Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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:show more

Meituan LongCat

15,197 subscribers

33,081 views • 5 months ago •via X (Twitter)

Arts Education Science & Technology

Anya Rossi• Live Now

Private livecam show

11 Comments

Garry5 months ago

How much time it will take to generate 60 seconds of avatar video (720p) with audio upload?

ZIAISTAN5 months ago

Amazing

blankbrain5 months ago

oh finally , some good open sauce stuff from good plebs

Alice The Ai Expert5 months ago

Open digital humans leveled up

T10005 months ago

@toyxyz3 This is great.

Ruzaina5 months ago

Open-source avatars are leveling up

.5 months ago

the question is: it is better then ltx 2.3? its faster? if dont, it is useless

𝘿𝙖𝙫𝙞𝙙 ✦ 𝙈𝙂𝙏5 months ago

whisper swap is the right call, wav2vec2 was always the weak link for lip sync. Curious what your real-time latency looks like end-to-end on a production load

Sani Ai Tech5 months ago

Open-source digital humans with 8-step inference and solid lip sync is a big deal

chener5 months ago

@HeyGen

Artyom5 months ago

Is this based on wan 2.2 video model?

Related Videos

INSANE...this is an Open Source Video model available for free on Hugging Face. LongCat just dropped an amazing video avatar model that can do crazy things. And it's 100% Opensource.

Shubham Saboo

30,601 views • 5 months ago

Skywork Matrix-Game 3.0 is here! FULLY OPEN SOURCE! Real-Time and Streaming Interactive World Model with Long-Horizon Memory - Fully open source: code, model, and technical report - 720p @ 40FPS with a 5B model - Minute-long memory consistency - Trained on Unreal Engine + AAA games + real-world data - Scales up to 28B MoE for quality, dynamics, and generalization Homepage 👉 Code 👉 Model 👉 Tech report 👉 Create. Explore. Play. With Matrix-Game 3.0

Skywork Matrix-Game 3.0 is here! FULLY OPEN SOURCE! Real-Time and Streaming Interactive World Model with Long-Horizon Memory - Fully open source: code, model, and technical report - 720p @ 40FPS with a 5B model - Minute-long memory consistency - Trained on Unreal Engine + AAA games + real-world data - Scales up to 28B MoE for quality, dynamics, and generalization Homepage 👉 Code 👉 Model 👉 Tech report 👉 Create. Explore. Play. With Matrix-Game 3.0

Skywork

54,911 views • 7 months ago

THIS IS FUCKING INSANE another Chinese developer just released a FREE tool that can Source AI avatar tool. it just got released and it already has 32,000 stars It is called LongCat Avatar and it can turn a single photo + audio file into a realistic talking video with synchronized lip movements. The workflow is too easy: → Upload a photo → Add your audio → Let the model generate the video you can create talking-avatar videos that run for several minutes, without a camera, studio, or expensive production setup. It’s open source and 100% free to use. The repo is public, so you can run it yourself. AI avatar platforms have some serious competition. will be dropping more free tools soon, so bookmark

Innopro

13,185 views • 1 month ago

1/3 🚀Thrilled to introduce Wan2.1-FLF2V-14B - our first 14B-parameter large model for First-Last-Frame to video generation! Open-source, open-source, open-source! Empowering digital artists with unprecedented efficiency and creative flexibility. #wan #AIGC #alart

1/3 🚀Thrilled to introduce Wan2.1-FLF2V-14B - our first 14B-parameter large model for First-Last-Frame to video generation! Open-source, open-source, open-source! Empowering digital artists with unprecedented efficiency and creative flexibility. #wan #AIGC #alart

Wan

197,448 views • 1 year ago

Introducing Wan-Animate-2. A major upgrade to our open-source character animation model with: • High Fidelity Character Animation • Multi-Character Animation • Text-Controlled Camera Viewpoint • Real-Time Streaming Generation Weights, demos, and docs 👇

Introducing Wan-Animate-2. A major upgrade to our open-source character animation model with: • High Fidelity Character Animation • Multi-Character Animation • Text-Controlled Camera Viewpoint • Real-Time Streaming Generation Weights, demos, and docs 👇

Wan

88,646 views • 3 months ago

Stable Audio 3 by Stability AI is just out It mainly comes with 3 open source variants: - Stable Audio 3 Medium (2B) - Stable Audio 3 Small (0.6B) - Music - Stable Audio 3 Small (0.6B) - VFX (and a "large" closed variant) The open models are really fast and high quality

Stable Audio 3 by Stability AI is just out It mainly comes with 3 open source variants: - Stable Audio 3 Medium (2B) - Stable Audio 3 Small (0.6B) - Music - Stable Audio 3 Small (0.6B) - VFX (and a "large" closed variant) The open models are really fast and high quality

apolinario (poli)

41,854 views • 5 months ago

AI video just reached a new level. Seedance 1.5 Pro by BytePlus turns static images into cinematic videos with real action and realism. Key features: • Native audio generation with ultra precise lip sync • Multilingual dialogues with multiple speakers • Natural motion, expressive emotions and cinematic quality visuals • Stable, premium output ready for narration, ads and professional creative work This does not look like an AI video. It feels like real footage, synchronized, expressive and production ready. #Seedance #AIVideo #VideoGeneration #BytePlusAI

AI video just reached a new level. Seedance 1.5 Pro by BytePlus turns static images into cinematic videos with real action and realism. Key features: • Native audio generation with ultra precise lip sync • Multilingual dialogues with multiple speakers • Natural motion, expressive emotions and cinematic quality visuals • Stable, premium output ready for narration, ads and professional creative work This does not look like an AI video. It feels like real footage, synchronized, expressive and production ready. #Seedance #AIVideo #VideoGeneration #BytePlusAI

Enzo Sanchez | IA

95,539 views • 10 months ago

🎮Get a first look at Tencent HY World 1.5 (WorldPlay)! 🎮 Our newest world model with real-time interaction and long-term memory. It’s going *open-source* tomorrow.

🎮Get a first look at Tencent HY World 1.5 (WorldPlay)! 🎮 Our newest world model with real-time interaction and long-term memory. It’s going open-source tomorrow.

Tengfei Wang

114,601 views • 11 months ago

my animated bot avatars are OSS now! introducing: 🐱 Open Bot Avatar a JSON spec and renderer for interactive agent avatars everything open source & MIT licensed, excited to see what you build with it!

Dominik Scholz

132,276 views • 12 days ago

Krea 2 is back and this time the weights are OPEN. This open source release ships with two models designed to work together — Krea 2 RAW and Krea 2 Turbo. RAW is for training, Turbo is for inference.

Krea 2 is back and this time the weights are OPEN. This open source release ships with two models designed to work together — Krea 2 RAW and Krea 2 Turbo. RAW is for training, Turbo is for inference.

ComfyUI

32,394 views • 4 months ago

🚀 LongCat-Video Now Open-Source: Text/Image-to-Video + Video Continuation in One Model 🏆 Text/Image-to-Video Performance Hits Open-Source SOTA 🎬 Minutes-Long High-Quality Videos: No Color Drift/Quality Loss (Industry-Standout) ⚙ 13.6B Params | Strong Open-Source DiT-Based Unified Multitask Video Base Model ⚡ C2F Pipeline + Block Sparse Attention: 720p/30fps Video in Minutes 🤗 Open-Source Links: GitHub： Hugging Face： Project Page：

🚀 LongCat-Video Now Open-Source: Text/Image-to-Video + Video Continuation in One Model 🏆 Text/Image-to-Video Performance Hits Open-Source SOTA 🎬 Minutes-Long High-Quality Videos: No Color Drift/Quality Loss (Industry-Standout) ⚙ 13.6B Params | Strong Open-Source DiT-Based Unified Multitask Video Base Model ⚡ C2F Pipeline + Block Sparse Attention: 720p/30fps Video in Minutes 🤗 Open-Source Links: GitHub： Hugging Face： Project Page：

Meituan LongCat

43,895 views • 1 year ago

🚨 The moment we’ve all been waiting for is here! 🚨 The upgraded launches tomorrow! 🔹 Officially Licensed 🔹 Buyback and Burn Feature 🔹 Gamble with BAZED Token 🔹 New Original Games 🔹 New Sportsbook 🔹 New Slots Provider 🔹 Rakeback and Cashback Get ready for a whole new $BAZED experience!

🚨 The moment we’ve all been waiting for is here! 🚨 The upgraded launches tomorrow! 🔹 Officially Licensed 🔹 Buyback and Burn Feature 🔹 Gamble with BAZED Token 🔹 New Original Games 🔹 New Sportsbook 🔹 New Slots Provider 🔹 Rakeback and Cashback Get ready for a whole new $BAZED experience!

BazedBet.com

59,073 views • 1 year ago

Ubisoft La Forge open-sourced its PBR material model CHORD, together with ComfyUI custom nodes for end-to-end AI material generation. This is a real step toward generative AI in AAA game pipelines and demonstrates how ComfyUI has grown from an open-source community tool to a production platform. Huge thanks to the Ubisoft La Forge team for giving back real production-grade tools to the open source community.

Ubisoft La Forge open-sourced its PBR material model CHORD, together with ComfyUI custom nodes for end-to-end AI material generation. This is a real step toward generative AI in AAA game pipelines and demonstrates how ComfyUI has grown from an open-source community tool to a production platform. Huge thanks to the Ubisoft La Forge team for giving back real production-grade tools to the open source community.

ComfyUI

96,515 views • 11 months ago

🔬 Quantum computing is enabling new possibilities in research and science. With Dynex’s Quantum-as-a-Service (#QaaS) technology, researchers can solve real-world problems at scale with unprecedented speed and efficiency. Fields of potential Use Cases in Optimizations are: 🔹 Advanced quantum physics research. 🔹 Accelerating molecular and genetic studies in biology. 🔹 Climate modeling for precise simulations. Dynex’s advanced technology supports scientists in testing hypotheses, exploring new theories, and tackling problems that were previously out of reach. 🔗 Learn more:

🔬 Quantum computing is enabling new possibilities in research and science. With Dynex’s Quantum-as-a-Service (#QaaS) technology, researchers can solve real-world problems at scale with unprecedented speed and efficiency. Fields of potential Use Cases in Optimizations are: 🔹 Advanced quantum physics research. 🔹 Accelerating molecular and genetic studies in biology. 🔹 Climate modeling for precise simulations. Dynex’s advanced technology supports scientists in testing hypotheses, exploring new theories, and tackling problems that were previously out of reach. 🔗 Learn more:

Dynex

13,722 views • 1 year ago

🔴 BOMBSHELL: Some Chinese developers just humiliated the entire paid AI video industry You upload a photo You upload an audio And it generates a video of a person speaking in sync that lasts for minutes It's called LongCat-Avatar It's open source and on top of that FREE What used to require a camera, studio, and editing now comes straight from a repo I'll leave the repo link in the comments

Abir Rahman

276,371 views • 2 months ago

Gemma 4 is here! Our most intelligent open models to date, are built on the same world-class research and tech as Gemini 3, and are sized to run and fine-tune efficiently on local hardware. Check out what Google Gemma 4 brings to devs: 💎 Advanced Reasoning: Deep logic tasks, complex multi-step planning, and beyond 💎 Longer context: Seamlessly analyze entire codebases with context windows of 128K tokens for our edge models and 256K tokens for our largest models 💎 Vision and audio: Rich, multimodal interactions out of the box 💎 140+ languages: Trained on 140+ languages 💎 Apache 2.0 license: industry-standard open-source license

Gemma 4 is here! Our most intelligent open models to date, are built on the same world-class research and tech as Gemini 3, and are sized to run and fine-tune efficiently on local hardware. Check out what Google Gemma 4 brings to devs: 💎 Advanced Reasoning: Deep logic tasks, complex multi-step planning, and beyond 💎 Longer context: Seamlessly analyze entire codebases with context windows of 128K tokens for our edge models and 256K tokens for our largest models 💎 Vision and audio: Rich, multimodal interactions out of the box 💎 140+ languages: Trained on 140+ languages 💎 Apache 2.0 license: industry-standard open-source license

Google for Developers

270,448 views • 7 months ago

Real-world and digital asset tokenization is the next step for #web3 and it begins with #Hedera. #RWA 🔗

Real-world and digital asset tokenization is the next step for #web3 and it begins with #Hedera. #RWA 🔗

Hedera

99,782 views • 1 year ago

Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation paper page: Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring temporal consistency across video frames remains a formidable challenge. This paper proposes a novel zero-shot text-guided video-to-video translation framework to adapt image models to videos. The framework includes two parts: key frame translation and full video translation. The first part uses an adapted diffusion model to generate key frames, with hierarchical cross-frame constraints applied to enforce coherence in shapes, textures and colors. The second part propagates the key frames to other frames with temporal-aware patch matching and frame blending. Our framework achieves global style and local texture temporal consistency at a low cost (without re-training or optimization). The adaptation is compatible with existing image diffusion techniques, allowing our framework to take advantage of them, such as customizing a specific subject with LoRA, and introducing extra spatial guidance with ControlNet. Extensive experimental results demonstrate the effectiveness of our proposed framework over existing methods in rendering high-quality and temporally-coherent videos.

Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation paper page: Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring temporal consistency across video frames remains a formidable challenge. This paper proposes a novel zero-shot text-guided video-to-video translation framework to adapt image models to videos. The framework includes two parts: key frame translation and full video translation. The first part uses an adapted diffusion model to generate key frames, with hierarchical cross-frame constraints applied to enforce coherence in shapes, textures and colors. The second part propagates the key frames to other frames with temporal-aware patch matching and frame blending. Our framework achieves global style and local texture temporal consistency at a low cost (without re-training or optimization). The adaptation is compatible with existing image diffusion techniques, allowing our framework to take advantage of them, such as customizing a specific subject with LoRA, and introducing extra spatial guidance with ControlNet. Extensive experimental results demonstrate the effectiveness of our proposed framework over existing methods in rendering high-quality and temporally-coherent videos.

AK

375,313 views • 3 years ago

Alongside the release of Muse Image, we’re sharing an early preview of Muse Video. It offers competitive performance in prompt adherence, visual fidelity, and temporal consistency. We’re investing in areas with current performance gaps, such as audio-video synchronization and physically accurate fast motion.

Alongside the release of Muse Image, we’re sharing an early preview of Muse Video. It offers competitive performance in prompt adherence, visual fidelity, and temporal consistency. We’re investing in areas with current performance gaps, such as audio-video synchronization and physically accurate fast motion.

AI at Meta

265,152 views • 4 months ago