@dotvonesy · X

Beautiful Effects for Mobile and Web:

FLUX 3 Video Generator — AI 视频生成工作台，支持文字或图片生成视频、参考图及镜头、动作和声音提示，并清晰标注模型可用状态

pw · HN

Hiya! So I've been playing around with having Claude make videos for a bit now even had some success posting the results to TikTok (and setup a whole pipeline so Claude can generate and post autonomously). With the release of Nano Banana 2 Lite, I was curious show fast I could make the generation, so last night I gave it a whirl and got down to around 30s for short-form video. It uses GLM-5.2 fast via Fireworks to generate the scripts and image prompts and, like I said, Nano Banana 2 Lite for the images, gpt-4o-mini-tts for the narration, and ffmpeg to string it all together and add the Ken Burns zoom effect (which still has a shake I haven't been able to get rid of). The video compilation proved to be the blocker once the rest was in place, but I was able to speed that up by putting it on a 64 vCPU EC2. The cost might be the most interesting aspect as the short form videos tend to be about 25 cents. Almost 90% of that is the images, which are 3.336 cents a piece. Of course, running

Seedance 2 Pro — 多模态 AI 视频生成平台。支持文本+多张图片+视频+音频参考同时输入，实现角色一致性、多镜头叙事、音频同步动作、精准镜头控制。几分钟生成商业级短视频，适合营销、电商、社交媒体、品牌故事、预可视化等高频内容创作需求。比传统文生视频更可控、更接近导演级表达

Sekhmet · HN

Adept – convert any YouTube playlist into a Udemy-like course

@botsnips · X

Check out our AI only shorts

@Alkaderpro · X

Just launched MotionDoc AI for the Higgsfield App Contest! 🚀 Turn any document into a professional motion graphics video with AI. 🔗 #HiggsfieldApp #MCP #AI #BuildInPublic

airobus · HN

I built a simple image-to-video tool with multiple AI models

lilaiqun · V2EX

受够了视频没听清就反复拖进度条，只考虑音频错别字多，写了个"会看画面"的视频转笔记工具 看视频经常一句话没听清，拖回去重听好几遍还是听不清。试了现有的转写工具，发现它们只用音频——恰恰是我听不清的词，它们也转不对（幻灯片上的术语、代码里的名词，声音里根本猜不出来）。 所以做了 **Vid2notes**：转写时不只听声音，还抽帧看画面。Whisper 转文字，多模态模型拿着字幕对着截图一起读，输出带截图、章节、时间戳和 AI 总结的图文笔记，可导出 Markdown / SRT / VTT 。 支持最长 10 小时的视频，常见格式都行。 技术栈给感兴趣的 V 友：全栈 Cloudflare （ Workers AI 跑 Whisper + GLM ，Rust + FFmpeg 跑在 Containers 里），按视频 MD5 缓存不重复算。 **每天免费 3 个视频**，不用绑卡：[vid2notes]( https://vid2notes.com/) 最想知道的反馈：准确率在你的视频上怎么样，尤其是带幻灯片/代码的教学视频。欢迎拍砖

@pinpointappdev · X