正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Real-time webcam demo with Hugging Face SmolVLM and ggml llama.cpp server. All running locally on a Macbook M3

Xuan-Son Nguyen

6,843 subscribers

974,221 次观看 • 1 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

10 条评论

Xuan-Son Nguyen 的头像

Xuan-Son Nguyen1 年前

@ggml_org Check it out:

Jaid 的头像

Jaid1 年前

@huggingface @ggml_org A man is looking over a sink holding some salad.

arXiv Bangers 的头像

arXiv Bangers1 年前

@huggingface @ggml_org Banger

Dmitrijus Drozdovas 的头像

Dmitrijus Drozdovas1 年前

@huggingface @ggml_org This is great! Has a touch of humour as well

Victor M 的头像

Victor M1 年前

@huggingface @ggml_org You dropped this 👑

ᕈablo ᑕarrera (パブロ) 的头像

ᕈablo ᑕarrera (パブロ)1 年前

@huggingface @ggml_org Congrats what amazing work!

yinka 的头像

yinka1 年前

@huggingface @ggml_org so cool and fast!

Grant Weston 的头像

Grant Weston1 年前

@huggingface @ggml_org what exactly are the specs on your machine? its running way faster than I expected. Gemma 3 is nowhere near as fast as that!

Xuan-Son Nguyen 的头像

Xuan-Son Nguyen1 年前

@huggingface @ggml_org I'm using a very small model, SmolVLM 500M, which have decent speed even without a GPU

agoraBlock 的头像

agoraBlock1 年前

@huggingface @ggml_org awesome🔥 do you know some cool production vision rag with citation? thanks in advance

相关视频

i made a computer vision system to monitor the situation - live webcam feed and roboflow RF-DETR for object detection - inputs are fed into SmolVLM which describes what it sees in one sentence - dataviz with vanilla js all running locally in real-time on my macbook air m2

i made a computer vision system to monitor the situation - live webcam feed and roboflow RF-DETR for object detection - inputs are fed into SmolVLM which describes what it sees in one sentence - dataviz with vanilla js all running locally in real-time on my macbook air m2

AA

72,723 次观看 • 7 个月前

🤯 You can now easily face-swap any video, all locally on your Macbook. All you need is a photo and a video. FaceFusion is an open-source face swapper/enhancer with a simple web interface. On an M1/M2 Macbook, it even makes use of Core ML!

🤯 You can now easily face-swap any video, all locally on your Macbook. All you need is a photo and a video. FaceFusion is an open-source face swapper/enhancer with a simple web interface. On an M1/M2 Macbook, it even makes use of Core ML!

Marcel Pociot 🧪

206,509 次观看 • 3 年前

locate-anything.cpp: native C++/ggml (ggml) inference for NVIDIA's LocateAnything-3B, open-vocabulary object detection / visual grounding, one of the neat detection VLMs out there, from the LocalAI team. Same detections as the official model, now running anywhere with no Python and faster, on CPU and GPU. Quantized GGUF on Hugging Face 🤗 Huge thanks to Georgi Gerganov for ggml and to NVIDIAAI for releasing LocateAnything! 🧵

locate-anything.cpp: native C++/ggml (ggml) inference for NVIDIA's LocateAnything-3B, open-vocabulary object detection / visual grounding, one of the neat detection VLMs out there, from the LocalAI team. Same detections as the official model, now running anywhere with no Python and faster, on CPU and GPU. Quantized GGUF on Hugging Face 🤗 Huge thanks to Georgi Gerganov for ggml and to NVIDIAAI for releasing LocateAnything! 🧵

Ettore Di Giacinto

16,770 次观看 • 3 个月前

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

CYANPUPPETS

18,317 次观看 • 9 个月前

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

CYANPUPPETS

32,540 次观看 • 10 个月前

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

CYANPUPPETS

125,171 次观看 • 9 个月前

New demo of #OpenClaw + #ROS + AgenticROS all running locally on a Radxa X4 Robot Operating System (ROS) robot!

New demo of #OpenClaw + #ROS + AgenticROS all running locally on a Radxa X4 Robot Operating System (ROS) robot!

Chris Matthieu

20,374 次观看 • 6 个月前

ds4f-mxfp4 branch running locally on a single M3 Ultra at ~31 toks/s building pagoda and frogger tests. 🚀

ds4f-mxfp4 branch running locally on a single M3 Ultra at ~31 toks/s building pagoda and frogger tests. 🚀

Ivan Fioravanti ᯅ

21,089 次观看 • 2 个月前

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

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

AK

95,337 次观看 • 1 年前

Hi kids, gramps here, taking over for the intern. Just released pi 0.81.0 which features first class integration with Georgi Gerganov wonderful llama.cpp server. Professional video demo recorded in an echo-y Austrian office below. Shout out to our friends at Hugging Face.

Hi kids, gramps here, taking over for the intern. Just released pi 0.81.0 which features first class integration with Georgi Gerganov wonderful llama.cpp server. Professional video demo recorded in an echo-y Austrian office below. Shout out to our friends at Hugging Face.

Pi

109,252 次观看 • 2 个月前

You really can just do things! Use *any* Hugging Face space as a MCP server along with your Local Models! 🔥 Here in we use Qwen 3 30B A3B with ggml llama.cpp and Hugging Face tiny agents to create images via FLUX powered by ZeroGPU ⚡ It's quite a bit crazy to see local models be capable of so much and just be able to understand/ infer from tool description! There's a lot of potential here in automating video generation workflows, content curation and a lot more.. Bonus: you can plug any other Inference Provider if you don't want to run locally too! npx @ huggingface/tiny-agents run [TASK] oh, and we provide both typescript and python client! 🐐

You really can just do things! Use any Hugging Face space as a MCP server along with your Local Models! 🔥 Here in we use Qwen 3 30B A3B with ggml llama.cpp and Hugging Face tiny agents to create images via FLUX powered by ZeroGPU ⚡ It's quite a bit crazy to see local models be capable of so much and just be able to understand/ infer from tool description! There's a lot of potential here in automating video generation workflows, content curation and a lot more.. Bonus: you can plug any other Inference Provider if you don't want to run locally too! npx @ huggingface/tiny-agents run [TASK] oh, and we provide both typescript and python client! 🐐

Vaibhav (VB) Srivastav

39,113 次观看 • 1 年前

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.

CYANPUPPETS

28,871 次观看 • 9 个月前

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.

CYANPUPPETS

15,968 次观看 • 8 个月前

This afternoon I picked up a new Nvidia DGX Spark computer with the goal of trying to run Gemma 4 31b (4bit) on it locally as a server. Just 1.5 hours later, it’s working! Using Open WebUI on my MacBook as the interface and it’s connecting to my DGX Spark running as a Gemma 4 server.

This afternoon I picked up a new Nvidia DGX Spark computer with the goal of trying to run Gemma 4 31b (4bit) on it locally as a server. Just 1.5 hours later, it’s working! Using Open WebUI on my MacBook as the interface and it’s connecting to my DGX Spark running as a Gemma 4 server.

Dave Lee

140,876 次观看 • 5 个月前

PAIR-Diffusion: Object-Level Image Editing with Structure-and-Appearance Paired Diffusion Models Gradio demo is out on Hugging Face Spaces demo:

PAIR-Diffusion: Object-Level Image Editing with Structure-and-Appearance Paired Diffusion Models Gradio demo is out on Hugging Face Spaces demo:

AK

87,766 次观看 • 3 年前

THIS AMERICAN DEVELOPER SPENT WEEKS DEBUGGING TIMEOUT ERRORS IN OLLAMA. THEN HE LOOKED UNDER THE HOOD LM Studio is just llama.cpp Ollama is just llama.cpp so he cloned llama.cpp from source, pulled Qwen 3.6 35B off Hugging Face, set up asymmetric KV quantization and got a local server running on 127.0.0.1:8080 plugged it into VS Code, connected it to OpenClaw, 53 tok/s on an M1 Max with 262K context zero wrappers, zero timeout errors, zero API fees bookmark & like this before your next timeout error hits full breakdown of my raw llama.cpp setup ↓

THIS AMERICAN DEVELOPER SPENT WEEKS DEBUGGING TIMEOUT ERRORS IN OLLAMA. THEN HE LOOKED UNDER THE HOOD LM Studio is just llama.cpp Ollama is just llama.cpp so he cloned llama.cpp from source, pulled Qwen 3.6 35B off Hugging Face, set up asymmetric KV quantization and got a local server running on 127.0.0.1:8080 plugged it into VS Code, connected it to OpenClaw, 53 tok/s on an M1 Max with 262K context zero wrappers, zero timeout errors, zero API fees bookmark & like this before your next timeout error hits full breakdown of my raw llama.cpp setup ↓

leopardracer

240,985 次观看 • 4 个月前

try out the Gradio Demo for AudioLDM: Text-to-Audio Generation with Latent Diffusion Models on Hugging Face demo:

try out the Gradio Demo for AudioLDM: Text-to-Audio Generation with Latent Diffusion Models on Hugging Face demo:

AK

82,138 次观看 • 3 年前

Real-time visual effects, running 100% locally in your browser! 🚀 I created a demo where you can just drop your video and watch it analyze feature points and optical flow for some cool visual effects! Have fun 😊 Demo: #ComputerVision #VFX

Real-time visual effects, running 100% locally in your browser! 🚀 I created a demo where you can just drop your video and watch it analyze feature points and optical flow for some cool visual effects! Have fun 😊 Demo: #ComputerVision #VFX

Alexandre Devaux

33,562 次观看 • 1 年前