Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Nvidia just dropped Describe Anything on Hugging Face Detailed Localized Image and Video Captioning

_akhaliq's profile picture

AK

512,491 subscribers

105,386 görüntüleme • 1 yıl önce •via X (Twitter)

Haberler & PolitikaEğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

6 Yorum

AK profil fotoğrafı
AK1 yıl önce

discuss with author:

AK profil fotoğrafı
AK1 yıl önce

app:

AI Pro Workflow profil fotoğrafı
AI Pro Workflow1 yıl önce

NVIDIA’s “Describe Anything” just dropped on Hugging Face — and it’s a vision-language beast. 🧠 Localized captions 🎯 Region-specific precision 📹 Works on images AND video Built with a novel focal prompt + localized backbone. If you're building multimodal apps, this changes the game.

Ofir Ozeri profil fotoğrafı
Ofir Ozeri1 yıl önce

Also localization? Meaning extracting objects xyz attributes?

Elomaquiabelo profil fotoğrafı
Elomaquiabelo1 yıl önce

@grok how can I use this on mi pc? Do I need code? Can I just download it... How it works

VRLA Tech profil fotoğrafı
VRLA Tech1 yıl önce

Your next W? A fresh gaming PC. Don’t lose out. 🎮🔥

Benzer Videolar

EasyControl just dropped on Hugging Face Adding Efficient and Flexible Control for Diffusion Transformer Free chatgpt style ghibli image generation with easy control
0:34

EasyControl just dropped on Hugging Face Adding Efficient and Flexible Control for Diffusion Transformer Free chatgpt style ghibli image generation with easy control

AK

222,208 görüntüleme • 1 yıl önce

DeepSite v2 just dropped on Hugging Face
0:23

DeepSite v2 just dropped on Hugging Face

AK

31,559 görüntüleme • 1 yıl önce

Nvidia just released ChronoEdit-14B-Diffusers-Paint-Brush-Lora on Hugging Face
0:36

Nvidia just released ChronoEdit-14B-Diffusers-Paint-Brush-Lora on Hugging Face

AK

81,169 görüntüleme • 9 ay önce

Nvidia just released Cosmos-Transfer1 on Hugging Face Conditional World Generation with Adaptive Multimodal Control
2:06

Nvidia just released Cosmos-Transfer1 on Hugging Face Conditional World Generation with Adaptive Multimodal Control

AK

93,079 görüntüleme • 1 yıl önce

MV-Adapter 3D texture generation apps just dropped on Hugging Face
0:30

MV-Adapter 3D texture generation apps just dropped on Hugging Face

AK

135,407 görüntüleme • 1 yıl önce

Wan2.2-Animate-14B just dropped on Hugging Face Unified Character Animation and Replacement with Holistic Replication
0:54

Wan2.2-Animate-14B just dropped on Hugging Face Unified Character Animation and Replacement with Holistic Replication

AK

157,300 görüntüleme • 11 ay önce

SpatialLM just dropped on Hugging Face Large Language Model for Spatial Understanding
0:50

SpatialLM just dropped on Hugging Face Large Language Model for Spatial Understanding

AK

674,259 görüntüleme • 1 yıl önce

Microsoft just dropped MineWorld on Hugging Face a Real-Time and Open-Source Interactive World Model on Minecraft
0:31

Microsoft just dropped MineWorld on Hugging Face a Real-Time and Open-Source Interactive World Model on Minecraft

AK

95,035 görüntüleme • 1 yıl önce

Alibaba just released LHM on Hugging Face Large Animatable Human Reconstruction Model from a Single Image in Seconds
1:31

Alibaba just released LHM on Hugging Face Large Animatable Human Reconstruction Model from a Single Image in Seconds

AK

170,429 görüntüleme • 1 yıl önce

LiveCC just dropped on Hugging Face Learning Video LLM with Streaming Speech Transcription at Scale video LLM capable of real-time commentary, trained with a novel video-ASR streaming method, SOTA on both streaming and offline benchmarks.
2:07

LiveCC just dropped on Hugging Face Learning Video LLM with Streaming Speech Transcription at Scale video LLM capable of real-time commentary, trained with a novel video-ASR streaming method, SOTA on both streaming and offline benchmarks.

AK

45,967 görüntüleme • 1 yıl önce

NVIDIA just released AnyFlow on Hugging Face The first any-step video diffusion model that generates high-quality text-to-video with any inference budget - 4 steps or 50, quality scales smoothly without degradation.
1:17

NVIDIA just released AnyFlow on Hugging Face The first any-step video diffusion model that generates high-quality text-to-video with any inference budget - 4 steps or 50, quality scales smoothly without degradation.

DailyPapers

41,726 görüntüleme • 3 ay önce

Stability AI just dropped Stable Audio Open Small on Hugging Face Fast Text-to-Audio Generation with Adversarial Post-Training
0:43

Stability AI just dropped Stable Audio Open Small on Hugging Face Fast Text-to-Audio Generation with Adversarial Post-Training

AK

55,100 görüntüleme • 1 yıl önce

Alibaba just dropped TaoAvatar on Hugging Face Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting
0:41

Alibaba just dropped TaoAvatar on Hugging Face Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting

AK

329,222 görüntüleme • 1 yıl önce