AI Film Daily · Saturday, October 17, 2026
AITVHOT
Kuaishou Kling 4.0 fully rolled out, generating videos up to 30 seconds in a single pass
Kuaishou Kling AI announces that Kling 4.0 is officially fully rolled out on klingai.com, generating videos up to 30 seconds in a single pass and supporting multiple extensions up to 2 minutes. The new version improves the stability of large camera movements such as high-speed motion, tracking shots, and orbiting shots, refines character lip-sync matching accuracy, supports 4K and 1080p 10-bit HDR output and 21:9 ultra-wide aspect ratio, and accepts up to 10 images, 5 videos, and 7 subjects per input.
Model releases/updates
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.
Kling 4.0 hands-on test: how do 30-second direct output, 15 references, and 10 keyframes perform?
Kling 4.0 is fully launched, with a single native generation of up to 30 seconds, support for combining up to 15 reference materials such as images and videos, and input of up to 10 keyframes; the company says it has strengthened stability for high-speed motion and large camera movements such as tracking and orbiting shots.
Alibaba TaoLive AIGC releases the TaoMate-H3-FL2VA first-and-last-frame control LoRA
The Alibaba TaoLive AIGC team released TaoMate-H3-FL2VA on October 15, a 3-step LoRA that adds first-frame and last-frame control to MiniMax H3's streaming TaoMate-H3 runtime; the team calls it the first known real-time streaming first-and-last-frame-to-audio-video (FL2VA) model.
Kling releases 4.0 video generation model
Kling's official account released 4.0 with the caption "The art of 4.0" and the hashtags #Kling4 and #KlingAI. The quoted @2x_labs content said Kling 4.0 has been officially released, with the slogan "Define the next frame with imagination."
OpenMOSS releases open-source image model MOSS-Image
OpenMOSS has released the image model MOSS-Image, with SFT and Base versions now available on Hugging Face, along with ComfyUI integration instructions. The model is trained on 3.2B images, uses the Apache 2.0 license, supports JSON and BBOX input but does not require them, and is compatible with both natural language and booru tag prompts.
Tools and Workflows
ComfyUI template tutorial: go from sketch to multi-shot ad without building a workflow
ComfyUI released a template tutorial demonstrating how to use ready-made templates on comfy.org and the built-in template browser to take a single sketch all the way to a 3D toy, retail packaging and a multi-shot ad.
ElevenLabs launches Instant Soundtracks in ElevenCreative
ElevenLabs Launches Instant Soundtracks in ElevenCreative; After Uploading a Video, the Model Generates an Original Score and Analyzes Sound Effect Cue Points in the Footage, Automatically Placing Sound Effects on the Timeline at the Corresponding Timestamps.
Platforms and Regulation
WeChat launches the "Lüpaopao Short Drama" mini program to compete with Hongguo for the free short drama market
The WeChat Short Drama Content Center launched the "Lüpaopao Short Drama" mini program in late September, with the slogan "Free good dramas, watch with one tap," featuring three sections: Free Theater, Swipe, and Me; it adopts a joint distribution model and inserts ads between episodes. The company disclosed that after integration, user time spent is 5 times that of the overall WeChat short drama market and retention is more than 2.5 times the market average, and high-quality new dramas under joint distribution with per-user watch time of ≥10 minutes can receive up to 100% revenue incentives.
Tips and Opinions
FLUX 3 Image Klein released: a 5.6B open-source model supporting generation and editing with 10 reference images
FLUX 3 Image Klein is released, a 5.6B-parameter open-weight model that merges text-to-image and image editing into a single model, can accept a text prompt plus up to 10 reference images and output a single image, supports bounding-box editing instructions and in-image text rendering, and supports resolutions up to 4K.
Hands-On with MOSS-Image 5B INT8 Quantization and 8-Step DMD on a 12 GB RTX 3060
The author tested MOSS-Image (5B single-stream DiT, Qwen3.5-9B text encoder, FLUX.2 VAE, Apache 2.0) on a 12 GB RTX 3060 using 35 difficult prompts and a single seed (42), without cherry-picking images and including failure cases.
"Bu Shao Xin" (Not Heartburn) surpasses 2.2 billion views: how AI short dramas mass-produce nationwide memes
As of October 13, the "Bu Shao Xin" topic derived from AI short drama dialogue has surpassed 2.2 billion views on Douyin and over 57 million views on Xiaohongshu, spilling over into contexts such as food, pet care, and the workplace. The article argues that its breakout stems from plain values, high production capacity, and Hongguo Short Drama's distribution capability: according to National Radio and Television Administration statistics, AI dramas account for over 90% of the 430,000 micro short dramas launched in the first 8 months of this year; as of July 2026, Hongguo Short Drama reached 168 million daily active users and 125 minutes of average daily usage per person per month.