos from a Single Image with MiniMax H3 (Includes Workflow)
Stable Diffusion Art published a tutorial explaining how to use MiniMax H3 (i.e., Hailuo 3.0) in ComfyUI to generate 24fps multi-shot videos with synchronized stereo audio from a single image, with visuals and sound effects generated in the same sampling pass.
MiniMax H3 reference-to-video (ref2va) ComfyUI workflow tutorial
Stable Diffusion Art released a complete ComfyUI workflow tutorial for MiniMax H3 reference-to-video (ref2va), which can combine up to 9 reference images, 3 reference videos and 3 audio clips to generate a 24fps multi-shot video with synchronized stereo dialogue, sound effects and music in one pass.
Google Flow 2026 Review: Can You Use Veo 3.1 to Make a Short Film?
Google Flow can use Veo 3.1 and Gemini Omni to generate videos, but you need to assemble the short film yourself as a sequence of 8-10 second shots. The free version gives 50 credits per day, French subscription starts at 4.99 euros; European users cannot edit imported videos, and Veo 3.1 Qualité does not support reference images. The author calculated the per-minute generation cost for each tier based on official documentation, and noted that Flow is suitable for beginners and trailers, while long-form projects require other tools.