@papipava · X

check it out, currently working on adding a chrome extension

Rule2025 · V2EX

做了个把房源照片自动做成视频的小工具： ReelHive 之前在折腾海外房产相关的项目，跟几位 real estate agent 聊下来，发现一个很典型的痛点： - listing 照片都有，而且通常拍得不错（摄影师外包） - 但是业主 / 中介越来越要求「要有视频、要有 Reels / TikTok 」 - 真正去剪视频很花时间，请人做视频又贵，而且每套房子都要重复同样的活 大部分“照片生成视频”的工具，本质都是把一堆 JPG 丢进时间轴，统一套一个 pan & zoom 模板，最后效果很像 PPT 幻灯片，真实用户反馈是： “有视频是有了，但拿不出手，反而拉低了 listing 质感。” 所以我最近做了一个小工具 [ReelHive]( https://reelhive.app)，专门给房产经纪、房产摄影师、marketing team 用来「把现成的房源照片快速变成可用的视频」。 简单说一下它在做什么： 1. 你把一套房子的 listing 照片丢进去（支持一次多选上传），按你希望的顺序排好。 2. 选择一个风格：Luxury / Mo

@matumeister · X

osmansoylemez · Product Hunt

Reelina AI 475 AI models for photo and video, on one credit balance.

@nrqa__ · X

the AI agent resource list I wish existed a year ago 1). for learning the fundamentals (videos) ↳ llm introduction - the crash course that actually explains how these models work before you touch a line of code ↳ llms from scratch - build one yourself so the black box stops feeling like magic ↳ agentic ai overview (stanford) - a proper academic breakdown of what makes an "agent" different from a chatbot ↳ building and evaluating agents - how to actually test whether your agent is doing its job or just faking it ↳ building effective agents - practical patterns for agents that hold up outside a demo ↳ building agents with mcp - how model context protocol changes the way agents connect to tools and data ↳ building an agent from scratch - no frameworks, no shortcuts, just the raw build ↳ philo agents - a full playlist for going deeper once the basics click 2). for cloning and remixing (repos) ↳ genai agents - a growing collection of agent examples you can clone and

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

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

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