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。

New Moondream 2B release! ✨ New features: - Long-form captioning - Open vocab tagging - Better counting, object detection, text understanding - Faster HF transformers inference

vik

28,806 subscribers

51,983 次观看 • 1 年前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

12 条评论

vik 的头像

vik1 年前

Release notes Demo

AssemblyAI 的头像

AssemblyAI1 年前

Announcing: Our most advanced speech-to-text model goes beyond accuracy to capture the real-world complexity of human conversation and deliver reliable, source-of-truth audio data. Explore Universal-2 updates 👇

Shannon Sands 的头像

Shannon Sands1 年前

wen bolting on a diffusion model to an output head and generating ghibli

vik 的头像

vik1 年前

investigating

snow 的头像

snow1 年前

this is a really awesome release video btw, i love this format, pretty clean. gonna fit all the new features into moondream-zig :)

vik 的头像

vik1 年前

possible to integrate xnnpack with zig code? they have good quant matmuls

bellicose_bestie 的头像

bellicose_bestie1 年前

MLX???

vik 的头像

vik1 年前

soon!

Solsticio 的头像

Solsticio1 年前

How good is this for OCR?

vik 的头像

vik1 年前

It was a big focus for this release, but we're only 10% of the way through OCR pretraining. I'd say it's decent but expect a ton more improvement coming soon!

Pratyush 🖇️ life/acc 的头像

Pratyush 🖇️ life/acc1 年前

But can it ghiblify images? 😜

vik 的头像

vik1 年前

watch this space

相关视频

DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding TL;DR: DINO-X Pro: sota model with enhanced perception capabilities for various scenarios; DINO-X Edge: model optimized for faster inference speed and better suited for deployment on edge devices

DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding TL;DR: DINO-X Pro: sota model with enhanced perception capabilities for various scenarios; DINO-X Edge: model optimized for faster inference speed and better suited for deployment on edge devices

Alexandre Morgand

60,743 次观看 • 1 年前

Microsoft's new Florence 2 is big for Computer Vision. It's a merge between Text and Vision. With a single prompt you can instruct the model to do CV tasks like captioning, object detection, grounding, and segmentation. The best part, it only uses a single backbone to handle everything. ▸ Excels in zero-shot performance ▸ Unified model for detection, captioning, etc. ▸ FLD-5B dataset: 5B+ annotations, 126M images ▸ New benchmarks (>5.5+) on COCO, ADE20K

Microsoft's new Florence 2 is big for Computer Vision. It's a merge between Text and Vision. With a single prompt you can instruct the model to do CV tasks like captioning, object detection, grounding, and segmentation. The best part, it only uses a single backbone to handle everything. ▸ Excels in zero-shot performance ▸ Unified model for detection, captioning, etc. ▸ FLD-5B dataset: 5B+ annotations, 126M images ▸ New benchmarks (>5.5+) on COCO, ADE20K

Lior Alexander

186,579 次观看 • 2 年前

We will not accept people’s cancer care being compromised by long waits. Our new Cancer Care Action Plan will deliver better prevention, earlier detection, faster treatment and team-based support services to give patients care they can count on.

We will not accept people’s cancer care being compromised by long waits. Our new Cancer Care Action Plan will deliver better prevention, earlier detection, faster treatment and team-based support services to give patients care they can count on.

David Eby

20,247 次观看 • 3 年前

👉Elements is officially upgraded!🥳 Now with: ⚡️ Faster generation 💬 More accurate prompt response (better semantic understanding) 🌟 Improved picture quality PLUS! The new "Endframes" + "Extend" feature is now live!😍😍 Come and play with these exciting updates! 🎨✨ #KlingAI #ElementsUpgrade #AI

👉Elements is officially upgraded!🥳 Now with: ⚡️ Faster generation 💬 More accurate prompt response (better semantic understanding) 🌟 Improved picture quality PLUS! The new "Endframes" + "Extend" feature is now live!😍😍 Come and play with these exciting updates! 🎨✨ #KlingAI #ElementsUpgrade #AI

Kling AI

62,255 次观看 • 1 年前

The June Pixel Drop includes new features and updates that make your devices more personalized and helpful. You’ll now be able to: ✨ React in real-time with Screen reactions (no green screen required) ✨ Blend any combination of text, images and video to create your own high-quality video with Gemini Omni ✨ Create your own custom soundtrack in Gemini from an idea or photo ✨ Turn any app into a compact, floating window to make multitasking smoother ✨ Use Voice Translate on more devices to translate phone calls in real time ✨ Chat smarter with Magic Cue in more apps ✨ Use call features like Take a Message in more regions ✨ Automatically notify your loved ones in an emergency with features like Car Crash Detection, Fall Detection and Loss of Pulse Detection ✨ Edit your photos by simply asking in more regions

The June Pixel Drop includes new features and updates that make your devices more personalized and helpful. You’ll now be able to: ✨ React in real-time with Screen reactions (no green screen required) ✨ Blend any combination of text, images and video to create your own high-quality video with Gemini Omni ✨ Create your own custom soundtrack in Gemini from an idea or photo ✨ Turn any app into a compact, floating window to make multitasking smoother ✨ Use Voice Translate on more devices to translate phone calls in real time ✨ Chat smarter with Magic Cue in more apps ✨ Use call features like Take a Message in more regions ✨ Automatically notify your loved ones in an emergency with features like Car Crash Detection, Fall Detection and Loss of Pulse Detection ✨ Edit your photos by simply asking in more regions

Google

96,570 次观看 • 2 个月前

Smart Turn v2: open source, native audio turn detection in 14 languages. New checkpoint of the open source, open data, open training code, semantic VAD model on Hugging Face, fal, and Pipecat AI. - 3x faster inference (12ms on an L40) - 14 languages (13 more than v1, which was english-only) - New synthetic data set `chirp_3_all` with ~163k audio samples - 99% accuracy on held out `human_5_all` test data Good turn detection is critical for voice agents. This model "understands" both semantic and audio patterns, and mitigates the voice AI trade-off between unwanted turn latency vs the agent interrupting people before they are finished speaking. Training scripts for both Modal and local training are in the repo. We want to make it as easy as possible to contribute to or customize this model! Here's a demo running the smart-turn model with default settings, aimed at generally hitting 400ms total turn detection time. You can tune things to be faster, too. You can help by contributing data, doing architecture expermints, or cleaning open source data! Keep reading ...

Smart Turn v2: open source, native audio turn detection in 14 languages. New checkpoint of the open source, open data, open training code, semantic VAD model on Hugging Face, fal, and Pipecat AI. - 3x faster inference (12ms on an L40) - 14 languages (13 more than v1, which was english-only) - New synthetic data set `chirp_3_all` with ~163k audio samples - 99% accuracy on held out `human_5_all` test data Good turn detection is critical for voice agents. This model "understands" both semantic and audio patterns, and mitigates the voice AI trade-off between unwanted turn latency vs the agent interrupting people before they are finished speaking. Training scripts for both Modal and local training are in the repo. We want to make it as easy as possible to contribute to or customize this model! Here's a demo running the smart-turn model with default settings, aimed at generally hitting 400ms total turn detection time. You can tune things to be faster, too. You can help by contributing data, doing architecture expermints, or cleaning open source data! Keep reading ...

kwindla

42,246 次观看 • 1 年前

🚀 Project Zero – Release #5 Our biggest upgrade so far is live, a major step forward in usability, security, and readiness for scale. ✨ Full Frontend Redesign for a faster, cleaner, more intuitive experience 📊 New My Dashboard to track activity, progress, and key info in one place 👤 Updated Profile & Settings pages with clearer layouts and smoother management 🛡️ New Authentication Flow + Whitelist Removal for stronger, scalable security This release makes Project Zero feel more polished, more reliable, and better prepared for the next phase: welcoming more users, partners, and enterprise integrations. 👉 Try it: 👉 Full release note:

Project Zero

25,243 次观看 • 9 个月前

QVAC SDK 0.12.0 is now live, bringing longer context, increased memory optimisation, new modalities, and broader ecosystem support directly to your device. Key Features and Updates: - TurboQuant KV-Cache Quantization: Fit much longer context in the same memory. TurboQuant, an algorithm from Google Research, compresses the KV cache by up to 5x, near-lossless. - Text-to-Video: Generate video from a text prompt, fully local, with the new wan2.1 model in the Diffusion addon - Apple Metal Performance for Flux2-klein: Diffusion on Apple Silicon now matches MLX performance, the native benchmark for Apple GPUs - Robot Control (new VLA addon): A GGML-based Vision-Language-Action addon brings fast, efficient robot control to edge devices - Coding Assistant / Harness Support: QVAC now works with OpenCode and OpenClaw as a local provider. A new @qvac/ai-sdk-provider package automates model registry and provider integration - Cross-Platform Voice: Text-to-speech and Parakeet transcription moved from ONNX to the GGML engine for better CPU and GPU support on macOS, iOS, Windows, Linux, and Android. Parakeet also adds long-term streaming diarization (tracking who spoke when on live audio) - Faster Lightweight Visual Classification: A new GGML-based Classification addon delivers millisecond-level classification, useful where a vision-language model (VLM) would be unnecessarily slow - Under the Hood: Fabric synced to llama.cpp v8828 (from v8189), plus GPU acceleration added to image-upscale models for faster results Full release notes:

QVAC SDK 0.12.0 is now live, bringing longer context, increased memory optimisation, new modalities, and broader ecosystem support directly to your device. Key Features and Updates: - TurboQuant KV-Cache Quantization: Fit much longer context in the same memory. TurboQuant, an algorithm from Google Research, compresses the KV cache by up to 5x, near-lossless. - Text-to-Video: Generate video from a text prompt, fully local, with the new wan2.1 model in the Diffusion addon - Apple Metal Performance for Flux2-klein: Diffusion on Apple Silicon now matches MLX performance, the native benchmark for Apple GPUs - Robot Control (new VLA addon): A GGML-based Vision-Language-Action addon brings fast, efficient robot control to edge devices - Coding Assistant / Harness Support: QVAC now works with OpenCode and OpenClaw as a local provider. A new @qvac/ai-sdk-provider package automates model registry and provider integration - Cross-Platform Voice: Text-to-speech and Parakeet transcription moved from ONNX to the GGML engine for better CPU and GPU support on macOS, iOS, Windows, Linux, and Android. Parakeet also adds long-term streaming diarization (tracking who spoke when on live audio) - Faster Lightweight Visual Classification: A new GGML-based Classification addon delivers millisecond-level classification, useful where a vision-language model (VLM) would be unnecessarily slow - Under the Hood: Fabric synced to llama.cpp v8828 (from v8189), plus GPU acceleration added to image-upscale models for faster results Full release notes:

QVAC

9,932,369 次观看 • 2 个月前

Meet LongCat-Video-Avatar: a robust audio-driven avatar model that pushes the boundaries of long-form video generation. Compared with the previous InfiniteTalk, LongCat-Video-Avatar delivers far better long-sequence stability and realism. New highlights： ⚙ Built on the LongCat-Video architecture, now supporting Audio-Text-to-Video (AT2V), Audio-Text-Image-to-Video (ATI2V), and Video Continuation modes. 🎭 Open-source SOTA Realism: Ranked 1st in overall anthropomorphism scores for both single and multi-subject scenarios in EvalTalker evaluations (492 participants, 3 independent raters per video). ♾ High-quality long videos: Cross-Chunk Latent Stitching prevents pixel degradation and error accumulation over time, ensuring seamless stitching quality. 🔒 Long-term consistency: Reference Skip Attention maintains ID consistency while eliminating rigid copy-paste artifacts. 🪄 Supports multi-person and infinite-length video generation. 🔗Open-sourced Code: Hugging Face: Project: Paper:

Meituan LongCat

28,170 次观看 • 8 个月前

New short course: Open Source Models with Hugging Face 🤗, taught by Maria Khalusova, Marc Sun, and Younes Belkada! Hugging Face has been a game changer by letting you quickly grab any of hundreds of thousands of already-trained open source models to assemble into new applications. This course teaches you best practices for building this way, including how to search and choose among models. You’ll learn to use the Transformers library and walk through multiple models for text, audio, and image processing, including zero-shot image segmentation, zero-shot audio classification, and speech recognition. You'll also learn to use multimodal models for visual question answering, image search, and image captioning. Finally, you’ll learn how to demo what you build locally, on the cloud, or via an API using Gradio and Hugging Face Spaces. You can sign up here:

New short course: Open Source Models with Hugging Face 🤗, taught by Maria Khalusova, Marc Sun, and Younes Belkada! Hugging Face has been a game changer by letting you quickly grab any of hundreds of thousands of already-trained open source models to assemble into new applications. This course teaches you best practices for building this way, including how to search and choose among models. You’ll learn to use the Transformers library and walk through multiple models for text, audio, and image processing, including zero-shot image segmentation, zero-shot audio classification, and speech recognition. You'll also learn to use multimodal models for visual question answering, image search, and image captioning. Finally, you’ll learn how to demo what you build locally, on the cloud, or via an API using Gradio and Hugging Face Spaces. You can sign up here:

Andrew Ng

224,538 次观看 • 2 年前

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

Tencent Hy

89,257 次观看 • 11 个月前

Marketing Skills v2.0 is finally here! 🎉 I've been working on this for over a month. The biggest release yet. Shorter names, one unified CRO skill, and a foundation built to scale. What's new: ✨ Cleaner, faster skill names → /paid-ads → /ads → /email-sequence → /emails → /social-content → /social → /launch-strategy → /launch → /pricing-strategy → /pricing → /referral-program → /referrals → + 11 more 🔗 /cro is now one skill Page CRO + Form CRO merged. One mental model for every conversion optimization workflow. 📦 100+ refinements across the entire skill set 40 skills. 52 tool integrations. 100% evals coverage. Free and open source. 🚨 Heads up — v2.0 is a breaking change, so reinstall to get the new names: npx skills add coreyhaines31/marketingskills

Marketing Skills v2.0 is finally here! 🎉 I've been working on this for over a month. The biggest release yet. Shorter names, one unified CRO skill, and a foundation built to scale. What's new: ✨ Cleaner, faster skill names → /paid-ads → /ads → /email-sequence → /emails → /social-content → /social → /launch-strategy → /launch → /pricing-strategy → /pricing → /referral-program → /referrals → + 11 more 🔗 /cro is now one skill Page CRO + Form CRO merged. One mental model for every conversion optimization workflow. 📦 100+ refinements across the entire skill set 40 skills. 52 tool integrations. 100% evals coverage. Free and open source. 🚨 Heads up — v2.0 is a breaking change, so reinstall to get the new names: npx skills add coreyhaines31/marketingskills

Corey Haines

138,293 次观看 • 3 个月前

NVIDIA Cosmos Reason 2 is here. 🥳 An open, highly accurate reasoning vision language model for physical AI, featuring: ✅ Improved spatio-temporal understanding and timestamp precision ✅ Flexible deployment with 2B and 8B model sizes ✅ Long-context reasoning with up to 256K tokens ✅ Expanded visual perception across complex environments We also have new Cosmos releases: Predict 2.5, Transfer 2.5, and the NVIDIA GR00T N1.6 robot foundation model. 📗Read our technical blog: 🤗 Download Cosmos Reason 2 on Hugging Face:

NVIDIA Cosmos Reason 2 is here. 🥳 An open, highly accurate reasoning vision language model for physical AI, featuring: ✅ Improved spatio-temporal understanding and timestamp precision ✅ Flexible deployment with 2B and 8B model sizes ✅ Long-context reasoning with up to 256K tokens ✅ Expanded visual perception across complex environments We also have new Cosmos releases: Predict 2.5, Transfer 2.5, and the NVIDIA GR00T N1.6 robot foundation model. 📗Read our technical blog: 🤗 Download Cosmos Reason 2 on Hugging Face:

NVIDIA AI Developer

45,677 次观看 • 7 个月前

Meet LongCat-Video-Avatar 1.5🐱—our upgraded, open-source digital human framework. Built for real production, not just short demos. What's New: 🔹 Upgraded Audio Encoder: Replaces Wav2Vec2 with Whisper-Large, yielding significantly smoother and more natural lip dynamics. 🔹 Production-Ready Stability: Achieves accurate lip-synchronization, full-body temporal stability, and robust long-video generation with strict identity consistency. 🔹 Stylized Domain Generalization: Robustly generalizes to anime, animals, and complex real-world conditions such as multi-person interactions and object handling. 🔹 Efficient 8-Step Inference: Advanced step distillation accelerates inference to 8 NFE, balancing cost-effective serving with exceptional visual fidelity. 📊 LongCat-Video-Avatar 1.5 performs strongly in realism, naturalness, and stability, outperforming leading open-source models and closed systems. 🐱 Avatar 1.5 framework is now open source: 🔗 Weights & Code: 🔗 HuggingFace: 🔗 Tech Report: 🔗 Project Page:

Meituan LongCat

31,310 次观看 • 2 个月前

Greetings. I've just pressed the option key and now I am holding it, which is why you see that small reddish capsule at the top of my screen, flashing in synchrony with my voice volume, etcetera. Anyway, I hope that didn't somehow clip the audio. The reason I'm doing this is to show off the fact that I've integrated NVIDIA's new parakeet, or relatively new parakeet, voice transcription speech to text model into Hex, my open source free Mac audio transcription tool. And Parakeet is ridiculously fast, so I will stop rambling in just a moment and release the option key, and it will transcribe and paste into the text box. So yeah, that was very fast. Faster than Whisper. Certainly faster and more accurate than Mac dictation. Uh so yeah, give it a shot and enjoy. The download link to Hex will be uh pasted beneath this transcription.

Greetings. I've just pressed the option key and now I am holding it, which is why you see that small reddish capsule at the top of my screen, flashing in synchrony with my voice volume, etcetera. Anyway, I hope that didn't somehow clip the audio. The reason I'm doing this is to show off the fact that I've integrated NVIDIA's new parakeet, or relatively new parakeet, voice transcription speech to text model into Hex, my open source free Mac audio transcription tool. And Parakeet is ridiculously fast, so I will stop rambling in just a moment and release the option key, and it will transcribe and paste into the text box. So yeah, that was very fast. Faster than Whisper. Certainly faster and more accurate than Mac dictation. Uh so yeah, give it a shot and enjoy. The download link to Hex will be uh pasted beneath this transcription.

Kit Langton

14,301 次观看 • 9 个月前

🪽 𝗔𝗻𝗴𝗲𝗹𝗶𝗰 𝗢𝗽𝗲𝗻 𝗔𝗹𝗽𝗵𝗮 𝗥𝗲𝗹𝗲𝗮𝘀𝗲 𝗗𝗮𝘁𝗲 𝗔𝗻𝗻𝗼𝘂𝗻𝗰𝗲𝗱 - 𝟲 𝗔𝘂𝗴𝘂𝘀𝘁 𝟮𝟬𝟮𝟰! We are ecstatic to announce that Angelic’s long-awaited Open Alpha will launch on August 6th! This historic event marks our first public launch and is one of the biggest milestones in our history. You're in store for an incredible new build featuring fantastic new features, along with exciting quests, rewards, and gameplay sessions with our partners, including Saga Intern, Aethir, , CARV, BLOCKLORDS, Luc and more! Stay tuned as we roll out the schedule of events leading up to and following our trailer release on August 6th! 🫶 #OpenAlphaRelease #strategy #RPG

🪽 𝗔𝗻𝗴𝗲𝗹𝗶𝗰 𝗢𝗽𝗲𝗻 𝗔𝗹𝗽𝗵𝗮 𝗥𝗲𝗹𝗲𝗮𝘀𝗲 𝗗𝗮𝘁𝗲 𝗔𝗻𝗻𝗼𝘂𝗻𝗰𝗲𝗱 - 𝟲 𝗔𝘂𝗴𝘂𝘀𝘁 𝟮𝟬𝟮𝟰! We are ecstatic to announce that Angelic’s long-awaited Open Alpha will launch on August 6th! This historic event marks our first public launch and is one of the biggest milestones in our history. You're in store for an incredible new build featuring fantastic new features, along with exciting quests, rewards, and gameplay sessions with our partners, including Saga Intern, Aethir, , CARV, BLOCKLORDS, Luc and more! Stay tuned as we roll out the schedule of events leading up to and following our trailer release on August 6th! 🫶 #OpenAlphaRelease #strategy #RPG

Angelic: Dark Symphony

1,111,322 次观看 • 2 年前

✨ Meet our new open family of models: NVIDIA Nemotron 3 Open in weights, data, tools, and training, Nemotron 3 is built for multi-agent apps and features: • An efficient hybrid Mamba‑Transformer MoE architecture • 1M token context for long-term memory and improved reasoning • Multi‑environment reinforcement learning via NeMo Gym for advanced skill adaptation Plus NVFP4 pre-training, latent MoE, 1T tokens of data, and more. 📗Read the details in our tech blog: 🤗 Try the model on Hugging Face:

✨ Meet our new open family of models: NVIDIA Nemotron 3 Open in weights, data, tools, and training, Nemotron 3 is built for multi-agent apps and features: • An efficient hybrid Mamba‑Transformer MoE architecture • 1M token context for long-term memory and improved reasoning • Multi‑environment reinforcement learning via NeMo Gym for advanced skill adaptation Plus NVFP4 pre-training, latent MoE, 1T tokens of data, and more. 📗Read the details in our tech blog: 🤗 Try the model on Hugging Face:

NVIDIA AI Developer

68,941 次观看 • 8 个月前

🎉 恭喜发财🧧🐍 As we welcome the Chinese New Year, we're thrilled to announce the launch of Qwen2.5-VL , our latest flagship vision-language model! 🚀 💗 Qwen Chat: 📖 Blog: 🤗 Hugging Face: 🤖 ModelScope: 🌟 Key Highlights: * Visual Understanding : From flowers to complex charts, Qwen2.5-VL sees it all! * Agentic Capabilities : It’s a visual agent that can reason and interact with tools like computers & phones. * Long Video Comprehension : Captures events in videos over 1 hour long! ⏳🎥 * Precise Localization : Generates bounding boxes & JSON outputs for accurate object detection. * Structured Data Outputs : Perfect for finance & commerce, handling invoices, forms & more! 💼📊 Try Qwen2.5-VL now at Qwen Chat or explore models on Hugging Face & ModelScope . 🌐

🎉 恭喜发财🧧🐍 As we welcome the Chinese New Year, we're thrilled to announce the launch of Qwen2.5-VL , our latest flagship vision-language model! 🚀 💗 Qwen Chat: 📖 Blog: 🤗 Hugging Face: 🤖 ModelScope: 🌟 Key Highlights: * Visual Understanding : From flowers to complex charts, Qwen2.5-VL sees it all! * Agentic Capabilities : It’s a visual agent that can reason and interact with tools like computers & phones. * Long Video Comprehension : Captures events in videos over 1 hour long! ⏳🎥 * Precise Localization : Generates bounding boxes & JSON outputs for accurate object detection. * Structured Data Outputs : Perfect for finance & commerce, handling invoices, forms & more! 💼📊 Try Qwen2.5-VL now at Qwen Chat or explore models on Hugging Face & ModelScope . 🌐

Qwen

762,520 次观看 • 1 年前