Dark_Apollo

Simple boy in difficult situation :)

𝒘𝒂𝒏𝒕 𝒕𝒐 𝒃𝒆 𝒂 𝒑𝒂𝒓𝒕 𝒐𝒇 #𝒓𝒂𝒊𝒔𝒆𝒐𝒇𝑨𝑰

[Acyuta @AgniVesa_07]

Until death, all defeat is psychological.

Jai hind.

[Vineeta Singh 🇮🇳 @biharigurl]

The tree was uprooted by nature's fury, but Hanuman Ji's idol stood untouched. Faith doesn't bend to storms, and devotion cannot be shaken. Jai Bajrangbali! 🚩

[Dark_Apollo @darkapolloai]

@JobFound5 Interested, please share detail

[BijanBowen @bijanbowen]

Had Claude Fable 5 log network packets and display them as cars on a highway, different car types = different packet types

[Bilim Dünyası @dunyasalbilim]

Neye odaklanırsan, onu harekete geçirirsin.

[Unsloth AI @UnslothAI]

Gemma 4 12B can now run locally on just 8GB RAM via Dynamic GGUFs.

Google's new model, Gemma 4 12B Unified supports image, audio and 256K context.

You can run and train the model via Unsloth Studio.

GGUF: https://t.co/8cL321pVDh
Guide: https://t.co/odRo9WjRpA

[SkalskiP @skalskip92]

SAM 3D Body is a CVPR 2026 award candidate paper from @AIatMeta

model recovers a full 3D human body mesh from a single RGB image

you can run it automatically, or guide the reconstruction with masks and 2D keypoints

thx to @NielsRogge for awesome demo idea

[爱丽丝呀！ @BTCqzy1]

港大最新开源的 AI 视频神器 ViMax 真的太牛了！

不管是跨境电商 带货视频 还是AI短剧自动生成，它都能完美搞定！

今天给大家实测的是带货视频的生成～

输入一句话商品描述，它就能自动走完全流程：
自动写爆款带货脚本
自动生成专业宫格分镜提示词
自动分镜 + 多镜头切换
自动用上传的产品图保持高度一致性
自动生成多语言口播（可选择字幕）

以前做一条视频要花几天上千块，现在一句话搞定

地址：https://t.co/jrXr2ClaL5

学会了就可以闲鱼接单了～ dyor

[ModelScope @ModelScope2022]

Introducing LocateAnything-3B, a vision-language model for fast, precise visual grounding from NVIDIA. Up to 2.5x throughput improvement over prior methods. 🤖 https://t.co/28Wvz4Q7lg

Trained on 12M images, 138M+ queries, 785M bounding boxes across natural scenes, robotics, autonomous driving, GUI, and document understanding.

🎯 Object detection, phrase grounding, GUI element locating, scene text detection, document layout, pointing — all in one model.
Already integrated into NVIDIA Nemotron Nano Omni for production-grade VLM grounding.
📄 Non-commercial research use only.

[⚡AI Search⚡ @aisearchio]

NVIDIA's LocateAnything is a new vision model for grounding and detection. Very performant and accurate!

> 10x faster than Qwen3-VL
> 138M queries + 785M boxes
> GUI, OCR, docs, dense detection
> Free & open source

https://t.co/UvkH8l0QRb

[阿西_出海 @axichuhai]

🚀兄弟们！发现一个永久免费的域名项目

在 GitHub 已经获得 162K Star，直接封神了

是个开源公益项目，注册免费、续费免费，没有隐藏费用，没有水印广告。

个人、组织、商业项目都能用，支持 Cloudflare、FreeDNS 等主流 DNS 服务商，还有几个不错的后缀可以选。

适合个人学习、开源项目、临时演示场景，感觉是真在做公益啊。

[机器之心 JIQIZHIXIN @jiqizhixin]

What if your phone could generate or edit images in under a second?

ByteDance’s Intelligent Creation Lab presents DreamLite, a compact 0.39B parameter model that unifies text-to-image generation and editing in one network. It uses a simple trick: concatenating images side-by-side as input — blank for generation, source for editing.

DreamLite achieves GenEval 0.72 (generation) and ImgEdit 4.11 (editing), outperforming existing on-device models and rivaling server-side systems. With step distillation, it runs a 1024×1024 image in less than 1s on a Xiaomi 14.

DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing

Paper: https://t.co/Pg34jShWhg
Project: https://t.co/RKA1pc7k3O
Code: https://t.co/uecgs0YeiT

Our report: https://t.co/VGlEopobcF

📬 #PapersAccepted by Jiqizhixin

[Xie Zhifei @XieZhifei14110]

Stop using Whisper for ASR !

open sourcing Mega-ASR — the first full-scenario SOTA industrial-grade ASR model, built for the audio nobody else can crack: far-field, reverb, electrical hum, device noise, the real-world mess.

beats open + closed SOTA by 10–30% on real-world benchmarks. the harder the audio is for humans, the bigger the lead.

[SkalskiP @skalskip92]

there's no catch; SAM3 is open source and really good

one of the things it does really well is object tracking, even in crazy complex scenes like basketball

probably my favorite computer vision model ever

[Alberto @SwiftyAlbert]

Por favor mirad qué maravilla el trazado cefalométrico asistido por IA, aunque no entendáis de ortodoncia:

[有趣的80后程序员 @sunbaolong_2001]

Netflix just dropped a game-changer: VOID (Video Object and Interaction Deletion). 🎬🚀
It’s not just "filling a hole." VOID actually understands causality—it deletes the object AND its interaction influence (shadows, physical impacts).
I’ve decoded the Two-Pass workflow in ComfyUI (SAM 3.1 + Optical Flow).
Full deep dive & stress tests: 👇
🔗 https://t.co/D8YLVjTh29
中文版 https://t.co/KJg250MnMk
#NetflixVOID #ComfyUI #AIVideo #VideoEditing #AI视频

[Harman @itsharmanjot]

🚨 Paid AI video tools keep rejecting your best prompts.

This desktop app doesn’t.

One dev open-sourced a full studio 200+ models (Flux, Kling, Sora-style, Veo, lip sync, cinema controls), no filters, MIT license.

Self-hosted or bring your own keys.
Clean Electron interface.
Mac/Windows/Linux.

Already climbing fast because creators are done with subscriptions + guardrails.

Who’s installing tonight? Drop your first test below.

https://t.co/iqCGUWd3cf

[Roy🇨🇦 @GrandpaRoy2]

A kit available on the internet turns an ordinary paper airplane made from a sheet of A4 paper into a real mini-drone.
I can’t help looking at this whimsical little thing and picturing how it could be scaled up and weaponized for use in Ukraine.

[Oliver Prompts @oliviscusAI]

You can now parse any document with one 1.7B parameter model 🤯

It’s called dots-ocr. One system that handles text, tables, formulas, images, and PDFs across 100+ languages.

No separate OCR pipeline.
No task-specific models.

[Inworld AI @inworld_ai]

The #1 TTS is now available on-device

Running our TTS locally is something we've been working toward for a while. Today it's in private preview.

Leaderboard-topping quality, no cloud inference costs, no network dependency. Just the model on your hardware running locally.