0xrekt

不要讲正确的废话

[Larus Canus @MrLarus]

🤯一个控制 AI 航拍镜头的新玩法！
直接在图片上画线， 让 AI 按红线生成无人机镜头💥

我做了一段广州中轴线 FPV 航拍：
低空穿过花城广场 → 贴楼拔高 → 穿楼顶结构 → 绕楼俯冲 → 掠过珠江 → 冲向小蛮腰 → 绕塔上升

城市航拍、景区穿越、商业地产、楼宇宣传片…全都能这么玩！
先画路线，AI先替你飞一遍，航拍自由！🚁

工作流和提示词放评论区👇

[0xrekt @Mr__Stew]

@sageaurelius @deepseek_ai No worry my friend, it's China behind, China will do anything to make sure it is the first and the best.

[Zack D. Films @zackdfilms1]

Spinning Mt Fuji Like A Beyblade 🤯

[huangserva @servasyy_ai]

微软发布了一个 4B模型，可以在 3 秒内把任意图像转换为 3D 资产。

它使用一种名为 O‑Voxel 的新几何格式，并且可以在 CUDA 上用不到 100 毫秒转换为带纹理的网格模型。

输出为 GLB 文件，包含完整的 PBR 材质，可直接用于 Blender、Unity 和 Unreal。

完全开源👇

[Science girl @sciencegirl]

Enormous brown bear seen at high altitudes in Alaska

[独立开发者William @DLKFZWilliam2]

哈哈哈这大佬解决了我多年游戏资产一致性spritesheet问题,��开源了

我用AI查看了下源码,恍然大悟
本质上是我之前方向错了:

不能用生图类的AI生成sprite sheet,因为sprite sheet本地上就是将动画抽关键帧

所以用生图AI比如Image2设计,再用Kling这类视频AI做动画,再后续处理

[Justine Moore @venturetwins]

I am obsessed with this Japanese man using AI video to put himself into movies

(he's on IG at @ai_am_furufuru)

[AmirMušić @AmirMushich]

Meta Tribe2 is a model that predicts your brain's response on videos

so now you can edit videos with more clarity of how to compose them, what works and what doesn't

and we built a free tool for you based on this model
yes, totally free

see details below

[0xrekt @Mr__Stew]

@mxvdxn Wow which AI

[Vadim B @slipgatecentral]

I’m building procedural cityscape generator with Claude directly plugged to Houdini, with zero prior experience. This is some next level shit right there, keeps blowing my mind

[Sac @Saccc_c]

刚发现 GPT 网页端现在可以直接体验 360 全景图了，amazing

方法巨简单，提示词里让他生成 360 全景图片，点击图片下方的“enter 360 world”即可进入全景视角

[小互 @xiaohu]

用 AI 将60岁的妈妈穿越回她年轻的时候

作为她60岁的生日礼物

这个创意有点牛P…

[✶ @echoesofworld]

Gerringong, Australia

[Viktor Oddy @viktoroddy]

❤️‍🔥 Just Recorded a 16 min Tutorial on How to use Gemini 3.1 + Seedance 2.0 Build Cinematic $10k Websites (step-by-step)

You can now build stunning marketing sites fully with AI

[Alpha Beta Gamer @gameralphabeta]

Fight a huge Fish Train in HIERONYMUS, a bizarre indie FPS game, based on the art of Hieronymus Bosch!

Steam: https://t.co/2HFRCSLEKr

EXCLUSIVE video of the full Fish Train boss: https://t.co/sfmKr9j40I

by indie dev @HieronymusGame

[Aristo @aristomarinetti]

"Never trust a thought that occurs to you indoors."

— Friedrich Nietzsche

[0xrekt @Mr__Stew]

@everestchris6 POOL. interesting

[Chris @everestchris6]

this OpenClaw bot finds $500k–$1.2M homes without pools, renders a pool into their backyard, and mails the owner a postcard showing the before/after, on autopilot...

here's how pool builders can close $50k+ deals with this system:

- scans satellite imagery for mid-market homes with empty backyards
- filters by lot size, sun exposure & recent ownership change
- pulls the homeowner direct from public records (not shared leads)
- renders a luxury pool dropped into their actual yard
- calculates build cost + home value lift for their specific zip
- generates a cinematic video of their backyard with the new pool
- prints a personalised postcard with the before/after + QR code
- drops it in the mail + hits them with retargeting

every step from sourcing to outreach is automated.

reply "POOL" + RT and i'll send you the full breakdown so you can build this too (must be following so i can DM)

[AA @measure_plan]

html-in-canvas API is shattering my expectations

[AYi @AYi_AInotes]

holy shit， 微软直接把之前因为太危险被下架的语音AI王炸，给重新开源了，
这个叫VibeVoice的项目，GitHub已经冲到了29.3k星，
做播客的，搞有声书的，做AI视频配音的，还有天天要转写会议记录的兄弟，
谁没被付费语音工具的订阅费坑过，谁没被长音频处理崩过，
谁没被本地部署的复杂程度搞到头疼，
这个项目直接把这些痛点全给解决了，

核心能力直接爆表：
- TTS：一次生成90分钟多说话人（最多4人）对话，情感、自然转接、长上下文超强
- 实时流式版（0.5B模型）：延迟仅~300ms
- ASR：单次处理60分钟音频，自动说话人分离 + 时间戳 + 50+语言

完全本地运行，免费无订阅，还带了不可感知水印 + AI声明防滥用。

2025��因为deepfake风险被Microsoft自己下架过，现在加了安全措施重新上线，真正的“核弹级”开源项目。

这下ElevenLabs要慌了😂
github 地址评论区自取👇
#VibeVoice #开源 #语音AI #Microsoft #TTS #ASR