Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Efficient LoFTR was just integrated into Hugging Face Transformers! It improves upon LoFTR, a detector-free image matcher, by being 2.5x faster. It can even surpass the SOTA efficient sparse matching pipeline SuperPoint + LightGlue. Now available in a few lines of code!

NielsRogge's profile picture

Niels Rogge

19,546 subscribers

32,261 Aufrufe • vor 10 Monaten •via X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

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

222,119 Aufrufe • vor 1 Jahr

GitHub just released its Copilot SDK. You can now embed Copilot into any of your applications and make it much more powerful with just a few lines of code. I built a quick example here.
4:06

GitHub just released its Copilot SDK. You can now embed Copilot into any of your applications and make it much more powerful with just a few lines of code. I built a quick example here.

Santiago

62,766 Aufrufe • vor 4 Monaten

AccVideo just dropped on Hugging Face Accelerating Video Diffusion Model with Synthetic Dataset present a efficient distillation method to accelerate video diffusion models with synthetic dataset method is 8.5x faster than HunyuanVideo
1:04

AccVideo just dropped on Hugging Face Accelerating Video Diffusion Model with Synthetic Dataset present a efficient distillation method to accelerate video diffusion models with synthetic dataset method is 8.5x faster than HunyuanVideo

AK

20,633 Aufrufe • vor 1 Jahr

Grok just dropped a crazy AI feature you can now edit image by chatting to Grok and.. it can even change specific object in the image this is incredible for AI artist
0:23

Grok just dropped a crazy AI feature you can now edit image by chatting to Grok and.. it can even change specific object in the image this is incredible for AI artist

el.cine

159,815 Aufrufe • vor 1 Jahr

Pretty Insane - SoTA Text to Speech model capable of English AND Hindi - 3B Llama backbone - Apache 2.0 licensed 🔥 > Sub 80 ms latency > Supports both English, Hindi including code-mix > Runs in a free google colab too 🤯 Best part: They're actively working on other languages like Tamil, Telugu, Bengali, etc > Available on Hugging Face hub, powered by Transformers 💥
0:52

Pretty Insane - SoTA Text to Speech model capable of English AND Hindi - 3B Llama backbone - Apache 2.0 licensed 🔥 > Sub 80 ms latency > Supports both English, Hindi including code-mix > Runs in a free google colab too 🤯 Best part: They're actively working on other languages like Tamil, Telugu, Bengali, etc > Available on Hugging Face hub, powered by Transformers 💥

Vaibhav (VB) Srivastav

33,749 Aufrufe • vor 11 Monaten

Google Chief Scientist, Jeff Dean "AI now generates 25% of Google's integrated code" Google has already trained a Gemini model on its internal codebase to help developers this doesn’t cover everything, but it improves AI-assisted coding by integrating code into its parameters
0:35

Google Chief Scientist, Jeff Dean "AI now generates 25% of Google's integrated code" Google has already trained a Gemini model on its internal codebase to help developers this doesn’t cover everything, but it improves AI-assisted coding by integrating code into its parameters

Haider.

173,461 Aufrufe • vor 1 Jahr

🚀 Keet 3.21 is here! This massive update upgrades our entire P2P stack, making Keet faster, more efficient, and ready for the next era of private communication. 10,000 lines of code rewritten—this is just the beginning! Update Keet now & feel the difference 🍐
2:27

🚀 Keet 3.21 is here! This massive update upgrades our entire P2P stack, making Keet faster, more efficient, and ready for the next era of private communication. 10,000 lines of code rewritten—this is just the beginning! Update Keet now & feel the difference 🍐

Keet by 🕳🥊

24,081 Aufrufe • vor 1 Jahr

How to vibe code games and deploy them for free entirely on Hugging Face get started in a few minutes, no logins, signups or subscriptions deploy on Hugging Faces spaces for anyone to play for free this game was made with a few prompts in anychat starting with "make a three.js game" and then adding "make it better" with some small tweaks
0:33

How to vibe code games and deploy them for free entirely on Hugging Face get started in a few minutes, no logins, signups or subscriptions deploy on Hugging Faces spaces for anyone to play for free this game was made with a few prompts in anychat starting with "make a three.js game" and then adding "make it better" with some small tweaks

AK

40,822 Aufrufe • vor 1 Jahr

OpenAI Co-founder Andrej Karpathy predicts transformers may soon surpass the human brain in capabilities "Transformers have the potential to surpass the human brain in efficiency and memorization capabilities, despite current limitations in data availability and training. As AI technology advances, transformers may become more efficient learners than the human brain, which operates under various limitations"
1:12

OpenAI Co-founder Andrej Karpathy predicts transformers may soon surpass the human brain in capabilities "Transformers have the potential to surpass the human brain in efficiency and memorization capabilities, despite current limitations in data availability and training. As AI technology advances, transformers may become more efficient learners than the human brain, which operates under various limitations"

Haider.

133,777 Aufrufe • vor 1 Jahr

VAST AI releases Triplane Meets Gaussian Splatting on Hugging Face Fast and Generalizable Single-View 3D Reconstruction with Transformers demo: TGS enables fast reconstruction from single-view image. It builds the 3D representation upon a hybrid Triplane-Gaussian representation by evaluating a transformer-based framework, from which 3D Gaussians would be decoded
0:23

VAST AI releases Triplane Meets Gaussian Splatting on Hugging Face Fast and Generalizable Single-View 3D Reconstruction with Transformers demo: TGS enables fast reconstruction from single-view image. It builds the 3D representation upon a hybrid Triplane-Gaussian representation by evaluating a transformer-based framework, from which 3D Gaussians would be decoded

AK

113,220 Aufrufe • vor 2 Jahren

You can achieve this smooth, native number transition using Expo-ui with just a few lines of code. All without writing a single line of native code! 🚀 Here is how you can do it 👇
0:21

You can achieve this smooth, native number transition using Expo-ui with just a few lines of code. All without writing a single line of native code! 🚀 Here is how you can do it 👇

Hewad Mubariz

61,263 Aufrufe • vor 2 Monaten

Finally! Codellama-70b as Copilot in VSCode! 😱 You can now harness the power of the most advanced code generation model, Code Llama 70B, right in Visual Studio Code with Perplexity This model has outperformed even GPT-4 in code writing, and it's now seamlessly integrated into our editor 🥳 Do you anticipate the emergence of more open-source models that surpass GPT-4?
0:33

Finally! Codellama-70b as Copilot in VSCode! 😱 You can now harness the power of the most advanced code generation model, Code Llama 70B, right in Visual Studio Code with Perplexity This model has outperformed even GPT-4 in code writing, and it's now seamlessly integrated into our editor 🥳 Do you anticipate the emergence of more open-source models that surpass GPT-4?

Daniel San

69,499 Aufrufe • vor 2 Jahren

The code of GSPN #CVPR2025 is released! We proposed a new sqrt(N) complexity attention mechanism, which enables efficient high resolution image generation. We can generate 8k images with 42x speed up compared to self-attention in StableDiffusionXL! Code: Paper:
0:35

The code of GSPN #CVPR2025 is released! We proposed a new sqrt(N) complexity attention mechanism, which enables efficient high resolution image generation. We can generate 8k images with 42x speed up compared to self-attention in StableDiffusionXL! Code: Paper:

Xiaolong Wang

354,791 Aufrufe • vor 1 Jahr

The GitHub Copilot SDK is here 🙌 You can take the same Copilot agentic core that powers GitHub Copilot CLI and embed it in any application, with just a few lines of code.
0:46

The GitHub Copilot SDK is here 🙌 You can take the same Copilot agentic core that powers GitHub Copilot CLI and embed it in any application, with just a few lines of code.

GitHub

299,554 Aufrufe • vor 4 Monaten

Chameleon 🦎 by Meta is now available in Hugging Face transformers 😍 A multimodal model that comes in 7B and 34B sizes 🤩 But what makes this model so special? keep reading ⇣
0:34

Chameleon 🦎 by Meta is now available in Hugging Face transformers 😍 A multimodal model that comes in 7B and 34B sizes 🤩 But what makes this model so special? keep reading ⇣

merve

50,221 Aufrufe • vor 1 Jahr

The Future of Bitcoin is Here! BitcoinOS transforms Bitcoin into a superchain, making it faster, cheaper, and more efficient. We are unlocking the true potential of Bitcoin and driving mainstream adoption. Join us in revolutionizing Bitcoin and shaping the future of finance.
1:31

The Future of Bitcoin is Here! BitcoinOS transforms Bitcoin into a superchain, making it faster, cheaper, and more efficient. We are unlocking the true potential of Bitcoin and driving mainstream adoption. Join us in revolutionizing Bitcoin and shaping the future of finance.

BOS

49,449 Aufrufe • vor 1 Jahr

The new Screenshot to Code from Vercel v0 is insane. I just took a screenshot of a pricing table and it was converted into code using AI in seconds! It even outputs the code and allows you to modify any specific parts.
0:20

The new Screenshot to Code from Vercel v0 is insane. I just took a screenshot of a pricing table and it was converted into code using AI in seconds! It even outputs the code and allows you to modify any specific parts.

Alvaro Cintas

377,988 Aufrufe • vor 2 Jahren

ManipTrans is out on Hugging Face Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning
0:42

ManipTrans is out on Hugging Face Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning

AK

22,136 Aufrufe • vor 1 Jahr

Being loud and aggressive takes a lot of energy. Jeonghan is just energy-efficient.
1:56

Being loud and aggressive takes a lot of energy. Jeonghan is just energy-efficient.

Sugar down bad for Stella

112,936 Aufrufe • vor 11 Monaten

OpenAI Codex is now integrated directly in Visual Studio Code through the new Agent Sessions view - and can be powered by your GitHub Copilot subscription. Try it out now with VS Code Insiders and a Copilot Pro+ subscription. Happy coding!
0:32

OpenAI Codex is now integrated directly in Visual Studio Code through the new Agent Sessions view - and can be powered by your GitHub Copilot subscription. Try it out now with VS Code Insiders and a Copilot Pro+ subscription. Happy coding!

Visual Studio Code

334,902 Aufrufe • vor 7 Monaten