Rubynian

🎨 3D Generalist & AI Artist
🚀 ComfyUI workflows
🥇 Award winning AI Filmmaker

[Ingi Erlingsson 🪄 @ingi_erlingsson]

Human in the loop 🤖

Made in @ComfyUI with a laundry list of tools: @ltx_model 2.3 + @thesystms FLW LoRA, @Alibaba_Wan 2.2 I2V + T2V, Florence2, @Meta Sapiens2, @OpenAI GPT Image 2.0, @suno , @AdobeAE

[AYi @AYi_AInotes]

Claude终于补上了自己最大的短板，现在能真正看懂视频了。

不用等Anthropic官方慢吞吞的更新，现在通过Algrow的MCP平台，你只要扔一个YouTube、TikTok或者Instagram的链接，Claude就能完整看完整个视频，分析画面、音频、节奏、文字叠加，甚至给你出一份可落地的深度分析报告。

演示效果直接颠覆认知，
输入一个YouTube Shorts频道的URL，Claude会自动调用视频分析工具，批量拉取该频道所有短视频，生成包含标题、播放量、点赞率的完整数据表格。
接着��会做病毒化深度拆解，告诉你为什么有的视频爆了，有的却石沉大海。
它能精准识别出所有视频共用的模板、配音和动画风格，然后一针见血地指出：决定性差异从来不是后期特效，而是前2秒的hook概念冲击力。
最狠的是帧级留存分析，它会画出每一秒的观众流失曲线，标出哪些时间段是“死亡区”，观众会在这一秒毫不犹豫划走。

以前你要花三天时间，手动刷几十条视频、记满一本笔记、做无数个表格才能得出的结论。
现在一句话，30秒搞定。

Algrow的后端会自动完成视频下载、关键帧提取、音频转写，再把多模态数据完整喂给Claude。
通过MCP工具链，它能一口气跑完“看视频→抓数据→交叉对比→输出报告”的全流程，中间不需要你任何干预。

目前这个功能正处于免费无限试用的推广期。
正式上线后定价也非常亲民，1个积分可分析约8分钟视频，最低25美元/月的订阅就包含12小时以上的分析额度。

为什么这件事意义重大？

1. 大模型的战争已经彻底转向生态
Claude的文本推理能力一直是行业顶尖，但原生视频能力长期落后于Gemini。这次第三方开发者用MCP的方式，一夜之间就把Claude拉到了同一水平线，甚至���为工具链式调用能力变得更强。这证明未来的胜负手从来不是参数，而是谁的生态能长出更多杀手级应用。

2. 内容创作者迎来核武器级生产力工具
以后再也不用熬夜刷竞品了。让Claude帮你把同赛道所有爆款和扑街视频全看一遍，直接提炼出可复制的hook公式、转场节奏和内容结构。谁先用上这套工具，谁就能在流量战里领先别人一个身位。

3. 视频研究Agent的时代正式开启
视频是互联网上体量最大、最难处理的数据类型。一旦Claude能看懂视频，再结合MCP的工具链能力，很快就能诞生能自动监控全网流量趋势、生成完整内容策略、甚至迭代创意的AI Agent。内容分析这个曾经的人力密集型工作，正���被彻底重构。

当然它也有局限，对小众文化梗和细腻情绪的理解仍有误差，敏感内容不要随意投喂，免费期结束后算力成本可能会传导到价格上。
但这些都不重要，潘多拉的盒子已经打开了。

[A.I.Warper @AIWarper]

Testing the new LTX 2.3 IC LORA for head swaps.

Pretty good straight out of the box!

Will have to play more with this haha

Link below

[POM @peterom]

Face-swapping often works in optimal conditions but breaks down when faces are distorted, lighting is bad, etc.

Allison Pereira has been on a quest to solve by training an IC LoRA for LTX2 - and he's getting very close + likely gen'd in <2 mins on consumer hardware!

[Rubynian @Rubynian2]

@Anima_Labs ANIMA

[Oliver Henry @oliverhenry]

https://t.co/Mg6IwpDnGK

[Benson Sun @BensonTWN]

換上了 Opus 4.6 之後，生產力簡直飛起。

OpenClaw 的創辦人也說過，要用就用最好的模型，不要用次級品，太他媽同意了。

[ChatCut @chatcutapp]

IT FUCKING HAPPENED.

Seedance 2.0 now works with the @openclaw agent inside @chatcutapp.

This UGC video was generated entirely with Seedance 2.0 after I sent an Amazon link.

The agent crawled the page, extracted product info and photos, then fed the right assets into Seedance 2.0 to generate the UGC product video.

My brain is literally melting at this point...

[ChatCut @chatcutapp]

Seedance 2.0 + OpenClaw FTW!

Instead of just generating one final video with Seedance 2.0, the OpenClaw agent decided to:

- generated a guy (with Seedance 2.0) ON A GREENSCREEN

- keyed out the green to create transparency

- downloaded MULTIPLE BACKGROUND IMAGE OPTIONS to audition for the human

- generated separate motion-graphics overlays on top, using code elements

Seedance 2.0 is cool...

But this combo I believe is the REAL GAME CHANGER.

[Rubynian @Rubynian2]

@dreamina_ai So goooooood😍

[Rubynian @Rubynian2]

#DreaminaCPP #seedance2
New era is here🍎

[Rubynian @Rubynian2]

🎉 Exciting News!

I'm honoured to be selected for the Dreamina Creative Partner Program!

If you're a creator as well like me, I highly recommend you check this out: https://t.co/SP9wGr3LlT

#DreaminaCPP #AICreation

[Dreamina AI @dreamina_ai]

Apply now at: https://t.co/kR3amUVlS4

🌟 Creative Partner
We believe in fueling your potential. All active partners have been upgraded to Standard Membership. This means your monthly credit allowance has increased by 3x to 4x (compared to the previous Basic tier).

Plus, earn up to 50,000 credits/month for your top-performing content.
More iterations. Less limits.

[Rubynian @Rubynian2]

I am beyond excited to join the Qwen-Image LoRA Hackathon as a Featured Creator to share my latest obsession: Medieval Marginalia!

Competition Information:
https://t.co/LERGYTav9E

Medieval_Petify Qwen LoRA Download Link:
https://t.co/WvYjWd8Nap

#HappyQwensday #QwenImageLora

[Wildminder @wildmindai]

Pretty cool unified AI VFX production pipeline.
- Cinema Prompt Engineering with ~110 film and animation presets;
- an infinite Storyboard Canvas + distributed rendering across multiple ComfyUI nodes;
- 13+ LLM providers.
https://t.co/hDrTSIh4lN

[Rubynian @Rubynian2]

@beechinour Veo

[Matthew @TzDev_]

Adventure AI is seriously impressive 🤯

This relighting tool has been helping designers every day by delivering more control, speed, and high-quality results.

To celebrate, I will randomly select 3 winners from those who comment “Adventure AI”

[Remotion @Remotion]

We're collecting great Remotion prompts!

Browse, copy and submit good ones:
https://t.co/p4RjD5yiip

[AmirMušić @AmirMushich]

https://t.co/iXuDFf6GVy

[paul @tetsuoarena]

Just dropped GrokFilm, 185+ cinema & photography techniques to level up your @grok Imagine prompts.

Dutch angles, chiaroscuro lighting, rack focus, film noir... each technique explained + one-click "Try in Grok" button.

Stop getting generic AI images. Start thinking like a cinematographer.

https://t.co/ggzsLOCczE

[Will Eastcott @willeastcott]

SuperSplat 2.19.0 is here! ✨
Your free and open source Gaussian Splat Editor
🎞️ Create videos of 4D Gaussian splats
➡️ Import support for SPZ and KSPLAT added
🌐 HTML viewer export now based on SOG
⌨️ New hotkeys for animation authoring
[1 / 2]