Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

🚀 Introducing #SparseVideoGen: 2x speedup in video generation with HunyuanVideo with high pixel-level fidelity (PSNR = 29)! No training is required, no perceptible difference to the human eye! Blog: Paper: Code: #ArtificialIntelligence #OpenSource [1/7]

HaochengXiUCB's profile picture

Haocheng Xi

1,514 subscribers

45,770 Aufrufe • vor 1 Jahr •via X (Twitter)

#SparseVideoGen
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

[1/N]🚀New decoding paradigm drop!🚀 Introducing Lookahead Reasoning(LR): step-level speculation that stacks with Speculative Decoding(SD). It has been accepted to #NeurIPS2025 🎉 📖 Blog: 💻 Code: 📄 Paper:
0:22

[1/N]🚀New decoding paradigm drop!🚀 Introducing Lookahead Reasoning(LR): step-level speculation that stacks with Speculative Decoding(SD). It has been accepted to #NeurIPS2025 🎉 📖 Blog: 💻 Code: 📄 Paper:

Hao AI Lab

43,199 Aufrufe • vor 11 Monaten

🎉🚀 Introducing Noya (YC W23) 🚀🎉 Noya is a wireframing tool that generates designs & code. Try it out: Noya lets you work in low-fidelity wireframes, while still producing high-fidelity designs and React prototypes to share with your team.
2:17

🎉🚀 Introducing Noya (YC W23) 🚀🎉 Noya is a wireframing tool that generates designs & code. Try it out: Noya lets you work in low-fidelity wireframes, while still producing high-fidelity designs and React prototypes to share with your team.

Devin Abbott

108,304 Aufrufe • vor 3 Jahren

🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project: 📜Paper: 🧑‍💻Code:
1:04

🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project: 📜Paper: 🧑‍💻Code:

Ziwei Liu

26,953 Aufrufe • vor 1 Jahr

Introducing The Matrix --- a foundation world model for generating infinite-length, hyper-realistic videos with real-time, frame-level control: - Infinite-length video generation - 720p high-quality rendering - Real-time, frame-level control at 16 FPS - Generalization to real-world video control 🔗Blog: 📄Paper: 💻Code & Playable Demo: Coming soon! Key Innovation: A brand new technique called the shift-window denoise process model, enabling auto-regressive generation for diffusion and consistency models in real-time. Special thanks to project leader Ruili Feng and the entire Matrix team for their dedication and hard work over the year-long project.
1:00

Introducing The Matrix --- a foundation world model for generating infinite-length, hyper-realistic videos with real-time, frame-level control: - Infinite-length video generation - 720p high-quality rendering - Real-time, frame-level control at 16 FPS - Generalization to real-world video control 🔗Blog: 📄Paper: 💻Code & Playable Demo: Coming soon! Key Innovation: A brand new technique called the shift-window denoise process model, enabling auto-regressive generation for diffusion and consistency models in real-time. Special thanks to project leader Ruili Feng and the entire Matrix team for their dedication and hard work over the year-long project.

Hongyang Zhang

178,382 Aufrufe • vor 1 Jahr

Make Pixels Dance: High-Dynamic Video Generation paper page: Creating high-dynamic videos such as motion-rich actions and sophisticated visual effects poses a significant challenge in the field of artificial intelligence. Unfortunately, current state-of-the-art video generation methods, primarily focusing on text-to-video generation, tend to produce video clips with minimal motions despite maintaining high fidelity. We argue that relying solely on text instructions is insufficient and suboptimal for video generation. In this paper, we introduce PixelDance, a novel approach based on diffusion models that incorporates image instructions for both the first and last frames in conjunction with text instructions for video generation. Comprehensive experimental results demonstrate that PixelDance trained with public data exhibits significantly better proficiency in synthesizing videos with complex scenes and intricate motions, setting a new standard for video generation.
3:09

Make Pixels Dance: High-Dynamic Video Generation paper page: Creating high-dynamic videos such as motion-rich actions and sophisticated visual effects poses a significant challenge in the field of artificial intelligence. Unfortunately, current state-of-the-art video generation methods, primarily focusing on text-to-video generation, tend to produce video clips with minimal motions despite maintaining high fidelity. We argue that relying solely on text instructions is insufficient and suboptimal for video generation. In this paper, we introduce PixelDance, a novel approach based on diffusion models that incorporates image instructions for both the first and last frames in conjunction with text instructions for video generation. Comprehensive experimental results demonstrate that PixelDance trained with public data exhibits significantly better proficiency in synthesizing videos with complex scenes and intricate motions, setting a new standard for video generation.

AK

102,706 Aufrufe • vor 2 Jahren

we built the world’s first self-installing API powered by claude code add memory to your AI agents in 5 mins with Hyperspell (YC F25) no human coding required
1:43

we built the world’s first self-installing API powered by claude code add memory to your AI agents in 5 mins with Hyperspell (YC F25) no human coding required

conor brennan-burke

29,355 Aufrufe • vor 10 Monaten

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

354,887 Aufrufe • vor 1 Jahr

Introducing the HeyGen Avatar Agent — built in partnership with #HeyGen, the leading AI video platform. Give it a blog URL, a topic, or a script you've already written, pick a presenter, and a finished avatar video lands in your inbox. No camera, no scriptwriting, no HeyGen subscription required. Try it for free: #AIagent #AgenticAI #AI #agentAI
0:29

Introducing the HeyGen Avatar Agent — built in partnership with #HeyGen, the leading AI video platform. Give it a blog URL, a topic, or a script you've already written, pick a presenter, and a finished avatar video lands in your inbox. No camera, no scriptwriting, no HeyGen subscription required. Try it for free: #AIagent #AgenticAI #AI #agentAI

Agent.ai

22,075 Aufrufe • vor 6 Monaten

Found out that tap🍎 already posted a video of the crazy threadling infinite stack, so I decided to knock it up a notch. Introducing Solo Argos in 1 phase with no mechanics required
1:07

Found out that tap🍎 already posted a video of the crazy threadling infinite stack, so I decided to knock it up a notch. Introducing Solo Argos in 1 phase with no mechanics required

NAPainter_ GCX 2026 ✈️

93,188 Aufrufe • vor 2 Monaten

🎉 InstantCharacter is NOW Open-Source! Personalize Any Character with High Consistency One image + text → custom poses, styles & scenes 1️⃣ First framework to balance character consistency, image quality, & open-domain flexibility/generalization 2️⃣ Compatible with Flux, delivering high-fidelity, text-controllable results 3️⃣ Comparable to industry leaders like GPT-4o in precision & adaptability Try it yourself on： 🔗Hugging Face Demo： Dive Deep into InstantCharacter: 🔗Project Page: 🔗Code: 🔗Paper： #TencentHunyuan #HY #InstantCharacter #OpenSource #AI #CharacterCustomization
0:29

🎉 InstantCharacter is NOW Open-Source! Personalize Any Character with High Consistency One image + text → custom poses, styles & scenes 1️⃣ First framework to balance character consistency, image quality, & open-domain flexibility/generalization 2️⃣ Compatible with Flux, delivering high-fidelity, text-controllable results 3️⃣ Comparable to industry leaders like GPT-4o in precision & adaptability Try it yourself on： 🔗Hugging Face Demo： Dive Deep into InstantCharacter: 🔗Project Page: 🔗Code: 🔗Paper： #TencentHunyuan #HY #InstantCharacter #OpenSource #AI #CharacterCustomization

Tencent Hy

78,039 Aufrufe • vor 1 Jahr

ByteDance just announced MagicVideo-V2 Multi-Stage High-Aesthetic Video Generation paper page: The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field. In this work, we introduce MagicVideo-V2 that integrates the text-to-image model, video motion generator, reference image embedding module and frame interpolation module into an end-to-end video generation pipeline. Benefiting from these architecture designs, MagicVideo-V2 can generate an aesthetically pleasing, high-resolution video with remarkable fidelity and smoothness. It demonstrates superior performance over leading Text-to-Video systems such as Runway, Pika 1.0, Morph, Moon Valley and Stable Video Diffusion model via user evaluation at large scale
2:07

ByteDance just announced MagicVideo-V2 Multi-Stage High-Aesthetic Video Generation paper page: The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field. In this work, we introduce MagicVideo-V2 that integrates the text-to-image model, video motion generator, reference image embedding module and frame interpolation module into an end-to-end video generation pipeline. Benefiting from these architecture designs, MagicVideo-V2 can generate an aesthetically pleasing, high-resolution video with remarkable fidelity and smoothness. It demonstrates superior performance over leading Text-to-Video systems such as Runway, Pika 1.0, Morph, Moon Valley and Stable Video Diffusion model via user evaluation at large scale

AK

181,036 Aufrufe • vor 2 Jahren

🚀Introducing Zero Alpha: our first autonomous DeFi AI Agents fueled by our data. they evolve on their own, going beyond simple trades to execute advanced strategies under any conditions. No human intervention is required. This changes everything. Watch the video now 👀 $PZERO
0:45

🚀Introducing Zero Alpha: our first autonomous DeFi AI Agents fueled by our data. they evolve on their own, going beyond simple trades to execute advanced strategies under any conditions. No human intervention is required. This changes everything. Watch the video now 👀 $PZERO

Project Zero

12,124 Aufrufe • vor 1 Jahr

16 teams have been invited. Only one will leave with the hardware 🏆 The National High School Invitational is ready to crown the best in high school baseball 👑 #NHSI23 is set for March 29 - April 1 National Training Complex:
2:19

16 teams have been invited. Only one will leave with the hardware 🏆 The National High School Invitational is ready to crown the best in high school baseball 👑 #NHSI23 is set for March 29 - April 1 National Training Complex:

USA Baseball Events

179,863 Aufrufe • vor 3 Jahren

1/5 🚀 Thrilled to open-source OSCAR 🤖 — an action-conditioned world model for robotics, led by the visiting student in my group Zhuoyuan Wu! It generalizes across different robot embodiments with precise action controllability. All trained on a single GH200 GPU, and outperforms existing open-sourced baselines, which have larger model capacity and need more compute. Everything is public, including training data. 📄 Paper: 🌐 Project: 💻 Code: 🤗 Robot data: 🤗 Human data: 🤗 Weights: #Robotics #WorldModels #AI #OpenSource
0:31

1/5 🚀 Thrilled to open-source OSCAR 🤖 — an action-conditioned world model for robotics, led by the visiting student in my group Zhuoyuan Wu! It generalizes across different robot embodiments with precise action controllability. All trained on a single GH200 GPU, and outperforms existing open-sourced baselines, which have larger model capacity and need more compute. Everything is public, including training data. 📄 Paper: 🌐 Project: 💻 Code: 🤗 Robot data: 🤗 Human data: 🤗 Weights: #Robotics #WorldModels #AI #OpenSource

Jun Gao

104,826 Aufrufe • vor 2 Monaten

🚀 Excited to release LongLive 2.0! 🎬 An end-to-end infrastructure for long video generation, with FP4 and parallelism at the core of both training and inference. ⚡45.7 FPS generation speed on 5B model⚡ ✨ LongLive 2.0 supports real-video training, few-step distillation, multi-shot training/inference, sequence-parallel acceleration, NVFP4 KV cache, and async VAE decoding deployment. 🧩 To our knowledge, this is the first open-source 4-bit long video generation infra that covers both training and inference. 🙌 Welcome to check it out, try it, and share feedback! 🔗 Code: 📰 Paper: 🎥 Demo: #LongVideoGeneration #VideoGeneration #Realtime #AIInfra #EfficientAI #FP4 #Parallel #NVIDIA
1:31

🚀 Excited to release LongLive 2.0! 🎬 An end-to-end infrastructure for long video generation, with FP4 and parallelism at the core of both training and inference. ⚡45.7 FPS generation speed on 5B model⚡ ✨ LongLive 2.0 supports real-video training, few-step distillation, multi-shot training/inference, sequence-parallel acceleration, NVFP4 KV cache, and async VAE decoding deployment. 🧩 To our knowledge, this is the first open-source 4-bit long video generation infra that covers both training and inference. 🙌 Welcome to check it out, try it, and share feedback! 🔗 Code: 📰 Paper: 🎥 Demo: #LongVideoGeneration #VideoGeneration #Realtime #AIInfra #EfficientAI #FP4 #Parallel #NVIDIA

Yukang Chen

59,546 Aufrufe • vor 3 Monaten

Flova now integrates Seedance 2.0 — unlocking next-level AI video creation. With Seedance 2.0, you get: • High-quality, long-form video generation • Strong motion consistency and cinematic output • Faster generation with significantly improved efficiency Flova also introduces a new Quick Access feature — instantly launch Seedance 2.0 or even NanoBanana with just one click. No complex setup, no prompt engineering required. And the best part? Lower cost, higher value — create more, spend less. #Flovaai #Seedance #aivideo
0:32

Flova now integrates Seedance 2.0 — unlocking next-level AI video creation. With Seedance 2.0, you get: • High-quality, long-form video generation • Strong motion consistency and cinematic output • Faster generation with significantly improved efficiency Flova also introduces a new Quick Access feature — instantly launch Seedance 2.0 or even NanoBanana with just one click. No complex setup, no prompt engineering required. And the best part? Lower cost, higher value — create more, spend less. #Flovaai #Seedance #aivideo

FlovaAI

475,640 Aufrufe • vor 4 Monaten

AI video is no longer a lottery machine. With Seedance Enterprise 2.5 on BytePlus, shot generation hit rates go from 15 randomized rerolls down to 1–2 usable takes, delivering a 70%+ drop in actual costs and a massive boost in production efficiency. What makes it truly production-ready is its unmistakable human realism. Skin texture, eye light, and natural micro-expressions stay physically grounded under motion. Powered by 30-second single-shot generation and up to 50 multimodal references, characters and camera sweeps hold absolute consistency without faces drifting or features melting. Combine that with targeted localized editing, and you’re no longer fighting AI artifacts, you’re dropping high-fidelity footage straight into the final render. Seedance 2.5 API is about to launch on BytePlus, and Lumina is rolling it out soon!
0:30

AI video is no longer a lottery machine. With Seedance Enterprise 2.5 on BytePlus, shot generation hit rates go from 15 randomized rerolls down to 1–2 usable takes, delivering a 70%+ drop in actual costs and a massive boost in production efficiency. What makes it truly production-ready is its unmistakable human realism. Skin texture, eye light, and natural micro-expressions stay physically grounded under motion. Powered by 30-second single-shot generation and up to 50 multimodal references, characters and camera sweeps hold absolute consistency without faces drifting or features melting. Combine that with targeted localized editing, and you’re no longer fighting AI artifacts, you’re dropping high-fidelity footage straight into the final render. Seedance 2.5 API is about to launch on BytePlus, and Lumina is rolling it out soon!

Sharon Riley

45,772 Aufrufe • vor 25 Tagen

China's No.1 #Matcha Exporter?🍵 It's Guizhou! With 1 in 7 global cups from Tongren, this is the true Matcha Heartland. Sip the difference. Plan your visit to the Matcha Capital now! #NO1 #tea #travel
0:25

China's No.1 #Matcha Exporter?🍵 It's Guizhou! With 1 in 7 global cups from Tongren, this is the true Matcha Heartland. Sip the difference. Plan your visit to the Matcha Capital now! #NO1 #tea #travel

UP Guizhou

11,354 Aufrufe • vor 7 Monaten