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.

With Atlas, you can literally make films. And it also basically solves first-frame-last-frame transitions. Reconstruct a 3D scene from images, then position the camera exactly where you want it, and let Atlas fill in what the camera would see along that path. You’re in the director's chair, staging the... show more

David Pantera

6,156 subscribers

27,621 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

31 Comments

David Pantera1 month ago

Request access to Atlas here:

Ekim Kaya1 month ago

when do we get our hands on it? :)

David Pantera1 month ago

We're opening early access to Atlas to a select group of partners over the next few weeks. Please sign up for the waitlist and someone from our team will get in touch -

Ekim Kaya1 month ago

I did. I already have a user base to which I can start selling pretty quickly :) No public info about pricing yet?

ClipStudio1 month ago

the top down drop straight into the stone well in the cobblestone village is the bit i keep rewinding, and then it just keeps going into the ship bridge with the blue holo globe. no cut anywhere

Ai(n) Malcolm1 month ago

Bad time for drone pilots

Bobcat1 month ago

Would love to try it whenever you guys will have me. I'm currently making a historical film that spans the 20th century. (With Marble the problem was that I was so broke earlier this year, I couldn't afford any plugins to transfer splats to Unreal!)

David Pantera1 month ago

make sure to request access!

Matthew Johnson1 month ago

Ooh! This is definitely one of the tools that I've been waiting for. Looking forward to seeing where it goes.

justin1 month ago

this is super cool!

Peachy J1 month ago

That first to last frame transition fix is a big unlock.

Purvh1 month ago

How well does Atlas preserve characters and scene details across longer camera paths?

Ian Danforth1 month ago

Is it reproducible? If I change the path slightly does it change a ton of the content it generates?

Steve d’Atelier | MrCakeFlex1 month ago

Didn’t Franco Vazza publish a paper arguing we can’t live in a simulation because the compute required would exceed the energy available in the universe? I guess he never heard of computer graphics.

blackbox1 month ago

staging a camera path through a reconstructed scene is a very different job than prompting a shot. one is direction, the other is gambling. the interesting question is how far the camera can drift before the geometry starts inventing things.

niebin1 month ago

你好左边这个是什么工具

Wagaba Allan1 month ago

I was disappointed with Mabel I hope this is completely different

Jeff Young1 month ago

The idea of reconstructing a 3D scene and then placing camera keyframes is proper director territory. I’d try staging a short multi-scene shot in Krea with similar camera paths to see how the transitions read.

TAL77SVAD1 month ago

#MadeForLoosers

Jacob Brown1 month ago

have anyone attempted motion tracking with real green screen of a subject on this yet? Really interested in seeing how a consistent 1 minute take would look in here.

Konpaku1 month ago

How well does it handle complex camera moves like dolly zooms?

Cobra 𐤊1 month ago

Maybe I am more prone to motion sickness but I wouldn't last in the theatre with these shots. @grok is this a closed source model? Can the frame (camera) stay fixed in one position?

armandoki1 month ago

Very cool, but you can’t make 99.9% of films without cutting so continuous takes like this aren’t particularly useful, although they’re visually impressive. I spent quite a bit of time making a filmmaking agent that used Marble, but got distracted with other work. Excited to see further development from your team!

AI Mastery Guide1 month ago

This is basically a camera in a scene

Si(super intelligence)1 month ago

👍

✋🏼 Sami Belhadj 📍1 month ago

We need a new awards category I think

Alexandra Dekimpe / AI Filmmaker1 month ago

Amazing !

Rish Agarwal1 month ago

Games, yes Films, probably not

FEEL-OS1 month ago

Sound would make it even more impressive.

Romain Simon1 month ago

Would love to integrate this in it looks incredible ❤️

Romagn1 month ago

Can you potentially generate an entire film starting from one frame?

Related Videos

a few space scenes made with atlas. each one started from a single image. atlas generates the video as the camera moves, including the parts of the scene that weren’t in the original image. orange = input image in 3D space blue = camera moving through the scene

a few space scenes made with atlas. each one started from a single image. atlas generates the video as the camera moves, including the parts of the scene that weren’t in the original image. orange = input image in 3D space blue = camera moving through the scene

Ian Curtis

10,414 views • 11 days ago

Bring your stories to life with a 3D camera. Start with a single frame and turn it into a 3D scene you can move through, shot by shot. Control the camera. Set the pace. Shape the story.

Bring your stories to life with a 3D camera. Start with a single frame and turn it into a 3D scene you can move through, shot by shot. Control the camera. Set the pace. Shape the story.

Moonvalley

18,809 views • 1 year ago

Camera control is no longer in the prompt Meet 3D Motion Control → Set the camera path in 3D → Your scene becomes the video reference the model follows → Same move, every take, exactly where you set it Available now in Magnific

Camera control is no longer in the prompt Meet 3D Motion Control → Set the camera path in 3D → Your scene becomes the video reference the model follows → Same move, every take, exactly where you set it Available now in Magnific

Magnific

611,138 views • 2 months ago

Get any camera move you want, using just your phone. Frame the shot, hit record, and move your camera exactly how you want it - a simple pan, a push-in and swirl, whatever. Load that clip into Agent One and tell it what you want in the shot. Your recorded video drives the camera move, Agent One runs it through Seedance, and you sit back and watch. Pro tip - match your phone frame to your first generated frame. The closer it lines up, the better it lands. Watch the video to see exactly how we did it.

Get any camera move you want, using just your phone. Frame the shot, hit record, and move your camera exactly how you want it - a simple pan, a push-in and swirl, whatever. Load that clip into Agent One and tell it what you want in the shot. Your recorded video drives the camera move, Agent One runs it through Seedance, and you sit back and watch. Pro tip - match your phone frame to your first generated frame. The closer it lines up, the better it lands. Watch the video to see exactly how we did it.

Invideo

30,905 views • 3 months ago

Jon Bernthal says his sex scene with Laurie Holden in The Walking Dead was so graphic that most of it was cut “We filmed a sex scene in a green Hyundai with Laurie Holden.” “What we did in that scene was so graphic.” “They ended up using only a wide shot of the car.” “I worked with the camera operator to make the scene feel as real and gritty as possible.” “You couldn’t actually see anything in the final scene, but I wanted it to feel authentic.”

Sensitive content

Jon Bernthal says his sex scene with Laurie Holden in The Walking Dead was so graphic that most of it was cut “We filmed a sex scene in a green Hyundai with Laurie Holden.” “What we did in that scene was so graphic.” “They ended up using only a wide shot of the car.” “I worked with the camera operator to make the scene feel as real and gritty as possible.” “You couldn’t actually see anything in the final scene, but I wanted it to feel authentic.”

Lin

722,613 views • 2 months ago

Looking right in 2D doesn’t really mean the scene holds together in 3D. That's why we open-sourced BlenderWorld last week and wanted to give it a closer look here. It’s a benchmark with 223 tasks where agents use Blender to build editable 3D scenes from text, images or video references. We evaluate the actual projects through scene inspection and renders from multiple viewpoints. Can a visual agent turn a real-world brief into a complete, editable 3D scene? BlenderWorld is here to evaluate that You can grab the benchmark below (Links in the comment) and plug in your own 3D agent to see how it does

Looking right in 2D doesn’t really mean the scene holds together in 3D. That's why we open-sourced BlenderWorld last week and wanted to give it a closer look here. It’s a benchmark with 223 tasks where agents use Blender to build editable 3D scenes from text, images or video references. We evaluate the actual projects through scene inspection and renders from multiple viewpoints. Can a visual agent turn a real-world brief into a complete, editable 3D scene? BlenderWorld is here to evaluate that You can grab the benchmark below (Links in the comment) and plug in your own 3D agent to see how it does

Qwen Developers

58,218 views • 4 days ago

Built a prototype with Atlas API + 8th Wall. I started with a single image, walked around the point cloud in augmented reality, and used my phone to frame the shot. Atlas generates the video along my camera path, filling in what the initial image never showed. Result at 0:15

Built a prototype with Atlas API + 8th Wall. I started with a single image, walked around the point cloud in augmented reality, and used my phone to frame the shot. Atlas generates the video along my camera path, filling in what the initial image never showed. Result at 0:15

Ian Curtis

12,230 views • 10 days ago

whats interesting is you can "trick" Atlas into becoming a 3D modeling tool by placing input images in 3D space the model then creates a coherent world this is how this scene was made – all the model sees is camera pose + RGB

whats interesting is you can "trick" Atlas into becoming a 3D modeling tool by placing input images in 3D space the model then creates a coherent world this is how this scene was made – all the model sees is camera pose + RGB

neilson

58,017 views • 1 month ago

Use the prompt below to take more control of your video generation and create smoother, more natural scene transitions. "Multi-shot: Every scene must begin with a medium close-up shot of the podcast setup and speaker in frame. End each scene with extreme close-up shot (tight face, eyes-centered). Maintain continuity in lighting, audio, and props."

Use the prompt below to take more control of your video generation and create smoother, more natural scene transitions. "Multi-shot: Every scene must begin with a medium close-up shot of the podcast setup and speaker in frame. End each scene with extreme close-up shot (tight face, eyes-centered). Maintain continuity in lighting, audio, and props."

Olatunde AI

14,610 views • 1 month ago

Atlas is huge for real-to-sim. Scanning spaces like this usually requires tons of equipment, but Atlas can reconstruct the environment from just a couple pictures. We then simulate robots navigating through the generated world. Atlas generates what the robot would see from the perspective of its cameras. Even depth. It generates the environment AND the training data from it...

Atlas is huge for real-to-sim. Scanning spaces like this usually requires tons of equipment, but Atlas can reconstruct the environment from just a couple pictures. We then simulate robots navigating through the generated world. Atlas generates what the robot would see from the perspective of its cameras. Even depth. It generates the environment AND the training data from it...

David Pantera

13,704 views • 1 month ago

3 Steps to Being Able to Produce Hollywood Level AI Animations (and not slop): 1. The quality of your animation doesn't start with the images or the prompt It starts with the idea and camera angles, then the images and video. A boring idea can't be revived with interesting looking images or cool scenes and without knowing basic fundamentals of camera movement / shots, the flow of the film will feel stale and slow (or too fast) This will not only stop you from burning credits 2. Add lighting into your scenes Adding a light source in your location images and referring to it will give your film a much higher quality feel and prevent an empty feeling film where seedance has to guess where the lighting is coming from For example in a kitchen scene add a lamp in the image with a golden glow coming off it 3. Don't leave direction up to the Claude No matter how good of a skill you have or level of model, it is terrible at directing To properly direct Wispr flow your idea shot by shot into Claude then add in a base acting direction for each character that the prompts always need to follow Also along with the scene and the tone of how your characters speak and move. This will prevent you from having stale feeling or AI looking movement and dialogue in your film

3 Steps to Being Able to Produce Hollywood Level AI Animations (and not slop): 1. The quality of your animation doesn't start with the images or the prompt It starts with the idea and camera angles, then the images and video. A boring idea can't be revived with interesting looking images or cool scenes and without knowing basic fundamentals of camera movement / shots, the flow of the film will feel stale and slow (or too fast) This will not only stop you from burning credits 2. Add lighting into your scenes Adding a light source in your location images and referring to it will give your film a much higher quality feel and prevent an empty feeling film where seedance has to guess where the lighting is coming from For example in a kitchen scene add a lamp in the image with a golden glow coming off it 3. Don't leave direction up to the Claude No matter how good of a skill you have or level of model, it is terrible at directing To properly direct Wispr flow your idea shot by shot into Claude then add in a base acting direction for each character that the prompts always need to follow Also along with the scene and the tone of how your characters speak and move. This will prevent you from having stale feeling or AI looking movement and dialogue in your film

Pounds

50,935 views • 7 days ago

The AI video content being made with the Google Gemini is blowing our minds¹ 🤯 With our latest #PixelDrop, you can now upload images directly from your camera roll, enter a prompt to describe a scene, and let Gemini bring it all to life:²

The AI video content being made with the Google Gemini is blowing our minds¹ 🤯 With our latest #PixelDrop, you can now upload images directly from your camera roll, enter a prompt to describe a scene, and let Gemini bring it all to life:²

Made by Google

44,608 views • 1 year ago

Atlas beta access is rolling out to users, some ideas for API developers - give Astra "eyes" in Blender, let it place and render new camera views with Atlas - 3D reconstruction (this video uses 9 image inputs of my studio to make a scene, any Zillow apartment works) - graybox-to-world, use depth inputs and generate multi-view renders of a scene

Atlas beta access is rolling out to users, some ideas for API developers - give Astra "eyes" in Blender, let it place and render new camera views with Atlas - 3D reconstruction (this video uses 9 image inputs of my studio to make a scene, any Zillow apartment works) - graybox-to-world, use depth inputs and generate multi-view renders of a scene

neilson

47,151 views • 1 month ago

The bike, the ruins, the ramps, the Highlands sky. All of it started as one sentence typed into Atlas. Concept art, 3D assets, a staging pass in Blender, an Unreal scene you can ride through. One canvas, so the world keeps one look from first image to engine. Try Atlas today.

The bike, the ruins, the ramps, the Highlands sky. All of it started as one sentence typed into Atlas. Concept art, 3D assets, a staging pass in Blender, an Unreal scene you can ride through. One canvas, so the world keeps one look from first image to engine. Try Atlas today.

Atlas

8,790,944 views • 2 months ago

Two of us filmed this on a couple phones, and we used Atlas to turn it into a short film. This is just a clip from the World Labs tech blog Atlas is able to generate the parts of the scene that none of the cameras actually filmed. It can freeze time, allowing you to reframe shots to positions never filmed, then resume. View events from impossible angles because Atlas knows what was there.

Two of us filmed this on a couple phones, and we used Atlas to turn it into a short film. This is just a clip from the World Labs tech blog Atlas is able to generate the parts of the scene that none of the cameras actually filmed. It can freeze time, allowing you to reframe shots to positions never filmed, then resume. View events from impossible angles because Atlas knows what was there.

David Pantera

951,950 views • 1 month ago

Introducing H3 Max Camera Controls, the world's fastest 3D video model. Turn a single viewpoint into a navigable 3D scene in less than 3 seconds. Set the horizontal and vertical camera angle in degrees, and H3 Max Camera Controls moves through the scene while preserving geometry, position, and materials across perspectives. Fast enough to control the camera in real time.

Introducing H3 Max Camera Controls, the world's fastest 3D video model. Turn a single viewpoint into a navigable 3D scene in less than 3 seconds. Set the horizontal and vertical camera angle in degrees, and H3 Max Camera Controls moves through the scene while preserving geometry, position, and materials across perspectives. Fast enough to control the camera in real time.

fal

239,950 views • 1 month ago

CRAZY... you can now draw a camera move with your mouse and watch the scene actually run it. Intangible shipped Motion Paths. You draw a spline in the 3D scene, attach an object, and it travels the exact route you drew. Cars, aircraft, a follow shot, parts down an assembly line. You're blocking the move. Not prompting for one. Here's how it works:↓

CRAZY... you can now draw a camera move with your mouse and watch the scene actually run it. Intangible shipped Motion Paths. You draw a spline in the 3D scene, attach an object, and it travels the exact route you drew. Cars, aircraft, a follow shot, parts down an assembly line. You're blocking the move. Not prompting for one. Here's how it works:↓

Hasan Toor

20,718 views • 1 month ago

We just open-sourced Topview 3D Builder 🎬 Stop rolling the AI lottery. Start building the shot. Describe a scene in ChatGPT, Claude, or any AI agent, or drop in a reference image, and get an editable 3D set. Block your characters, props, and camera. Lock in composition, spatial relationships, and motion paths before you generate a single frame. Then export the frame or animation to Topview, or take it to any AI video model you like for video generation. Your scene, your camera, your call. Now open to everyone. #TopviewAI #TopviewFilmStudio #3DBuilder #OpenSource #AIVideo #AIFilmmaking

We just open-sourced Topview 3D Builder 🎬 Stop rolling the AI lottery. Start building the shot. Describe a scene in ChatGPT, Claude, or any AI agent, or drop in a reference image, and get an editable 3D set. Block your characters, props, and camera. Lock in composition, spatial relationships, and motion paths before you generate a single frame. Then export the frame or animation to Topview, or take it to any AI video model you like for video generation. Your scene, your camera, your call. Now open to everyone. #TopviewAI #TopviewFilmStudio #3DBuilder #OpenSource #AIVideo #AIFilmmaking

TopviewAI

114,608 views • 12 days ago