Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

🚀Introducing MiniCPM-V 2.6! 🔥 1、Surpassing GPT-4V in single image, multi-image and video understanding 📸🎥 2、Outperforms GPT-4o mini and Gemini 1.5 on OpenCompass 🏆 3、Real-time video analysis on iPad 📱💨 Try out the best on-device multimodal LLM here！ 👑 GitHub： Huggingface： #MLLM #MiniCPM

OpenBMB

8,862 subscribers

196,372 Aufrufe • vor 2 Jahren •via X (Twitter)

Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von Henry Sibanda

Henry Sibandavor 2 Jahren

Almost everything openai has been holding back because ‘safety’ is available opensource except the speech to speech. And we all still doing just fine…

Profilbild von kache

kachevor 2 Jahren

great work guys

Profilbild von Pabli! 🔥💥💫

Pabli! 🔥💥💫vor 2 Jahren

The previous one was great. This one is superb. 🙌✨

Profilbild von Hailey Collet

Hailey Colletvor 2 Jahren

This + OWL-ViT (or Florence) + SAM2 is going to enable some crazy stuff

Profilbild von Tiezhen WANG

Tiezhen WANGvor 2 Jahren

The demo is super cool!

Profilbild von J Sam🌐

J Sam🌐vor 2 Jahren

🐐

Profilbild von Alex Volkov (Thursd/AI)

Alex Volkov (Thursd/AI)vor 2 Jahren

Going to absolutely mention this on the next @thursdai_pod tomorrow!

Profilbild von The Canaanite

The Canaanitevor 2 Jahren

Wow, that's really something. Amazing work!

Profilbild von pallendromeda

pallendromedavor 2 Jahren

lol it is me

Profilbild von Soible_VR

Soible_VRvor 2 Jahren

whats the status of llamacpp support for MiniCPM family?

Ähnliche Videos

💥 Introducing MiniCPM-o 2.6: An 8B size, GPT-4o level Omni Model runs on device ✨ Highlights: ~Match GPT-4o-202405 in vision, audio and multimodal live streaming ~End-to-end real-time bilingual audio conversation ~Voice cloning & emotion control ~Advanced OCR & video understanding ~Offline iPad-compatible multimodal live streaming 🔗 Try it out: GitHub: HF: Demo:

💥 Introducing MiniCPM-o 2.6: An 8B size, GPT-4o level Omni Model runs on device ✨ Highlights: ~Match GPT-4o-202405 in vision, audio and multimodal live streaming ~End-to-end real-time bilingual audio conversation ~Voice cloning & emotion control ~Advanced OCR & video understanding ~Offline iPad-compatible multimodal live streaming 🔗 Try it out: GitHub: HF: Demo:

OpenBMB

97,770 Aufrufe • vor 1 Jahr

🚀 Introducing MiniCPM-V 4.5 8B: pushing the boundary of multimodal AI! ～ SOTA VL Capability: Surpasses GPT-4o, Gemini 2.0 Pro, Qwen2.5-VL 72B on OpenCompass! ～ "Eagle Eye" Video: 96x visual token compression for high refresh rate and long video understanding ～ Controllable Hybrid Fast/Deep Thinking ～ Strong OCR & Doc Parsing: Surpasses GPT-4o & Gemini 2.5 on OmniDocBench Get ready for the future of multimodal AI 👉 Huggingface｜ Github｜ Gradio｜ #AI #MiniCM #GPT #Gemini #OpenBMB #ArtificialIntelligence #MachineLearning

🚀 Introducing MiniCPM-V 4.5 8B: pushing the boundary of multimodal AI! ～ SOTA VL Capability: Surpasses GPT-4o, Gemini 2.0 Pro, Qwen2.5-VL 72B on OpenCompass! ～ "Eagle Eye" Video: 96x visual token compression for high refresh rate and long video understanding ～ Controllable Hybrid Fast/Deep Thinking ～ Strong OCR & Doc Parsing: Surpasses GPT-4o & Gemini 2.5 on OmniDocBench Get ready for the future of multimodal AI 👉 Huggingface｜ Github｜ Gradio｜ #AI #MiniCM #GPT #Gemini #OpenBMB #ArtificialIntelligence #MachineLearning

OpenBMB

25,157 Aufrufe • vor 11 Monaten

🚨 MiniCPM-o 2.6, an 8B multimodal LLM, outperforms GPT-4o, Gemini 1.5 Pro, and Sonnet in visual (70.2 avg on OpenCompass, 1.8M pixel - 1344 x 1344), speech (bilingual realtime, beats GPT-4o-realtime in ASR/STT), with 75% fewer vision tokens, supporting 30+ languages 🔥

🚨 MiniCPM-o 2.6, an 8B multimodal LLM, outperforms GPT-4o, Gemini 1.5 Pro, and Sonnet in visual (70.2 avg on OpenCompass, 1.8M pixel - 1344 x 1344), speech (bilingual realtime, beats GPT-4o-realtime in ASR/STT), with 75% fewer vision tokens, supporting 30+ languages 🔥

Vaibhav (VB) Srivastav

42,009 Aufrufe • vor 1 Jahr

🥳 Introducing MiniCPM-o 4.5 The first full-duplex omni-modal LLM in open-source community 🎬🎙️ 🔥 Key Highlights: • Full-duplex Omni-modal Live Streaming: The model can see, listen, and speak simultaneously in a real-time conversation without mutual blocking • Proactive Interaction: Moving beyond reactive QA to performing proactive interaction, such as initiating reminders • Leading Performance: Scoring 77.6 on OpenCompass, it outperforms GPT-4o & Gemini 2.0 Pro in vision-language tasks with 9B params The best part? You can experience all above on your PC! #MiniCPM #OpenSource #MultimodalAI #LLM

🥳 Introducing MiniCPM-o 4.5 The first full-duplex omni-modal LLM in open-source community 🎬🎙️ 🔥 Key Highlights: • Full-duplex Omni-modal Live Streaming: The model can see, listen, and speak simultaneously in a real-time conversation without mutual blocking • Proactive Interaction: Moving beyond reactive QA to performing proactive interaction, such as initiating reminders • Leading Performance: Scoring 77.6 on OpenCompass, it outperforms GPT-4o & Gemini 2.0 Pro in vision-language tasks with 9B params The best part? You can experience all above on your PC! #MiniCPM #OpenSource #MultimodalAI #LLM

OpenBMB

398,009 Aufrufe • vor 6 Monaten

Introducing MiniCPM 4.1-8B: First Open-Source Reasoning LLM with Trainable Sparse Attention ✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks! ✅ Fast Generation: 3x decoding speedup for reasoning ✅ Efficient Architecture: Trainable sparse attention, frequency-ranked speculative decoding Download Models: Huggingface: Github: Technical Report: #AI #MiniCPM #LLM #OpenBMB #ArtificialIntelligence #MachineLearning

Introducing MiniCPM 4.1-8B: First Open-Source Reasoning LLM with Trainable Sparse Attention ✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks! ✅ Fast Generation: 3x decoding speedup for reasoning ✅ Efficient Architecture: Trainable sparse attention, frequency-ranked speculative decoding Download Models: Huggingface: Github: Technical Report: #AI #MiniCPM #LLM #OpenBMB #ArtificialIntelligence #MachineLearning

OpenBMB

19,293 Aufrufe • vor 11 Monaten

MiniCPM-V 4.5 achieves an average score of 77.0 on OpenCompass, a comprehensive evaluation of 8 popular benchmarks. With only 8B parameters, it surpasses widely used proprietary models like GPT-4o-latest, Gemini-2.0 Pro, and strong open-source models like Qwen2.5-VL 72B powered by a new unified 3D-Resampler over images and videos, MiniCPM-V 4.5 can now achieve 96x compression rate for video tokens, where 6 448x448 video frames can be jointly compressed into 64 video tokens (normally 1,536 tokens for most MLLMs). vibe coding a Video Chat AI app with MiniCPM-V-4.5 in anycoder

MiniCPM-V 4.5 achieves an average score of 77.0 on OpenCompass, a comprehensive evaluation of 8 popular benchmarks. With only 8B parameters, it surpasses widely used proprietary models like GPT-4o-latest, Gemini-2.0 Pro, and strong open-source models like Qwen2.5-VL 72B powered by a new unified 3D-Resampler over images and videos, MiniCPM-V 4.5 can now achieve 96x compression rate for video tokens, where 6 448x448 video frames can be jointly compressed into 64 video tokens (normally 1,536 tokens for most MLLMs). vibe coding a Video Chat AI app with MiniCPM-V-4.5 in anycoder

AK

19,088 Aufrufe • vor 11 Monaten

New open Omni model released! 👀OpenBMB MiniCPM-o 2.6 is a new 8B parameters, any-to-any multimodal model that can understand vision, speech, and language and runs on edge devices like phones and tablets. TL;DR: 🧠 8B total parameters (SigLip-400M + Whisper-300M + ChatTTS-200M + Qwen2.5-7B) 🔥 Outperforms GPT-4V on visual tasks with 70.2 average score on OpenCompass 🎙️ Best-in-class bilingual speech capabilities with real-time conversation and voice cloning 🎬 Supports multimodal streaming with support for continuous video/audio processing 📱 Runs on iPads and phones and supports 30+ languages 🖼️ Processes images up to 1.8M pixels (1344x1344) with OCR capabilities 🛠️ Easy integration with popular frameworks (llama.cpp, vLLM, Gradio) 🤗 commercial friendly (< 1 mio DAU) and available on Hugging Face

New open Omni model released! 👀OpenBMB MiniCPM-o 2.6 is a new 8B parameters, any-to-any multimodal model that can understand vision, speech, and language and runs on edge devices like phones and tablets. TL;DR: 🧠 8B total parameters (SigLip-400M + Whisper-300M + ChatTTS-200M + Qwen2.5-7B) 🔥 Outperforms GPT-4V on visual tasks with 70.2 average score on OpenCompass 🎙️ Best-in-class bilingual speech capabilities with real-time conversation and voice cloning 🎬 Supports multimodal streaming with support for continuous video/audio processing 📱 Runs on iPads and phones and supports 30+ languages 🖼️ Processes images up to 1.8M pixels (1344x1344) with OCR capabilities 🛠️ Easy integration with popular frameworks (llama.cpp, vLLM, Gradio) 🤗 commercial friendly (< 1 mio DAU) and available on Hugging Face

Philipp Schmid

19,409 Aufrufe • vor 1 Jahr

MiniCPM-o 4.5: Seeing, Listening, and Speaking — All at Once. 👁️👂🗣️ ✨Beyond traditional turn-taking, we’ve built a Native Full-Duplex engine that allows a 9B model to see, listen, and speak in one concurrent, non-blocking stream. Watch how it masters real-world complexity in real-time: 🔔 Proactive Auditory Interaction: Interrupts itself to alert you when it hears a "Ding!" while reading cards. 🎨 Temporal Flow Tracking: Follows your pen in real-time, narrating and "mind-reading" your drawing as you sketch. 🍎 Omni-Perception: Scans groceries & identifies prices on the fly. ✨Why it’s a category-leader: 📌Performance: Surpasses GPT-4o and Gemini 2.0 Pro on OpenCompass (Avg. 77.6). 📌Architecture: End-to-end fusion of SigLip2, Whisper, and CosyVoice2 on a Qwen3-8B base. 📌Efficiency: Full-duplex live streaming now runs locally on PCs via llama.cpp-omni. The era of "Wait-and-Response" AI is over. Proactive, real-time intelligence is now open-source. 🚀Experience it on Hugging Face: 🔗 #MiniCPM #Omnimodal #FullDuplex #EdgeAI #OpenSource #ComputerVision

MiniCPM-o 4.5: Seeing, Listening, and Speaking — All at Once. 👁️👂🗣️ ✨Beyond traditional turn-taking, we’ve built a Native Full-Duplex engine that allows a 9B model to see, listen, and speak in one concurrent, non-blocking stream. Watch how it masters real-world complexity in real-time: 🔔 Proactive Auditory Interaction: Interrupts itself to alert you when it hears a "Ding!" while reading cards. 🎨 Temporal Flow Tracking: Follows your pen in real-time, narrating and "mind-reading" your drawing as you sketch. 🍎 Omni-Perception: Scans groceries & identifies prices on the fly. ✨Why it’s a category-leader: 📌Performance: Surpasses GPT-4o and Gemini 2.0 Pro on OpenCompass (Avg. 77.6). 📌Architecture: End-to-end fusion of SigLip2, Whisper, and CosyVoice2 on a Qwen3-8B base. 📌Efficiency: Full-duplex live streaming now runs locally on PCs via llama.cpp-omni. The era of "Wait-and-Response" AI is over. Proactive, real-time intelligence is now open-source. 🚀Experience it on Hugging Face: 🔗 #MiniCPM #Omnimodal #FullDuplex #EdgeAI #OpenSource #ComputerVision

OpenBMB

115,462 Aufrufe • vor 6 Monaten

🚀 MiniCPM enters the physical world — enabling robots to understand, remember, and act. We open-source MiniCPM-Robot, our first embodied AI model series, including: 🤖 MiniCPM-RobotManip — a 1.5B general-purpose Vision-Language-Action (VLA) model for robotic manipulation. 🐕 MiniCPM-RobotTrack — a compact model for real-world target tracking. ⚡ PhyAI — a high-performance inference framework built for embodied models. Together, they bring efficient, practical, and open embodied intelligence closer to real-world robots. ⭐ GitHub: 🤗 MiniCPM-RobotManip: 🤗 MiniCPM-RobotTrack:

🚀 MiniCPM enters the physical world — enabling robots to understand, remember, and act. We open-source MiniCPM-Robot, our first embodied AI model series, including: 🤖 MiniCPM-RobotManip — a 1.5B general-purpose Vision-Language-Action (VLA) model for robotic manipulation. 🐕 MiniCPM-RobotTrack — a compact model for real-world target tracking. ⚡ PhyAI — a high-performance inference framework built for embodied models. Together, they bring efficient, practical, and open embodied intelligence closer to real-world robots. ⭐ GitHub: 🤗 MiniCPM-RobotManip: 🤗 MiniCPM-RobotTrack:

OpenBMB

329,321 Aufrufe • vor 24 Tagen

1/ Introducing Glider - the smallest model to beat GPT-4o-mini on eval tasks ⚡🚀 - Open source, open weights, open code - Explainable evaluations by nature - Trained on 183 criteria and 685 domains Try it out for free at 🔥

1/ Introducing Glider - the smallest model to beat GPT-4o-mini on eval tasks ⚡🚀 - Open source, open weights, open code - Explainable evaluations by nature - Trained on 183 criteria and 685 domains Try it out for free at 🔥

PatronusAI

14,856 Aufrufe • vor 1 Jahr

🚀 🚀Excited to announce the technical report of MiniCPM-o 4.5! MiniCPM-o 4.5 transitions #AI interaction from traditional turn-based processing to a real-time, native full-duplex stream-based paradigm. 🌊 The Omni-Flow Framework Instead of traditional VAD-based workarounds, we introduce the #Omni-#Flow framework. This unified stream paradigm aligns video, audio, and text on a synchronized millisecond timeline. • Native Full-Duplex: Simultaneous perception and response. • Proactive Interaction: Natively manages turn-taking without external VAD, supports proactive reminding. 📉 9B Scale, SOTA Performance MiniCPM-o 4.5 demonstrates SOTA multimodal intelligence at its scale: • Multimodal Benchmarks: Comparable to #Gemini 2.5 Flash on MMBench EN (87.6) and MathVista (80.1). • Streaming Evaluation: 54.4% win rate on LiveSports-3K-CC, surpassing specialized models. 💻 The Ultimate Edge AI — Fully Functional without Network Connection We are providing one-click installers for Windows (12G VRAM,RTX 5070) and macOS (M1-M5 Max/ M5 Pro). • Local API Support: Deploy your own inference server to integrate native full-duplex into custom apps. • Free Access: We are offering free community API services for exploration. • 100% Private: Your data never leaves your machine. Deploy in under 10 minutes. 🛠️👇 👐 Join the Open Future The weights are open. The protocol is public. 📄 Technical Report: 💻 GitHub: 🤗 HuggingFace: 🌐 Web Demo: #MiniCPMo #OpenSourceAI #EdgeAI #MachineLearning #ComputerVision #LLM

🚀 🚀Excited to announce the technical report of MiniCPM-o 4.5! MiniCPM-o 4.5 transitions #AI interaction from traditional turn-based processing to a real-time, native full-duplex stream-based paradigm. 🌊 The Omni-Flow Framework Instead of traditional VAD-based workarounds, we introduce the #Omni-#Flow framework. This unified stream paradigm aligns video, audio, and text on a synchronized millisecond timeline. • Native Full-Duplex: Simultaneous perception and response. • Proactive Interaction: Natively manages turn-taking without external VAD, supports proactive reminding. 📉 9B Scale, SOTA Performance MiniCPM-o 4.5 demonstrates SOTA multimodal intelligence at its scale: • Multimodal Benchmarks: Comparable to #Gemini 2.5 Flash on MMBench EN (87.6) and MathVista (80.1). • Streaming Evaluation: 54.4% win rate on LiveSports-3K-CC, surpassing specialized models. 💻 The Ultimate Edge AI — Fully Functional without Network Connection We are providing one-click installers for Windows (12G VRAM,RTX 5070) and macOS (M1-M5 Max/ M5 Pro). • Local API Support: Deploy your own inference server to integrate native full-duplex into custom apps. • Free Access: We are offering free community API services for exploration. • 100% Private: Your data never leaves your machine. Deploy in under 10 minutes. 🛠️👇 👐 Join the Open Future The weights are open. The protocol is public. 📄 Technical Report: 💻 GitHub: 🤗 HuggingFace: 🌐 Web Demo: #MiniCPMo #OpenSourceAI #EdgeAI #MachineLearning #ComputerVision #LLM

OpenBMB

147,994 Aufrufe • vor 3 Monaten

1/5 MiniCPM-V 4.6 (1.3B) is now live 🚀🚀 High-res visual processing, optimized for consumer-grade and mobile hardware. We’ve leveraged the latest LLaVA-UHD v4 technique to cut vision encoding costs by 55%, enabling native edge deployment with extreme efficiency. 🔥 Beats Gemma4-E2B-it and Qwen3.5-0.8B across key multimodal and Artificial Analysis benchmarks — scoring higher than Qwen3.5-0.8B using just 2.5% of its token budget. ⚡ TTFT (75.7ms) 2.2x Faster than Qwen3.5-0.8B even with 3136² high-res images. 🏗️ ~1.5x Token Throughput compared with Qwen3.5-0.8B on a single RTX 4090. Try the model here: 🤗 Hugging Face: 💻 GitHub: 🔭 Modelscope: 🌐 Web Demo: 📱 App Demo:

1/5 MiniCPM-V 4.6 (1.3B) is now live 🚀🚀 High-res visual processing, optimized for consumer-grade and mobile hardware. We’ve leveraged the latest LLaVA-UHD v4 technique to cut vision encoding costs by 55%, enabling native edge deployment with extreme efficiency. 🔥 Beats Gemma4-E2B-it and Qwen3.5-0.8B across key multimodal and Artificial Analysis benchmarks — scoring higher than Qwen3.5-0.8B using just 2.5% of its token budget. ⚡ TTFT (75.7ms) 2.2x Faster than Qwen3.5-0.8B even with 3136² high-res images. 🏗️ ~1.5x Token Throughput compared with Qwen3.5-0.8B on a single RTX 4090. Try the model here: 🤗 Hugging Face: 💻 GitHub: 🔭 Modelscope: 🌐 Web Demo: 📱 App Demo:

OpenBMB

352,972 Aufrufe • vor 3 Monaten

🤔The world’s best small models? We immediately compared Mistral-3-8B with our previous-gen model, MiniCPM-4.1 (Both in thinking) 😂The findings are compelling: ✅MiniCPM is still ～2x faster, maintaining a massive speed lead ✅It remains a full generation ahead in capabilities (excluding math/code) For developers prioritizing efficiency and speed, MiniCPM is undeniably the world's best small model.

🤔The world’s best small models? We immediately compared Mistral-3-8B with our previous-gen model, MiniCPM-4.1 (Both in thinking) 😂The findings are compelling: ✅MiniCPM is still ～2x faster, maintaining a massive speed lead ✅It remains a full generation ahead in capabilities (excluding math/code) For developers prioritizing efficiency and speed, MiniCPM is undeniably the world's best small model.

OpenBMB

260,271 Aufrufe • vor 8 Monaten

InternLM-XComposer-2.5 A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output We present InternLM-XComposer-2.5 (IXC-2.5), a versatile large-vision language model that supports long-contextual input and output. IXC-2.5 excels in various text-image comprehension and composition applications, achieving GPT-4V level capabilities with merely 7B LLM backend. Trained with 24K interleaved image-text contexts, it can seamlessly extend to 96K long contexts via RoPE extrapolation. This long-context capability allows IXC-2.5 to excel in tasks requiring extensive input and output contexts. Compared to its previous 2.0 version, InternLM-XComposer-2.5 features three major upgrades in vision-language comprehension: (1) Ultra-High Resolution Understanding, (2) Fine-Grained Video Understanding, and (3) Multi-Turn Multi-Image Dialogue. In addition to comprehension, IXC-2.5 extends to two compelling applications using extra LoRA parameters for text-image composition: (1) Crafting Webpages and (2) Composing High-Quality Text-Image Articles. IXC-2.5 has been evaluated on 28 benchmarks, outperforming existing open-source state-of-the-art models on 16 benchmarks. It also surpasses or competes closely with GPT-4V and Gemini Pro on 16 key tasks.

InternLM-XComposer-2.5 A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output We present InternLM-XComposer-2.5 (IXC-2.5), a versatile large-vision language model that supports long-contextual input and output. IXC-2.5 excels in various text-image comprehension and composition applications, achieving GPT-4V level capabilities with merely 7B LLM backend. Trained with 24K interleaved image-text contexts, it can seamlessly extend to 96K long contexts via RoPE extrapolation. This long-context capability allows IXC-2.5 to excel in tasks requiring extensive input and output contexts. Compared to its previous 2.0 version, InternLM-XComposer-2.5 features three major upgrades in vision-language comprehension: (1) Ultra-High Resolution Understanding, (2) Fine-Grained Video Understanding, and (3) Multi-Turn Multi-Image Dialogue. In addition to comprehension, IXC-2.5 extends to two compelling applications using extra LoRA parameters for text-image composition: (1) Crafting Webpages and (2) Composing High-Quality Text-Image Articles. IXC-2.5 has been evaluated on 28 benchmarks, outperforming existing open-source state-of-the-art models on 16 benchmarks. It also surpasses or competes closely with GPT-4V and Gemini Pro on 16 key tasks.

AK

66,472 Aufrufe • vor 2 Jahren

JUST IN: Google releases Gemini 1.5, a powerful MoE model. It's a huge breakthrough. The model has the longest context window ever seen: 1 million tokens. It can process 1 hour of video, 11 hours of audio, 30,000 lines of code, or 700,000 words in a single prompt. When tested on text, code, image, audio and video evaluations, 1.5 Pro outperforms 1.0 Pro on 87% of the benchmarks used for developing LLMs. You can can sign up in AI Studio to try it out.

JUST IN: Google releases Gemini 1.5, a powerful MoE model. It's a huge breakthrough. The model has the longest context window ever seen: 1 million tokens. It can process 1 hour of video, 11 hours of audio, 30,000 lines of code, or 700,000 words in a single prompt. When tested on text, code, image, audio and video evaluations, 1.5 Pro outperforms 1.0 Pro on 87% of the benchmarks used for developing LLMs. You can can sign up in AI Studio to try it out.

Lior Alexander

83,432 Aufrufe • vor 2 Jahren

VITA Towards Open-Source Interactive Omni Multimodal LLM discuss: The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas. In this paper, we introduce VITA, the first-ever open-source Multimodal Large Language Model (MLLM) adept at simultaneous processing and analysis of Video, Image, Text, and Audio modalities, and meanwhile has an advanced multimodal interactive experience. Starting from Mixtral 8x7B as a language foundation, we expand its Chinese vocabulary followed by bilingual instruction tuning. We further endow the language model with visual and audio capabilities through two-stage multi-task learning of multimodal alignment and instruction tuning. VITA demonstrates robust foundational capabilities of multilingual, vision, and audio understanding, as evidenced by its strong performance across a range of both unimodal and multimodal benchmarks. Beyond foundational capabilities, we have made considerable progress in enhancing the natural multimodal human-computer interaction experience. To the best of our knowledge, we are the first to exploit non-awakening interaction and audio interrupt in MLLM. VITA is the first step for the open-source community to explore the seamless integration of multimodal understanding and interaction. While there is still lots of work to be done on VITA to get close to close-source counterparts, we hope that its role as a pioneer can serve as a cornerstone for subsequent research.

VITA Towards Open-Source Interactive Omni Multimodal LLM discuss: The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas. In this paper, we introduce VITA, the first-ever open-source Multimodal Large Language Model (MLLM) adept at simultaneous processing and analysis of Video, Image, Text, and Audio modalities, and meanwhile has an advanced multimodal interactive experience. Starting from Mixtral 8x7B as a language foundation, we expand its Chinese vocabulary followed by bilingual instruction tuning. We further endow the language model with visual and audio capabilities through two-stage multi-task learning of multimodal alignment and instruction tuning. VITA demonstrates robust foundational capabilities of multilingual, vision, and audio understanding, as evidenced by its strong performance across a range of both unimodal and multimodal benchmarks. Beyond foundational capabilities, we have made considerable progress in enhancing the natural multimodal human-computer interaction experience. To the best of our knowledge, we are the first to exploit non-awakening interaction and audio interrupt in MLLM. VITA is the first step for the open-source community to explore the seamless integration of multimodal understanding and interaction. While there is still lots of work to be done on VITA to get close to close-source counterparts, we hope that its role as a pioneer can serve as a cornerstone for subsequent research.

AK

23,958 Aufrufe • vor 2 Jahren

Introducing "Mine Like A Chad" an entirely AI generated commercial for Tari Every single shot, every sound effect, the music, even the vfx are all AI generated. Breakdown of tools I used: Midjourney & Chat GPT - Image gen and Image editing Topaz Gigapixel - Image Upscale Kling, Luma & Higgsfield - Image to Video and VFX Eleven Labs - Sound Effects Udio - Music generation Davinci Resolve - Editing and Color Grade Huge shoutout to @RealJonahBlake and his Real agency for being amazing partners on this project and helping me out so much.

Introducing "Mine Like A Chad" an entirely AI generated commercial for Tari Every single shot, every sound effect, the music, even the vfx are all AI generated. Breakdown of tools I used: Midjourney & Chat GPT - Image gen and Image editing Topaz Gigapixel - Image Upscale Kling, Luma & Higgsfield - Image to Video and VFX Eleven Labs - Sound Effects Udio - Music generation Davinci Resolve - Editing and Color Grade Huge shoutout to @RealJonahBlake and his Real agency for being amazing partners on this project and helping me out so much.

Kyle Salazar

11,343 Aufrufe • vor 1 Jahr

Today we're launching FilmArena [dot] ai. Biggest release we've ever shipped. The problem: a new SOTA AI image & video model drops every week. OpenAI shipped GPT Image 2 literally yesterday. 1000 endpoints, no honest answer to "which one is best right now?" Arena AI and Artificial Analysis cracked LLM benchmarking. But for creative AI, they're solving the wrong problem. There is no "best image-to-video model." Best at what? World building? Action Sequences? Expressions? Every category has a different winner, and it flips weekly. So we benchmarked 40+ SOTA models with 2M+ votes across 190 countries. By subcategory. Re-ranked every week as new models ship. With thousands of real humans. But that's just half of it. Then there's the SANDBOX. Higgsfield and other aggregators put models in one place. But creators still juggle twelve subscriptions to do one job. FilmArena collapses it into one tab. Every frontier model. One interface. Same price. Call the best, or call 3 at once and compare. The AI film stack has been fragmented since day one. Today it isn't. Go try it free: filmarena [dot] ai Already wild results from this week: 1. OpenAI GPT Image 2 (released yesterday) dominates image editing, but Google DeepMind Nano Banana 2 still wins animated 2. PixVerse C-1 beats Dreamina AI Seedance 2 on animated 3. Veo 3.1 Fast outperforms Veo 3.1 on realistic video And a lot more. Go check it out.

Today we're launching FilmArena [dot] ai. Biggest release we've ever shipped. The problem: a new SOTA AI image & video model drops every week. OpenAI shipped GPT Image 2 literally yesterday. 1000 endpoints, no honest answer to "which one is best right now?" Arena AI and Artificial Analysis cracked LLM benchmarking. But for creative AI, they're solving the wrong problem. There is no "best image-to-video model." Best at what? World building? Action Sequences? Expressions? Every category has a different winner, and it flips weekly. So we benchmarked 40+ SOTA models with 2M+ votes across 190 countries. By subcategory. Re-ranked every week as new models ship. With thousands of real humans. But that's just half of it. Then there's the SANDBOX. Higgsfield and other aggregators put models in one place. But creators still juggle twelve subscriptions to do one job. FilmArena collapses it into one tab. Every frontier model. One interface. Same price. Call the best, or call 3 at once and compare. The AI film stack has been fragmented since day one. Today it isn't. Go try it free: filmarena [dot] ai Already wild results from this week: 1. OpenAI GPT Image 2 (released yesterday) dominates image editing, but Google DeepMind Nano Banana 2 still wins animated 2. PixVerse C-1 beats Dreamina AI Seedance 2 on animated 3. Veo 3.1 Fast outperforms Veo 3.1 on realistic video And a lot more. Go check it out.

Mehul Agarwal

47,260 Aufrufe • vor 3 Monaten

🚀 Meet the new Qwen3-TTS lineup: VoiceDesign & VoiceClone! Create, control, and clone voices—faster and more expressive than ever. ⚡ VoiceDesign-VD-Flash • Fully controllable speech via free-form text instructions — tone, rhythm, emotion, persona • No preset voices. Design your own unique vocal identity • Outperforms GPT-4o-mini-tts & Gemini-2.5-pro on role-play benchmarks ⚡ VoiceClone-VC-Flash • Clone any voice from just 3 seconds of audio • Generate speech in 10 languages (CN / EN / JP / ES + more) • 15% lower WER vs. ElevenLabs & GPT-4o-Audio in multilingual tests • Context-aware cadence for more natural delivery 🎙️ Try it now • Qwen Chat: • Blog:

🚀 Meet the new Qwen3-TTS lineup: VoiceDesign & VoiceClone! Create, control, and clone voices—faster and more expressive than ever. ⚡ VoiceDesign-VD-Flash • Fully controllable speech via free-form text instructions — tone, rhythm, emotion, persona • No preset voices. Design your own unique vocal identity • Outperforms GPT-4o-mini-tts & Gemini-2.5-pro on role-play benchmarks ⚡ VoiceClone-VC-Flash • Clone any voice from just 3 seconds of audio • Generate speech in 10 languages (CN / EN / JP / ES + more) • 15% lower WER vs. ElevenLabs & GPT-4o-Audio in multilingual tests • Context-aware cadence for more natural delivery 🎙️ Try it now • Qwen Chat: • Blog:

Qwen

180,928 Aufrufe • vor 7 Monaten

Leonardo’s Omni Editing is here — powered by FLUX.1 Kontext and GPT-Image-1 You can now edit any image right inside the viewer — with a simple prompt. No switching tools. No breaking flow. This launch is powered by two advanced Omni models: ✅ GPT-Image-1 — for multi-reference creativity and context-aware generation ✅ FLUX.1 Kontext — developed by Black Forest Labs, with Leonardo as an official launch partner. Built for fast, controlled edits that preserve key details. What’s new: • Inline prompt bar built into every generated image • Make fast, precise edits: lighting, objects, layout, even in-image text • Switch between models based on your creative needs • Stay in one workflow — no extra steps, no restarts Try it now 🔥

Leonardo’s Omni Editing is here — powered by FLUX.1 Kontext and GPT-Image-1 You can now edit any image right inside the viewer — with a simple prompt. No switching tools. No breaking flow. This launch is powered by two advanced Omni models: ✅ GPT-Image-1 — for multi-reference creativity and context-aware generation ✅ FLUX.1 Kontext — developed by Black Forest Labs, with Leonardo as an official launch partner. Built for fast, controlled edits that preserve key details. What’s new: • Inline prompt bar built into every generated image • Make fast, precise edits: lighting, objects, layout, even in-image text • Switch between models based on your creative needs • Stay in one workflow — no extra steps, no restarts Try it now 🔥

Leonardo.Ai

33,908 Aufrufe • vor 1 Jahr