Skip to content
Saturday, October 24, 2026Daily at 08:00

AI Film Daily · Saturday, October 24, 2026

AITVHOT

No. 1724October 2026Saturday
12stories11sources2first-hand postsAbout 5 min read
Lead

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.

Stable Diffusion Art 教程Original
01

Model releases/updates

SuSu_酥酥

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.

MindStudio Blog · 创作分享

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.

可灵 Kling

Kling 4.0 launches on idea.ai

Kling 4.0 is now available on idea.ai. According to idea.ai, this version can generate a 30-second scene from a single prompt, maintain character consistency across shots, and support switching between live-action, anime, and 3D styles.

02

Tools and Workflows

03

Industry News

IT之家1 other source

China's first AI theatrical feature film "Sanxingdui: Future Past" opens, first-day box office exceeds 125,000 yuan

China's first AI full-process theatrical feature film to receive a public screening license from the National Film Administration, "Sanxingdui: Future Past," released on October 23. As of press time, first-day box office exceeded 125,000 yuan, with cumulative box office of 142,000 yuan.

漫剧出海 · 每日观察

Vertical short dramas shift from a China-going-global playbook to platform infrastructure

Vertical short dramas are shifting from an experimental export from China to default infrastructure built by major platforms. TikTok has brought publishing, viewing, payment, and advertising in-app, while Hollywood studios have simultaneously announced they are entering vertical drama production. On TikTok's side, Minis Center handles viewing unlocks, Drama Center handles content-provider publishing, and Growth Max handles automated advertising; in the first half of 2026, short drama revenue sharing totaled $82 million.

Higgsfield 官方博客First-hand1 other source

Higgsfield Receives Additional Investment from TCV and NVIDIA, Expanding Series B Round

Higgsfield announced on October 23 an extension of its Series B round, adding new investment from TCV and NVIDIA; the round was previously led by DST Global in August. The company says it has more than 40 million users across 238 countries and regions, and that its annualized revenue run rate surpassed $1 billion in September, 18 months after launch. The funding will go toward product development, global infrastructure, hiring and market expansion.

04

Tips and Opinions

Frank Houbre · AI电影制作实战

Seedance 2.5 review: what has it changed for series production

Drawing on production practice for the series Lost Garden, the author sorts out the changes in Seedance 2.5 compared with 2.0: single generation extended from 15 seconds to 30 seconds, reference materials increased from 15 to 50 (30 images, 10 videos, 10 audio clips), a new 480p Draft mode and mov output added, and the API 720p price raised from $7 per million tokens to $10.70.

05

Briefs

End of issue

The AITVHot Daily is edited automatically from public sources. Every item links to its original. · Daily archive