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.

Fun & likely unintended use case for #NanoBananaPro: image→3D point cloud Prompt: This is a rendering of a 3D model of a person. Make an accurate image of the corresponding normal map. Then I run Poisson-based normals→3D Pretty amazing for a general-purpose 2D image model 🤩

Keenan Crane

39,193 subscribers

71,780 views • 9 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

the fact that i can take an image of a room and turn it into a 3d model in one shot is actually insane this took like 30 seconds from image to 3d model

the fact that i can take an image of a room and turn it into a 3d model in one shot is actually insane this took like 30 seconds from image to 3d model

Jan

131,884 views • 9 months ago

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Bilawal Sidhu

92,867 views • 2 years ago

Card design using Cavalry for the animation. Midjourney for the source image, turned into a 3D model using KREA AI. Then in Cavalry converted using the Image Sampler.

Card design using Cavalry for the animation. Midjourney for the source image, turned into a 3D model using KREA AI. Then in Cavalry converted using the Image Sampler.

Yianni

36,910 views • 11 months ago

From flat image to animated 3D models in Spaces → Generate 3D models from an image or a prompt → Retexture, remesh, convert and UV unwrap on the canvas → Auto-rig your characters and apply animations → Snapshot any model into your image or video workflow Now on Magnific

From flat image to animated 3D models in Spaces → Generate 3D models from an image or a prompt → Retexture, remesh, convert and UV unwrap on the canvas → Auto-rig your characters and apply animations → Snapshot any model into your image or video workflow Now on Magnific

Magnific

13,316 views • 23 days ago

📢We introduce “RefFusion”, a novel inpainting method for scenes reconstructed using 3D Gaussian Splatting. 🔗 TLDR: we personalize an image diffusion model to a given reference image and distill its knowledge to 3D through score distillation sampling.

📢We introduce “RefFusion”, a novel inpainting method for scenes reconstructed using 3D Gaussian Splatting. 🔗 TLDR: we personalize an image diffusion model to a given reference image and distill its knowledge to 3D through score distillation sampling.

Ashkan Mirzaei

34,700 views • 2 years ago

I added a node to my custom node that converts the depth image to a normal map! This is useful for 2D-style images where Normals Estimation doesn't work well.

I added a node to my custom node that converts the depth image to a normal map! This is useful for 2D-style images where Normals Estimation doesn't work well.

toyxyz

117,422 views • 1 year ago

Okay this new model is insane. Generate an image, then give it to the model to turn it into a 3D model with matching texture in seconds. Creativity on Spielwerk will be endless with this

Okay this new model is insane. Generate an image, then give it to the model to turn it into a 3D model with matching texture in seconds. Creativity on Spielwerk will be endless with this

Eike Drescher

37,987 views • 9 months ago

Meta dropped not just SAM-3 yesterday but also SAM-3D (for objects and humans)🤯 SAM 3D Body is a promptable model for recovering full-body 3D human meshes from a single image. Seems to be the new SOTA

Meta dropped not just SAM-3 yesterday but also SAM-3D (for objects and humans)🤯 SAM 3D Body is a promptable model for recovering full-body 3D human meshes from a single image. Seems to be the new SOTA

Niels Rogge

125,235 views • 9 months ago

Turn any webpage into a museum! 🏛️ Made this Chrome extension that uses Hunyuan 3D v3.1 on fal to turn any image into a 3D model, and three.js for the interactive viewer

Turn any webpage into a museum! 🏛️ Made this Chrome extension that uses Hunyuan 3D v3.1 on fal to turn any image into a 3D model, and three.js for the interactive viewer

Blendi

48,960 views • 4 months ago

SAM 3D Body is a CVPR 2026 award candidate paper from AI at Meta model recovers a full 3D human body mesh from a single RGB image you can run it automatically, or guide the reconstruction with masks and 2D keypoints thx to Niels Rogge for awesome demo idea

SAM 3D Body is a CVPR 2026 award candidate paper from AI at Meta model recovers a full 3D human body mesh from a single RGB image you can run it automatically, or guide the reconstruction with masks and 2D keypoints thx to Niels Rogge for awesome demo idea

SkalskiP

72,500 views • 2 months ago

Player stats UI animation with GPT Image 2 and MiniMax H3. This model is amazing for UI animations. Give GPT Image 2 your character image and ask it to create a stats UI. Then use that UI as a reference for MiniMax H3. You can check the prompt in the replies.

Player stats UI animation with GPT Image 2 and MiniMax H3. This model is amazing for UI animations. Give GPT Image 2 your character image and ask it to create a stats UI. Then use that UI as a reference for MiniMax H3. You can check the prompt in the replies.

Kōda

40,507 views • 16 days ago

The new Krea 3D feature is insanely good. You can turn an image into a 3D model to move & rotate in space - and it guides real-time scene generation. Watch me move this couch around a living room ⬇️

The new Krea 3D feature is insanely good. You can turn an image into a 3D model to move & rotate in space - and it guides real-time scene generation. Watch me move this couch around a living room ⬇️

Justine Moore

32,728 views • 1 year ago

woww.. AI can literally do 3D rendering now just upload a draft 3D animation, it turns it into cinematic film scene you can control the looks of the car and environment with image refs no need days of rendering anymore..

woww.. AI can literally do 3D rendering now just upload a draft 3D animation, it turns it into cinematic film scene you can control the looks of the car and environment with image refs no need days of rendering anymore..

el.cine

113,268 views • 8 months ago

My 3D Model of Malevola from Dispatch is finally finished! This was a super fun project, I learned how to use hair curves for the first time and also 3D printed the full model! Have a look at the full process video! #blender #b3d #dispatch

My 3D Model of Malevola from Dispatch is finally finished! This was a super fun project, I learned how to use hair curves for the first time and also 3D printed the full model! Have a look at the full process video! #blender #b3d #dispatch

Niall

15,127 views • 7 months ago

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

MrNeRF

52,849 views • 1 year ago

3d world abilities of AI models keep getting better, this is @Kling_AI 1.5 It can move around a space in 3d and you can steer its camera movements All based on a single input image

3d world abilities of AI models keep getting better, this is @Kling_AI 1.5 It can move around a space in 3d and you can steer its camera movements All based on a single input image

@levelsio

112,201 views • 1 year ago

⭐️3D Model Showcase ⭐️ I had the pleasure of working on a 3D model for Buffpup 🦴VchiBan✨ Thank you so much!!

⭐️3D Model Showcase ⭐️ I had the pleasure of working on a 3D model for Buffpup 🦴VchiBan✨ Thank you so much!!

Mari | 3D Modeler

147,049 views • 2 months ago