Skip to content
Date and source

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

Oct 9Fri
  1. VideoGen · 视频剪辑与镜头实战22

    What Features Does Image-to-Video AI Have? Breaking Down VideoGen's Core Capabilities

    Image-to-video AI turns static images into short clips; core features include start-frame control, motion prompts or automatic motion, duration and aspect ratio settings, native audio or silent output, quality tiers, batch conversion, lip-sync on static images, reference-image consistency, and post-generation editing.

  2. VideoGen · 视频剪辑与镜头实战38

    Seedance AI Lip-Sync Feature: How to Use It in VideoGen

    Seedance 2.0 is ByteDance's multimodal video model; by putting dialogue in quotation marks in the prompt and describing the tone, it can generate visuals, speech, and matching lip-sync in one pass, with a single clip up to 15 seconds. In VideoGen, you need to select a tier whose "Powered by" includes Seedance; Seedance 2.0 Mini supports 4 to 15 seconds, and Seedance 2.5 supports 4 to 30 seconds. Lip-sync drift is mostly caused by overly long dialogue, which can be shortened to one sentence or split into two clips.

  3. VideoGen · 视频剪辑与镜头实战22

    Which AI Video Generator Has the Strongest Features? Comparing Single Models, Digital Humans, and End-to-End Tools

    No single AI video generator is the strongest across all tasks: single-model tools such as Seedance 2.0 in Dreamina and Higgsfield offer the deepest single-model control, digital human tools like HeyGen excel at talking avatars and voiceover, while VideoGen leads in model selection, editing timeline, and finishing with voiceover, subtitles, and music.

  4. Wireflow · AI短剧与视频制作教程26

    ComfyUI vs Automatic1111: which Stable Diffusion UI to use in 2026

    The core of the ComfyUI vs Automatic1111 comparison is the trade-off between control and ease of use: ComfyUI uses node graphs, is faster, and is still actively updated, with v0.39.0 released on October 5, 2026; Automatic1111 is easier to get started with, but has not been updated since v1.10.1 on February 9, 2025, and does not support Flux.

  5. MattVidPro · YouTube 创作视频40

    How to make a seamlessly connected AI intro (full workflow)

    MattVidPro demonstrated the full process of making a seamless AI intro using Runway's Seedance 2.5 keyframe mode, the core of which is blending the AI intro with real footage and locking the final frame. He used ChatGPT to turn a rough idea into a complete prompt, then iteratively generated and stitched the best clips to complete the transition. The video also includes a Q&A segment on Runway Agent and Runway MCP.

  6. Kapwing 创作指南62

    How to recreate the Raindance AI two-person music video trend with Seedance 2.5 (with prompts)

    The Raindance AI trend originates from the music video for "Raindance" by Dave and Tems, in which creators use AI to replace the two performers in a dock scene with themselves or any character.

    Why it matters: Using two identity reference images plus one line-art motion reference, the Raindance two-person music video scene can be recreated in Seedance 2.5, and the approach can be transferred to other motion-reference trends.

  7. Comfy 官方博客74

    How I generate real-time video on a single GPU with MiniMax H3

    On a single RTX 5090 (32GB VRAM), the author used FastVideo's FastH3 V2 checkpoint with four-step sampling to produce 15-second 448×256 real-time video, aiming to bring down the cost of continuous generation from 6k per day.

    Why it matters: The author breaks down one by one the six optimizations for running real-time video on a single RTX 5090, which can be transferred to your own production workflow.

  8. note · knowhow_matome99 · 图像视频创作分享30

    The complete ComfyUI × MiniMax H3 guide: generate AI video locally on a PC for free and monetize it

    A guide explains how to use ComfyUI with MiniMax H3 to generate AI video locally on a PC for free and monetize it. It recommends the 8-Step V2 workflow of the distilled acceleration model FastH3; on an RTX 2070 Super with 16GB VRAM and an i7, the author takes about 15 minutes to generate a single video, and suggests using I2V to first produce a first-frame image and then generate the video. The author says that from posting AI videos on TikTok alone, monthly earnings once exceeded 550,000 yen.

  9. note · great_eagle2170 · 图像视频创作分享42

    [2026 edition] Even AI beginners can do it! 3 types of Reels videos that make people watch to the end | with prompts you can copy directly

    Aimed at AI beginners over 40, this introduces 3 presentation methods for making Instagram Reels videos with AI: Higgsfield's Earth Zoom Out effect for a zoom-out shot from a photo to the universe, the AIR BENDING effect for a smoke transformation transition, and Google Gemini's video generation feature for a wall collapsing to reveal a future space. The article includes English prompts you can copy directly and explains the workflow of editing into 9:16 vertical Reels with CapCut.

Oct 8Thu
  1. 视听指南 · 搜狐公开专栏60

    Central and provincial TV stations and platforms target AI documentaries: what are the new trends?

    From CCTV-9's "Start Asking Questions" to Hunan TV and Mango TV's "Taiwan Island Chronicle," and to Central Newsreel and Documentary Film Studio's Discovery Documentary Media's "Science Caught by Surprise" and "Chinese Civilization" Season 1, multiple documentaries fully made with AI or with deep AI involvement have premiered in succession within four months. The article traces AI's position in documentaries moving from voiceover, image restoration, and dubbing to full-process image generation, and mentions that the broadcaster's self-developed "Zhiji" system can shorten production cycles by 35%. Practitioners anchor authenticity in the text, with historical materials and expert review handled by humans, while AI handles visual presentation.

  2. 传媒内参 · 搜狐公开专栏60

    Central and provincial TV stations and platforms target AI documentaries: what new trends are there?

    Media Neican rounds up documentaries fully made with AI or with deep AI involvement over the past four months: all 10 episodes of CCTV-9's "Start Asking Questions" have visuals entirely generated by AI, all visuals of Hunan TV and Mango TV's "Taiwan Island Chronicle" (five episodes, about 140 minutes) are generated by AIGC, and Central Newsreel and Documentary Film Studio's Discovery Documentary Media's "Science Caught by Surprise" and "Chinese Civilization" Season 1 launched successively on iQIYI. The article traces the shift of AI in documentaries from voiceover, restoration, and dubbing toward full-process generation, and mentions that practitioners anchor authenticity in historical materials and expert review, with AI responsible for visual presentation.

  3. note · taaaak0504 · 图像视频创作分享31

    The full workflow for making "animated LINE stickers" with ChatGPT, Google Flow, and Claude Code

    An office-worker dad who is not good with computers used ChatGPT to generate a 12-cell green-background grid image, Claude Code to split it cell by cell and convert it into the APNG format required by LINE, and Google Flow to turn each cell into a 4-second video, completing the full workflow from making animated LINE stickers to applying for release. He currently has 5 sets of animated stickers on sale, with cumulative sales of 76 yen, and he documented fixes for 7 types of failures, including transparent backgrounds, image cropping, and specification errors.

  4. note · noble_mink9287 · 图像视频创作分享22

    College Student Creates "Future Tokyo" Video with AI: Generated with PixVerse, Edited with CapCut, and Submitted to TikTok

    A college student who is an AI beginner created a video themed "Tokyo 100 Years from Now" using AI. They first used AI to generate images blending Japanese castles, cherry blossoms, high-rise buildings, and aerial transportation, then used PixVerse to convert static images into dynamic footage, and finally completed editing with CapCut and submitted it to TikTok. The author emphasizes that AI is not fully automatic—prompt design and material selection still require personal judgment.

  5. 公众号:短剧自习室31

    After Prices Plummet, AI Short Drama Companies Are Undergoing Three Migrations in AI Entertainment

    The AI short drama industry shifted from capacity shortage to oversupply within half a year, with content prices dropping from 5,000 yuan per minute to just a few hundred yuan. In September, Douyin Group's native AI short dramas averaged 1,010 new releases per day. Industry companies are migrating in three directions: upward into AI mid-to-long dramas, such as "Northern School Notes" which peaked at 11.3% market share and exceeded 1 million yuan in first-week revenue sharing; into new AI interactive content, where DRAMAGO achieved a 40% monthly retention rate within 3 months of entering the market; and outward into overseas markets, where Kunlun Wanwei's AI short drama platform exceeded $65 million in monthly revenue.

  6. 机器之心 · 公开公众号 RSS73

    Shengshu Technology Releases Vidu Q4 Preview, Starting at 0.09 Yuan/Second

    Shengshu Technology has launched Vidu Q4 Preview, the first preview version of Vidu Q4 for creators, focusing on enhancing character performance, camera language, and complex visual effects. The launch price starts at 0.09 yuan per second, allowing up to 5 times more content to be generated with the same budget.

    Why it matters: Vidu Q4 Preview combines a launch price of 0.09 yuan per second with 15 reference images and 2K/4K output, providing a basis for judging the cost range of AI video mass production.

  7. 歸藏22

    Using Idle Code Plan Credits to Have Grok Bot Write Code and Render Videos

    Install programming agents like Pi or DeepSeek Harness in an Agent cloud computer, allocate unused credits from other Code plans into it, and then have Grok Bot call these tokens to write code and render videos—so idle credits aren't wasted. Previously, this user had Grok Bot generate AI morning report videos on a daily schedule, with content collection, code writing, and video rendering all running on a cloud virtual machine without using a local computer.

  8. note · kozo_t · 图像视频创作分享15

    A Person in Their 60s Generates AI Videos with Gemini: A Hands-On Experience from Black Bean Tea Ad to Premiere Pro Editing

    An author in their 60s tried AI video generation with Gemini, entering text prompts like "a woman slowly pouring hot black bean tea into a cup," generating shots of tea being poured, steam rising, and close-ups of black beans. He found that the more specific the prompts (character, scene, lighting, camera movement), the closer the results were to expectations, but failures like the same character changing faces across scenes and hand deformations remain common. He believes AI video is a material tool that needs to be paired with Premiere Pro editing, and is optimistic about its applications in side hustles like short videos and product introductions.

  9. note · sasao_66 · 图像视频创作分享22

    DomoAI Prompt Research for Generating 'Beautiful Woman Escaping Zombies' Videos

    The author shared the complete prompts used to create a 'beautiful woman escaping zombies' clip with DomoAI's video generation feature, covering scene details such as a nighttime abandoned street, zombie chase, turning back with a startled 'Dangerous!' with accurate lip-sync, and fleeing into a building and closing the door. The author emphasized realistic human texture and cinematic camera work. The author also noted that DomoAI's free generation includes watermarks, recommended subscribing, and announced the launch of a membership section with updates on AI beauty creation and tool usage at least twice per week.

  10. 机器之心SOTA模型 · 公开公众号 RSS22

    Anthropic Releases Claude Haiku 5.5; Mistral Opens Mistral Large 4 Public Preview API

    Anthropic released Claude Haiku 5.5 on October 7, the first Haiku model to support adjustable reasoning intensity, targeting high-frequency tasks such as summarization, classification, and coding sub-agents. When prompts do not exceed 100,000 tokens, pricing is $0.10 per million input tokens and $0.50 per million output tokens.

  11. Stuubzzz · 视频工作流实测71

    MiniMax H3 Four-Step Output: PDMD LoRA vs. NVIDIA SoL Refiner Benchmarked on RTX 5090

    The author benchmarked MiniMax H3's PDMD 4-step LoRA and NVIDIA SoL Refiner on an RTX 5090: PDMD averaged 101 seconds to output a 6.6-second clip at 2520×1440, while the 20-step Quality path took 753 seconds.

    Why it matters: The author benchmarked PDMD 4-step LoRA and NVIDIA SoL Refiner on an RTX 5090, providing itemized timing and image quality differences that can serve as a selection reference.

  12. Stuubzzz · 视频工作流实测62

    Stubelius Ultimate H3 0.11 Adds Intermediate Frames, Segment Continuation, and Timeline Pinning in ComfyUI

    Stubelius Ultimate H3 0.11 is a free open-source MiniMax H3 workflow by the author for ComfyUI, adding three ways to control segments by seconds in First/Last Frame mode: up to two intermediate frames, placing a video in the First Frame box to continue a segment, and pinning up to 8 audio clips or short segments to specified seconds.

  13. SuSu_酥酥48

    Tian Keyu Bets on World Models: $200 Million Valuation with No Product

    Tian Keyu, first author of the NeurIPS 2024 Best Paper, has focused on world models over the past year, aligned with the directions of Fei-Fei Li and Yann LeCun, targeting robotics and interactive video, and autonomous driving. His new company has no product and only a 10-person team, but has secured nearly $30 million in funding from five venture capital firms including Wuyuan Capital and IDG, with a post-investment valuation of $200 million. The company plans to train on approximately 100 million hours of video. AMD recently acquired Fei-Fei Li's World Labs for approximately $8.2 billion.

  14. 影视独舌 · 搜狐公开专栏66

    Traditional Film Company Embraces AI: A Look Behind the Production Process of "Pendulum" and Its 10 Million Revenue Share

    "Soul Ferry" Produced by iQiyi and Changxin Media

    Why it matters: A review of the production process behind the 10 million revenue share of the "Soul Ferry" AI series, showing how a traditional film company completed 197 minutes of long-form content with a 15-person team in four and a half months.