Loading video...

Video Failed to Load

Go Home

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.

NVIDIAAI's profile picture

NVIDIA AI

308,776 subscribers

90,483 views • 21 days ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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

34,315 views • 20 days ago

Woow Nvidia has just released a 2.6B open-source world model 🔥 You can turn a single image, text prompt and trajectory into controllable worlds... And on a single GPU! - Code available on GitHub - Paper as well on arxiv You can use it for many things like embodied AI and robotics research, simulations, etc. Because it can run on a single GPU (like an RTX 5090 or H100) it makes world models accessible to basically everyone!
1:14

Woow Nvidia has just released a 2.6B open-source world model 🔥 You can turn a single image, text prompt and trajectory into controllable worlds... And on a single GPU! - Code available on GitHub - Paper as well on arxiv You can use it for many things like embodied AI and robotics research, simulations, etc. Because it can run on a single GPU (like an RTX 5090 or H100) it makes world models accessible to basically everyone!

Paul Couvert

172,574 views • 25 days ago

NVIDIA just unleashed SANA-WM and it’s an absolute MONSTER for the future of open source AI! A blazing-fast 2.6B-parameter open-source world model that doesn’t just generate video… it creates controllable, physics-rich, high-fidelity worlds on demand. Why this is insanely powerful: • One image + text prompt + 6-DoF camera trajectory → generates 720p videos up to 60 seconds long with buttery-smooth, precisely controlled camera movement. You’re not just watching, you’re piloting the simulation. • Runs locally on a single consumer GPU (RTX 5090 level) thanks to heavy distillation + NVFP4 quantization. Full 60-second clip denoised in ~34 seconds. No massive clusters required. • 36× higher throughput than previous open models while rivaling (or beating) closed industrial giants in visual quality and consistency. • Trained lightning-fast: ~213K public videos in just 15 days on 64 H100s. • Built with next-level tech: Hybrid Linear Attention, dual-branch camera control, two-stage pipeline, and rock-solid metric-scale pose understanding. This is a true open world model, the foundation for embodied AI, robotics, autonomous systems, and hyper-realistic simulations that can run anywhere. Project: At our Zero-Human Company, we’re already running SANA-WM live in our core pipelines. It’s supercharging autonomous agent training, generating unlimited synthetic training data, and powering full end-to-end simulation loops, zero humans in the loop. The speed and control let us test thousands of edge-case scenarios overnight, iterate at lightspeed, and push our fully autonomous operations further than ever before. This is the kind of breakthrough that turns science fiction into daily reality. World models just leveled up — hard. The age of personal, local, controllable universes is here.
1:13

NVIDIA just unleashed SANA-WM and it’s an absolute MONSTER for the future of open source AI! A blazing-fast 2.6B-parameter open-source world model that doesn’t just generate video… it creates controllable, physics-rich, high-fidelity worlds on demand. Why this is insanely powerful: • One image + text prompt + 6-DoF camera trajectory → generates 720p videos up to 60 seconds long with buttery-smooth, precisely controlled camera movement. You’re not just watching, you’re piloting the simulation. • Runs locally on a single consumer GPU (RTX 5090 level) thanks to heavy distillation + NVFP4 quantization. Full 60-second clip denoised in ~34 seconds. No massive clusters required. • 36× higher throughput than previous open models while rivaling (or beating) closed industrial giants in visual quality and consistency. • Trained lightning-fast: ~213K public videos in just 15 days on 64 H100s. • Built with next-level tech: Hybrid Linear Attention, dual-branch camera control, two-stage pipeline, and rock-solid metric-scale pose understanding. This is a true open world model, the foundation for embodied AI, robotics, autonomous systems, and hyper-realistic simulations that can run anywhere. Project: At our Zero-Human Company, we’re already running SANA-WM live in our core pipelines. It’s supercharging autonomous agent training, generating unlimited synthetic training data, and powering full end-to-end simulation loops, zero humans in the loop. The speed and control let us test thousands of edge-case scenarios overnight, iterate at lightspeed, and push our fully autonomous operations further than ever before. This is the kind of breakthrough that turns science fiction into daily reality. World models just leveled up — hard. The age of personal, local, controllable universes is here.

Brian Roemmele

616,410 views • 24 days ago

Nvidia just dropped GEN3C 3D-Informed World-Consistent Video Generation with Precise Camera Control
1:18

Nvidia just dropped GEN3C 3D-Informed World-Consistent Video Generation with Precise Camera Control

AK

58,146 views • 1 year ago

The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.
0:25

The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.

Akshay 🚀

65,784 views • 5 months ago

Wan2.6 Image Generation is ready for Commercial Use! - Interleaved Text-and-Image Output - Multi-Image Conditioned Generation - Commercial-Grade ID Preservation - Extract Creative Elements - Precise Control of Camera Angles and Lighting Try Wan2.6 today!
1:01

Wan2.6 Image Generation is ready for Commercial Use! - Interleaved Text-and-Image Output - Multi-Image Conditioned Generation - Commercial-Grade ID Preservation - Extract Creative Elements - Precise Control of Camera Angles and Lighting Try Wan2.6 today!

Alibaba Cloud

145,741 views • 4 months ago

🚀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

222,014 views • 13 days ago

📹The Hailuo I2V-01-Director Model is now available to everyone! Experience cinematic storytelling with precise camera control—powered by both our text and image models. Try it here:
0:43

📹The Hailuo I2V-01-Director Model is now available to everyone! Experience cinematic storytelling with precise camera control—powered by both our text and image models. Try it here:

Hailuo AI (MiniMax)

319,991 views • 1 year ago

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇
0:43

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

Agrim Gupta

431,092 views • 2 years ago

This character didn't break once across 5 shots, 3 camera angles, and a voice swap. Wan 2.7 is live on OpenArt. Here's what changed: Multimodal control. Text, image, audio, video, all in one generation call. Up to 5 reference inputs plus voice profiles for character locking. Edit existing videos with a sentence. Full creative stack: generate, edit, clone, restyle, extend. The open-source video model that actually acts like a production toolkit.
1:30

This character didn't break once across 5 shots, 3 camera angles, and a voice swap. Wan 2.7 is live on OpenArt. Here's what changed: Multimodal control. Text, image, audio, video, all in one generation call. Up to 5 reference inputs plus voice profiles for character locking. Edit existing videos with a sentence. Full creative stack: generate, edit, clone, restyle, extend. The open-source video model that actually acts like a production toolkit.

OpenArt

2,071,522 views • 2 months ago

Collaborative Video Diffusion Consistent Multi-video Generation with Camera Control Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation
2:16

Collaborative Video Diffusion Consistent Multi-video Generation with Camera Control Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation

AK

29,262 views • 2 years ago

LTX-2 is natively supported in ComfyUI on Day 0 🎬🔊 The next chapter in controllability for open-source video generation. - Open-source audio-video foundation model - Generates motion, dialogue, SFX, and music together - Canny, Depth & Pose video-to-video control - Keyframe-driven generation - Native upscaling and prompt enhancement Everything in a single pass.
0:36

LTX-2 is natively supported in ComfyUI on Day 0 🎬🔊 The next chapter in controllability for open-source video generation. - Open-source audio-video foundation model - Generates motion, dialogue, SFX, and music together - Canny, Depth & Pose video-to-video control - Keyframe-driven generation - Native upscaling and prompt enhancement Everything in a single pass.

ComfyUI

108,086 views • 5 months ago

Apple just released and open-sourced FastVLM! FastVLM is a lightning-fast vision-language model that combines rapid image and text understanding with efficient on-device performance. 100% Open Source
0:21

Apple just released and open-sourced FastVLM! FastVLM is a lightning-fast vision-language model that combines rapid image and text understanding with efficient on-device performance. 100% Open Source

Sumanth

43,685 views • 9 months ago

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:
0:23

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Stability AI

976,258 views • 2 years ago

Introducing Image to Video for Gen-4.5, the world's best video model. Built for longer stories. Precise camera control. Coherent narratives. And characters that stay consistent. Gen-4.5 Image to Video is available now for all paid plans.
1:08

Introducing Image to Video for Gen-4.5, the world's best video model. Built for longer stories. Precise camera control. Coherent narratives. And characters that stay consistent. Gen-4.5 Image to Video is available now for all paid plans.

Runway

762,683 views • 4 months ago

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:
1:20

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:

Tencent Hy

168,304 views • 7 months ago

🚀 We just released LTX-Video 13B – our most powerful open-source video generation model yet. – 13B parameters – Multiscale rendering for better fine details – Better motion and scene understanding – Still fast - runs on local GPUs – Supports keyframes, camera/character motion & multi-shot sequences
2:20

🚀 We just released LTX-Video 13B – our most powerful open-source video generation model yet. – 13B parameters – Multiscale rendering for better fine details – Better motion and scene understanding – Still fast - runs on local GPUs – Supports keyframes, camera/character motion & multi-shot sequences

Yoav HaCohen

182,678 views • 1 year ago

and Wan2.2 again. MoCam - novel view synthesis. Lets you change the camera trajectory of a photo/video. - Video Re-camera - 3D Photo Conversion - Cinematic Control - Precise orbital/pan/zoom control - Corrects geometric artifacts
0:37

and Wan2.2 again. MoCam - novel view synthesis. Lets you change the camera trajectory of a photo/video. - Video Re-camera - 3D Photo Conversion - Cinematic Control - Precise orbital/pan/zoom control - Corrects geometric artifacts

Wildminder

13,720 views • 27 days ago

Generative 3D worlds are amazing! Here is a generative AI video showing fine grained camera control. Camera movements are all hand places within a generated 3D world.
0:52

Generative 3D worlds are amazing! Here is a generative AI video showing fine grained camera control. Camera movements are all hand places within a generated 3D world.

Brittani Natali

21,043 views • 1 year ago

Thinking with Camera A Unified Multimodal Model for Camera-Centric Understanding and Generation
3:08

Thinking with Camera A Unified Multimodal Model for Camera-Centric Understanding and Generation

AK

39,318 views • 7 months ago