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.

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

27,074 subscribers

12,230 views • 9 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

20 Comments

martin_casado9 days ago

NOO!!!!!! THIS IS CRAZY!!

Sylvan Shen9 days ago

Love the iterative process!

Ian Curtis9 days ago

it's fun seeing the handheld effect

Erik Luo9 days ago

Bro…

Ian Curtis9 days ago

👀 been loving the stuff you have been putting out!

Erik Luo9 days ago

🙌Atlas is just too good

Lux9 days ago

This is amazing. Can we use it?

Ian Curtis9 days ago

Will work on open sourcing it! Whats cool is @the8thwall is open source for the web augmented reality part too.

Lux9 days ago

@the8thwall How does it get the input camera motion? Could it be fed to it by an animation of a virtual camera or another video? Does it need to be AR?

Ian Curtis9 days ago

@the8thwall Yes, grabs my camera motion/position from my mobile device in AR then sends that info to Atlas API But it can totally be used in different ways

Ana.King669 days ago

Impressive work, Ian 👌

Ian Curtis9 days ago

Thank you 🫡 so many things to make, so little time

Ana.King669 days ago

Yep. Creativity is exploding rn with all the tools and possibilities 😮‍💨. Looking forward for worldlabs haptical holodeck in 2027 🤞🖖

Ian Curtis9 days ago

➕➕➕➕➕

Adam Chernick9 days ago

@BrittaniNatali There it is!! Let’s go!

Ian Curtis9 days ago

@BrittaniNatali Hah I had this working yesterday right as you said that 🙏😅

Adam Chernick9 days ago

@BrittaniNatali One step ahead! This is awesome dude

boon9 days ago

beautiful

⋆｡ﾟ🪐｡⋆｡ﾟ ℂ𝕃𝔸𝕌𝔻𝔼 & 𝔽ℝ𝕀𝔼ℕ𝔻𝕊 𝕀ℕℂ. 🛸 ⋆｡ﾟ☾9 days ago

@theworldlabs Very cool stuff! Will try it out soon too!

Ian Curtis9 days ago

@theworldlabs Yes! I’ll open source an example very soon

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 • 10 days ago

Atlas lets you build out large 3D environments starting from a single input image. You can then define a camera path through the world and generate a video along it. Here’s how the 3D structure, camera path and final flythrough connect.

Atlas lets you build out large 3D environments starting from a single input image. You can then define a camera path through the world and generate a video along it. Here’s how the 3D structure, camera path and final flythrough connect.

World Labs

18,163 views • 3 days ago

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 scene. Here we made a 1 min video with a couple images of totally different scenes, and we set where the camera keyframes should move through each part of the scene. The scene-to-scene transitions are great. Atlas makes it feel like a smooth shot with no cuts.

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 scene. Here we made a 1 min video with a couple images of totally different scenes, and we set where the camera keyframes should move through each part of the scene. The scene-to-scene transitions are great. Atlas makes it feel like a smooth shot with no cuts.

David Pantera

27,621 views • 1 month ago

Introducing Atlas: The world's first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D. Model the world, move the camera, and simulate space & time.

Introducing Atlas: The world's first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D. Model the world, move the camera, and simulate space & time.

World Labs

10,870,302 views • 1 month ago

🚨 BREAKING: NEW ATLAS ANALYSIS — The Frame They Didn’t Want You To See Image analyst MrMBB333 took a deep dive into the latest ATLAS imagery, and what he found changes everything. The truth is in the pixels. #ATLAS #MrMBB333 #Anomaly #SpaceWatch #Breaking

🚨 BREAKING: NEW ATLAS ANALYSIS — The Frame They Didn’t Want You To See Image analyst MrMBB333 took a deep dive into the latest ATLAS imagery, and what he found changes everything. The truth is in the pixels. #ATLAS #MrMBB333 #Anomaly #SpaceWatch #Breaking

Michael Bradbury

131,214 views • 1 year ago

🎬 Made something real with Seedance 2.5. I wanted to push cinematic AI video beyond “cool visuals” and create something that actually feels like a scene from a film. Built with Atlas Cloud + Seedance 2.5 ⚡️ From the prompt → generation → final result, the workflow made it surprisingly easy to turn an idea into a polished visual. What would you create with it? Built with Atlas Cloud #AtlasCloud #Seedance25 #AIVideo #GenerativeAI #AI

🎬 Made something real with Seedance 2.5. I wanted to push cinematic AI video beyond “cool visuals” and create something that actually feels like a scene from a film. Built with Atlas Cloud + Seedance 2.5 ⚡️ From the prompt → generation → final result, the workflow made it surprisingly easy to turn an idea into a polished visual. What would you create with it? Built with Atlas Cloud #AtlasCloud #Seedance25 #AIVideo #GenerativeAI #AI

Fatema

19,411 views • 1 month ago

It took me less than 10 minutes to create this scene. The longest part was finding the style for my initial image. I used Grok Imagine's extension video to ensure perfect continuity of style, voice, and music. Then I animated it, prompting in my native language without asking for any dialogue. Grok understood everything I asked and created a dialogue between the children in perfect French. I later posted the same children with a prompt in English, and this time, the dialogue was in English. I used Grok Imagine to create the image, animate it, and then extend the video to 30 seconds. I then started again with an image that I modified through editing and used it to tell another story.

It took me less than 10 minutes to create this scene. The longest part was finding the style for my initial image. I used Grok Imagine's extension video to ensure perfect continuity of style, voice, and music. Then I animated it, prompting in my native language without asking for any dialogue. Grok understood everything I asked and created a dialogue between the children in perfect French. I later posted the same children with a prompt in English, and this time, the dialogue was in English. I used Grok Imagine to create the image, animate it, and then extend the video to 30 seconds. I then started again with an image that I modified through editing and used it to tell another story.

Déborah

501,454 views • 7 months ago

I asked Kling 3.0 to create a short film from just a single image... and the result blew my mind! here's how I made this video using Multi-Shot 👇

I asked Kling 3.0 to create a short film from just a single image... and the result blew my mind! here's how I made this video using Multi-Shot 👇

TechHalla

77,883 views • 8 months ago

making perf testing fun: the reverse image search i built for Patina Systems is so fast we can literally search your library with a camera feed. it will embed each frame from the stream in ~10ms and finds the most similar photos in my last 20k photos in ~15-20ms, making realtime frame matching possible.

making perf testing fun: the reverse image search i built for Patina Systems is so fast we can literally search your library with a camera feed. it will embed each frame from the stream in ~10ms and finds the most similar photos in my last 20k photos in ~15-20ms, making realtime frame matching possible.

Tyler Angert

38,667 views • 1 year ago

15 years ago, I shot the music video for my song 'Comin At Ya' in London... The whole video was shot in a single, continuous take with no edits. Fun fact: The 1st time we tried it, the cameraman bumped into someone (he walked backwards the entire time) so we used the 2nd take!

15 years ago, I shot the music video for my song 'Comin At Ya' in London... The whole video was shot in a single, continuous take with no edits. Fun fact: The 1st time we tried it, the cameraman bumped into someone (he walked backwards the entire time) so we used the 2nd take!

ZUBY:

49,657 views • 2 months ago

Just tested Runway Aleph 2.0 and this blew my mind a bit lol I saw a video like this when Aleph first released and with the new Aleph 2.0 I wanted to create my own version. You basically select a single frame from the video, apply a change to that specific frame using Nano Banana Pro, GPT Image 2 or Gen-4 and based on the newly generated image Aleph propagates the change through the entire shot. It's really cool seeing the whole sequence adapt from just one edited frame

Just tested Runway Aleph 2.0 and this blew my mind a bit lol I saw a video like this when Aleph first released and with the new Aleph 2.0 I wanted to create my own version. You basically select a single frame from the video, apply a change to that specific frame using Nano Banana Pro, GPT Image 2 or Gen-4 and based on the newly generated image Aleph propagates the change through the entire shot. It's really cool seeing the whole sequence adapt from just one edited frame

Ege

88,621 views • 5 months 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

47,055 views • 1 month ago

Atlas - Episode 5 is here! Full playlist - Built with custom "beancat" agent harness, seedance 2.5, and generated via Atlas Cloud API

Atlas - Episode 5 is here! Full playlist - Built with custom "beancat" agent harness, seedance 2.5, and generated via Atlas Cloud API

biglootpig

402,994 views • 1 month ago

With today's OpenAI image gen updates, I made this demo site that generates cute skeuomorphic images. With the Responses API + gpt-4.1, it supports: – image streaming and a progress bar (via Responses events) – speed/quality toggle – image uploads – image edits

With today's OpenAI image gen updates, I made this demo site that generates cute skeuomorphic images. With the Responses API + gpt-4.1, it supports: – image streaming and a progress bar (via Responses events) – speed/quality toggle – image uploads – image edits

edwin

53,564 views • 1 year ago

By positioning multiple input views within the model's spatial context, Atlas allows you to generate image and video frames with precise control. Here, we hand-designed a camera trajectory to generate a 1 minute video at 1440p resolution from seven reference images.

By positioning multiple input views within the model's spatial context, Atlas allows you to generate image and video frames with precise control. Here, we hand-designed a camera trajectory to generate a 1 minute video at 1440p resolution from seven reference images.

World Labs

252,716 views • 1 month ago

From one frame to a whole video! I built a continuous 45-second shot out of a still image. Using a single image I created using Dreamina, I added new scenes with nano-banana. Then, using Kling's First/Last frame and Sora, I made it all work together. Topaz Astra for upscale:

From one frame to a whole video! I built a continuous 45-second shot out of a still image. Using a single image I created using Dreamina, I added new scenes with nano-banana. Then, using Kling's First/Last frame and Sora, I made it all work together. Topaz Astra for upscale:

Alex Patrascu

11,519 views • 1 year ago

Here's a demo of the gpt-4-vision API that I built in Bubble in 30 min. It takes a URL, converts it to an image, and sends it through the Vision API to respond with custom landing page optimization suggestions.

Here's a demo of the gpt-4-vision API that I built in Bubble in 30 min. It takes a URL, converts it to an image, and sends it through the Vision API to respond with custom landing page optimization suggestions.

Seth Kramer

954,101 views • 3 years ago

I was so frustrated with the experience using nano-banana that I built a self-correcting image agent. The agent generates images and evaluates them against the original request until the goal is met. Like in this video, it was able to achieve the goal in 6 loops.

I was so frustrated with the experience using nano-banana that I built a self-correcting image agent. The agent generates images and evaluates them against the original request until the goal is met. Like in this video, it was able to achieve the goal in 6 loops.

Pietro Schirano

101,769 views • 1 year ago