Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Playing with omnidreams ( inside flashdreams ( Fully interactive video generation at - 30FPS, - 720P resolution, - On a single RTX 6000 PRO GPU

ruilong_li's profile picture

Ruilong Li

5,312 subscribers

18,727 görüntüleme • 3 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

4 Yorum

Mark Kretschmann profil fotoğrafı
Mark Kretschmann3 ay önce

Super amazing!

Willem Helmet profil fotoğrafı
Willem Helmet3 ay önce

Wow!!! Flashdreams seems really cool

Cris Lenta profil fotoğrafı
Cris Lenta3 ay önce

love this! that gpu is only 15k though check your dms!

Yifan Jiang profil fotoğrafı
Yifan Jiang3 ay önce

really cool demo！

Benzer Videolar

Congrats to LemonSlice on their $10.5M seed! They built the world's first interactive talking AI video model—a face layer for voice agents. Trained on a custom, 20B-parameter video diffusion transformer, streaming at 20fps on a single GPU. Infinite-length video generation with no error accumulation.
2:25

Congrats to LemonSlice on their $10.5M seed! They built the world's first interactive talking AI video model—a face layer for voice agents. Trained on a custom, 20B-parameter video diffusion transformer, streaming at 20fps on a single GPU. Infinite-length video generation with no error accumulation.

Y Combinator

50,969 görüntüleme • 9 ay önce

StreamDiT Real-Time Streaming Text-to-Video Generation StreamDiT enables real-time text-to-video generation at 16 FPS on a single GPU (H100)
1:00

StreamDiT Real-Time Streaming Text-to-Video Generation StreamDiT enables real-time text-to-video generation at 16 FPS on a single GPU (H100)

AK

43,694 görüntüleme • 1 yıl önce

World models are moving beyond offline generation towards interactive, real-time experiences. Introducing ⚡FlashDreams⚡: an open-source high-performance inference and serving library built for autoregressive world models: 🔥 Up to 3.10× faster LingBot-World inference 🔥 Up to 2.12× faster Self-Forcing inference 🔥 Up to 1.40× faster Wan2.1 inference 🔥 8 integrated models 🔥 Multi-GPU, streaming, low-latency serving 🔥 Agentic skills that teach you how to use it FlashDreams is designed for a new generation of AI systems that continuously evolve over time while responding to user interactions. It powers applications across robotics, autonomous vehicle simulation, gaming, and virtual worlds. Github: Docs: Research page: Join the #flashdreams Discord channel at FlashDreams is also the runtime backbone behind NVIDIA OmniDreams ( 1/n #AI #WorldModels #FastInference #PhysicalAI #OpenSource #NVIDIA
0:46

World models are moving beyond offline generation towards interactive, real-time experiences. Introducing ⚡FlashDreams⚡: an open-source high-performance inference and serving library built for autoregressive world models: 🔥 Up to 3.10× faster LingBot-World inference 🔥 Up to 2.12× faster Self-Forcing inference 🔥 Up to 1.40× faster Wan2.1 inference 🔥 8 integrated models 🔥 Multi-GPU, streaming, low-latency serving 🔥 Agentic skills that teach you how to use it FlashDreams is designed for a new generation of AI systems that continuously evolve over time while responding to user interactions. It powers applications across robotics, autonomous vehicle simulation, gaming, and virtual worlds. Github: Docs: Research page: Join the #flashdreams Discord channel at FlashDreams is also the runtime backbone behind NVIDIA OmniDreams ( 1/n #AI #WorldModels #FastInference #PhysicalAI #OpenSource #NVIDIA

Ruilong Li

99,778 görüntüleme • 4 ay önce

#Battlefield6 NVIDIA DLSS 4 Reveal Trailer 📽️ The game includes support for DLSS 4 with Multi Frame Generation, DLSS Frame Generation, DLSS Super Resolution, DLAA, and NVIDIA Reflex. Desktop GPUs Performance At 4K, Ultra settings, DLSS 4 with Multi Frame Generation and DLSS Super Resolution multiply Battlefield 6's GeForce RTX 50 Series frame rates by an average of 3.8X. ▪️ GeForce RTX 5090 performance rockets to over 470 FPS. ▪️ GeForce RTX 5080 exceeds 330 FPS. ▪️ GeForce RTX 5070 Ti is in touching distance of 300 FPS. ▪️ GeForce RTX 5070 surpasses 230 FPS. At 2560x1440, Ultra settings, DLSS 4 with Multi Frame Generation and DLSS Super Resolution increase Battlefield 6 frame rates by an average of 3X. ▪️ GeForce RTX 5090 runs at almost 600 FPS. ▪️ GeForce RTX 5060 Ti over 240 FPS. At 1920x1080, Ultra settings, the combination of DLSS 4 with Multi Frame Generation and DLSS Super Resolution boost Battlefield 6’s GeForce RTX 50 Series frame rates by an average of 2.9X. ▪️ Allowing every GPU in NVIDIA's line-up to play at over 230 FPS, maxing out at over 740 FPS on the GeForce RTX 5090. Laptop GPUs Performance GeForce RTX 50 Series Laptop GPUs benefit similarly from DLSS 4 with Multi Frame Generation and DLSS Super Resolution, with Battlefield 6 frame rates multiplied by 3X on average at 2560x1600, with Ultra settings, enabling performance of up to 360 FPS. At 1920x1080, Ultra settings, GeForce RTX 50 Series Laptop GPU performance increases by 2.8X on average, enabling Battlefield 6 frame rates to surpass 480 FPS, and the range to run at over 200 frames per second.
0:41

#Battlefield6 NVIDIA DLSS 4 Reveal Trailer 📽️ The game includes support for DLSS 4 with Multi Frame Generation, DLSS Frame Generation, DLSS Super Resolution, DLAA, and NVIDIA Reflex. Desktop GPUs Performance At 4K, Ultra settings, DLSS 4 with Multi Frame Generation and DLSS Super Resolution multiply Battlefield 6's GeForce RTX 50 Series frame rates by an average of 3.8X. ▪️ GeForce RTX 5090 performance rockets to over 470 FPS. ▪️ GeForce RTX 5080 exceeds 330 FPS. ▪️ GeForce RTX 5070 Ti is in touching distance of 300 FPS. ▪️ GeForce RTX 5070 surpasses 230 FPS. At 2560x1440, Ultra settings, DLSS 4 with Multi Frame Generation and DLSS Super Resolution increase Battlefield 6 frame rates by an average of 3X. ▪️ GeForce RTX 5090 runs at almost 600 FPS. ▪️ GeForce RTX 5060 Ti over 240 FPS. At 1920x1080, Ultra settings, the combination of DLSS 4 with Multi Frame Generation and DLSS Super Resolution boost Battlefield 6’s GeForce RTX 50 Series frame rates by an average of 2.9X. ▪️ Allowing every GPU in NVIDIA's line-up to play at over 230 FPS, maxing out at over 740 FPS on the GeForce RTX 5090. Laptop GPUs Performance GeForce RTX 50 Series Laptop GPUs benefit similarly from DLSS 4 with Multi Frame Generation and DLSS Super Resolution, with Battlefield 6 frame rates multiplied by 3X on average at 2560x1600, with Ultra settings, enabling performance of up to 360 FPS. At 1920x1080, Ultra settings, GeForce RTX 50 Series Laptop GPU performance increases by 2.8X on average, enabling Battlefield 6 frame rates to surpass 480 FPS, and the range to run at over 200 frames per second.

Battlefield Bulletin

30,559 görüntüleme • 1 yıl önce

🤩Excited to share SANA-WM: a 2.6B open-source world model for minute-scale 720p video generation. Given one image + text + a 6-DoF camera trajectory, it synthesizes action-controllable 60s worlds on a single GPU. Project: Paper:
1:14

🤩Excited to share SANA-WM: a 2.6B open-source world model for minute-scale 720p video generation. Given one image + text + a 6-DoF camera trajectory, it synthesizes action-controllable 60s worlds on a single GPU. Project: Paper:

Haoyi Zhu

124,596 görüntüleme • 4 ay önce

Your gaming PC can now serve frontier models at interactive speed using official checkpoints without extreme quantization! Qwen3.6 35B → 8GB RTX 4060 laptop @ 39 tok/s DeepSeek-V4-Flash 284B → RTX 5090 desktop @ 22-25 tok/s GLM-5.2 753B → RTX PRO 6000 workstation @ 15 tok/s Run your claude code or codex now with frontier model for $0 Meet FreeToken 🧵
0:50

Your gaming PC can now serve frontier models at interactive speed using official checkpoints without extreme quantization! Qwen3.6 35B → 8GB RTX 4060 laptop @ 39 tok/s DeepSeek-V4-Flash 284B → RTX 5090 desktop @ 22-25 tok/s GLM-5.2 753B → RTX PRO 6000 workstation @ 15 tok/s Run your claude code or codex now with frontier model for $0 Meet FreeToken 🧵

Shuo Yang

1,099,414 görüntüleme • 1 ay önce

Finally!! Achieved 385 tok/s with GLM 5.2 NVFP4 on 8x RTX PRO 6000. It was buggy and incredibly slow at first. It took me over a week using agents to get this far.
0:22

Finally!! Achieved 385 tok/s with GLM 5.2 NVFP4 on 8x RTX PRO 6000. It was buggy and incredibly slow at first. It took me over a week using agents to get this far.

Hikari∣LocalLLM⚡

103,398 görüntüleme • 1 ay önce

🚀Generate a 30-second 1080p video in just 7 seconds! We’re open-sourcing FastVideo Dreamverse: real-time vibe directing for video generation on a single NVIDIA B200 GPU with LTX-2 model LTX Repo: Blog:
0:38

🚀Generate a 30-second 1080p video in just 7 seconds! We’re open-sourcing FastVideo Dreamverse: real-time vibe directing for video generation on a single NVIDIA B200 GPU with LTX-2 model LTX Repo: Blog:

Hao AI Lab

227,239 görüntüleme • 4 ay önce

Finally got my hands on the big one. Qwen3.5-122B-A10B — 122 billion parameters. Too big for any single consumer GPU. So I rented 4 of each... and then one professional card to see if brute force even matters. - 1x RTX PRO 6000 (96GB): 101.4 tok/s - 4x 5090 (128GB): 87.0 tok/s - 4x 4090 (96GB): 25.1 tok/s - 4x 3090 (96GB): 20.8 tok/s One single $8,500 card beat four RTX 5090s
0:59

Finally got my hands on the big one. Qwen3.5-122B-A10B — 122 billion parameters. Too big for any single consumer GPU. So I rented 4 of each... and then one professional card to see if brute force even matters. - 1x RTX PRO 6000 (96GB): 101.4 tok/s - 4x 5090 (128GB): 87.0 tok/s - 4x 4090 (96GB): 25.1 tok/s - 4x 3090 (96GB): 20.8 tok/s One single $8,500 card beat four RTX 5090s

stevibe

197,300 görüntüleme • 6 ay önce

(1/5) 5 seconds of video. 1.8s seconds of generation. One NVIDIA GeForce RTX 5090 on FastVideo. 🤯🚀 - FastWan-QAD, a new family of video generation models - Trained with FastVideo's Quantization-Aware Distillation (QAD) recipe. - Powered by FastVideo, we push a single NVIDIA GeForce RTX 5090 to its absolute limit: generating a 5-second 480P video in 1.8s end-to-end! 📜 Blog: 💻 Code: 💽 Model:
0:20

(1/5) 5 seconds of video. 1.8s seconds of generation. One NVIDIA GeForce RTX 5090 on FastVideo. 🤯🚀 - FastWan-QAD, a new family of video generation models - Trained with FastVideo's Quantization-Aware Distillation (QAD) recipe. - Powered by FastVideo, we push a single NVIDIA GeForce RTX 5090 to its absolute limit: generating a 5-second 480P video in 1.8s end-to-end! 📜 Blog: 💻 Code: 💽 Model:

Hao AI Lab

13,411 görüntüleme • 3 ay önce

One image + text + camera trajectory = controllable worlds. All on a single GPU. Our research team just released SANA-WM, a 2.6B open source world model natively trained for 60-second video generation with precise camera control.
0:20

One image + text + camera trajectory = controllable worlds. All on a single GPU. Our research team just released SANA-WM, a 2.6B open source world model natively trained for 60-second video generation with precise camera control.

NVIDIA AI

93,282 görüntüleme • 4 ay önce

MiniMax M2.7 is 230B params. Can you actually run it at home? I tested Unsloth's UD-IQ3_XXS (80GB) on 4 different rigs: 🟠 4x RTX 4090 (96GB): 71.52 tok/s, TTFT 1045ms 🟢 4x RTX 5090 (128GB): 120.54 tok/s, TTFT 725ms 🟡 1x RTX PRO 6000 (96GB): 118.74 tok/s, TTFT 765ms 🟣 DGX Spark (128GB) — 24.41 tok/s, TTFT 741ms Backend: llama.cpp. Context: 32k. Max tokens: 4096. I went with IQ3_XXS because it's the biggest quant that fits in 96GB VRAM while still leaving safe headroom for 32k context. Same quant across all four rigs, fairest comparison I could run. Now look at rough peak GPU power draw: 🟠 4x4090 → 1,800W peak (450W × 4) 🟢 4x5090 → 2,300W peak (575W × 4) 🟡 RTX PRO 6000 → 600W peak 🟣 DGX Spark → 240W peak (whole system) The RTX PRO 6000 is the quiet winner. One card, 96GB, matching a 4x5090 rig at roughly a quarter of the power and zero multi-GPU headaches. Best tokens-per-watt by a wide margin. DGX Spark is slow on generation but pulls the least power of any rig here, around 240W for the whole system. Prefill-friendly, memory-rich, wall-socket-friendly. And yes, plenty of people cap their cards. Even then, 4x 4090 or 4x 5090 still pulls well over 1,200W from the GPUs alone.
1:21

MiniMax M2.7 is 230B params. Can you actually run it at home? I tested Unsloth's UD-IQ3_XXS (80GB) on 4 different rigs: 🟠 4x RTX 4090 (96GB): 71.52 tok/s, TTFT 1045ms 🟢 4x RTX 5090 (128GB): 120.54 tok/s, TTFT 725ms 🟡 1x RTX PRO 6000 (96GB): 118.74 tok/s, TTFT 765ms 🟣 DGX Spark (128GB) — 24.41 tok/s, TTFT 741ms Backend: llama.cpp. Context: 32k. Max tokens: 4096. I went with IQ3_XXS because it's the biggest quant that fits in 96GB VRAM while still leaving safe headroom for 32k context. Same quant across all four rigs, fairest comparison I could run. Now look at rough peak GPU power draw: 🟠 4x4090 → 1,800W peak (450W × 4) 🟢 4x5090 → 2,300W peak (575W × 4) 🟡 RTX PRO 6000 → 600W peak 🟣 DGX Spark → 240W peak (whole system) The RTX PRO 6000 is the quiet winner. One card, 96GB, matching a 4x5090 rig at roughly a quarter of the power and zero multi-GPU headaches. Best tokens-per-watt by a wide margin. DGX Spark is slow on generation but pulls the least power of any rig here, around 240W for the whole system. Prefill-friendly, memory-rich, wall-socket-friendly. And yes, plenty of people cap their cards. Even then, 4x 4090 or 4x 5090 still pulls well over 1,200W from the GPUs alone.

stevibe

193,239 görüntüleme • 5 ay önce

it's open source time, with a real leap for world models 🎉 NVIDIA's SANA-WM: a camera-conditioned world model that fits on one GPU. 60s of 720p in 34s on a single 5090 - 2.6B params and Apache 2.0!
0:20

it's open source time, with a real leap for world models 🎉 NVIDIA's SANA-WM: a camera-conditioned world model that fits on one GPU. 60s of 720p in 34s on a single 5090 - 2.6B params and Apache 2.0!

Victor M

34,386 görüntüleme • 4 ay önce

AI at Meta's Muse Glimmer (30B dense, open-weights) launches with SGLang day-0 support. We got ~230 tok/s on a single RTX 5090, with NVFP4 + DFlash on. It also works out of the box on NVIDIA AI Developer RTX Pro 6000, DGX Spark, and MLX for Mac. Speed and reliability have always been the blockers for a local agent. SGLang and Muse Glimmer make a local agent that's blazing fast, always on, and gets things done. Go build and run a local agent on your own machine!🚀
0:32

AI at Meta's Muse Glimmer (30B dense, open-weights) launches with SGLang day-0 support. We got ~230 tok/s on a single RTX 5090, with NVFP4 + DFlash on. It also works out of the box on NVIDIA AI Developer RTX Pro 6000, DGX Spark, and MLX for Mac. Speed and reliability have always been the blockers for a local agent. SGLang and Muse Glimmer make a local agent that's blazing fast, always on, and gets things done. Go build and run a local agent on your own machine!🚀

LMSYS Org

43,846 görüntüleme • 1 ay önce

I asked Diaz Biffle what happened with his graphics card situation at World Series of Warzone. For those unaware, Biffle played 4 of the first 6 games on day 1 with a 7600XT GPU while everyone else was on a 7900, meaning he was at a MAJOR disadvantage. He still had a 9.5 KD after day one despite his GPU averaging over 100 FPS less in benchmark tests on modern titles at 1440p, the resolution they were playing on.
1:35

I asked Diaz Biffle what happened with his graphics card situation at World Series of Warzone. For those unaware, Biffle played 4 of the first 6 games on day 1 with a 7600XT GPU while everyone else was on a 7900, meaning he was at a MAJOR disadvantage. He still had a 9.5 KD after day one despite his GPU averaging over 100 FPS less in benchmark tests on modern titles at 1440p, the resolution they were playing on.

ModernWarzone

275,175 görüntüleme • 2 yıl önce

LingBot-World 2.0 (Infinity) is out on Hugging Face interactive world model with: Hour-long generation with zero quality drift Rich actions & events: attack, cast spells, shoot, summon storms Agentic world: a Director Agent drives real-time world evolution 720p/60fps. Playable like a game
1:00

LingBot-World 2.0 (Infinity) is out on Hugging Face interactive world model with: Hour-long generation with zero quality drift Rich actions & events: attack, cast spells, shoot, summon storms Agentic world: a Director Agent drives real-time world evolution 720p/60fps. Playable like a game

AK

29,480 görüntüleme • 2 ay önce

Wan 3.0 is live on OpenArt 🔊 • Native 30-second generation in a single pass — no stitching • Consistent motion, lighting & subjects throughout • 480p, 720p & 1080p outputs • Upgrade to Pro or Wonder for unlimited generations this week (Aug 24–31). Available now on OpenArt:
0:25

Wan 3.0 is live on OpenArt 🔊 • Native 30-second generation in a single pass — no stitching • Consistent motion, lighting & subjects throughout • 480p, 720p & 1080p outputs • Upgrade to Pro or Wonder for unlimited generations this week (Aug 24–31). Available now on OpenArt:

OpenArt

21,242 görüntüleme • 1 ay önce