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.

Combining the explicit control of 3D software with the creativity of generative AI models is a promising yet underrated workflow. Build your 3D scenes procedurally by describing them in natural language, then take them all the way with your image & video models of choice. Tools like intangible are... show more

Bilawal Sidhu

106,897 subscribers

37,629 views • 1 year 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

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

The next phase of AI video needs infrastructure, not more tools.. This isn’t just a product update. It’s a new category. Topview 4.0 is the world’s first AI video collaboration board, built for how creators and teams actually work. One shared workspace to create, review, and iterate together without switching tools. Prompt → Image → Video → Avatar in a single flow. Real-time collaboration. All top image and video models in one place. Creator-friendly pricing, cheaper than official APIs. If AI video is part of your workflow, this is the board it belongs on. TopviewAI

Kuria | AI

12,848 views • 5 months ago

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!

@levelsio

119,210 views • 1 year ago

2025 is year of 3D AI Rodin AI 1.5 now can not only generate 3D model with clean meshes but also create high quality textures You can export all the models to 3D software to create a new world

2025 is year of 3D AI Rodin AI 1.5 now can not only generate 3D model with clean meshes but also create high quality textures You can export all the models to 3D software to create a new world

el.cine

92,563 views • 1 year ago

From product image to video with just one tool - Dzine As you may have noticed, this is one of my favorite tools. It is also very underrated, as probably 50% of my tutorials include some workflow. I was testing the new image-to-video option today, and I love it. Step - by step guide in comments 🔽 I can do 95% of a workflow without switching between apps. Image generation, Image to image with style reference, background removal, background generation, and 2 frames image to video. The only other app I have been using for this video is CapCut so that I can stitch it together. Step by step 🔽

From product image to video with just one tool - Dzine As you may have noticed, this is one of my favorite tools. It is also very underrated, as probably 50% of my tutorials include some workflow. I was testing the new image-to-video option today, and I love it. Step - by step guide in comments 🔽 I can do 95% of a workflow without switching between apps. Image generation, Image to image with style reference, background removal, background generation, and 2 frames image to video. The only other app I have been using for this video is CapCut so that I can stitch it together. Step by step 🔽

Teodora P L

28,523 views • 1 year ago

I built an entire 3D editor this past weekend with -- using natural language 🤯 Powered by React, Three.js, and the Rapier physics engine. I believe AI will soon enable us to create the tools we need the moment we think of them. Thread 👇

I built an entire 3D editor this past weekend with -- using natural language 🤯 Powered by React, Three.js, and the Rapier physics engine. I believe AI will soon enable us to create the tools we need the moment we think of them. Thread 👇

Ian Curtis

175,983 views • 1 year ago

By far the best way to generate images at different angles is this 3D Camera Control node. Instead of describing angles with words, you just click the view you want. Simple UI, and the Qwen Image Edit 2511 multi-angle LoRA keeps things consistent across generations. Workflow below 👇

By far the best way to generate images at different angles is this 3D Camera Control node. Instead of describing angles with words, you just click the view you want. Simple UI, and the Qwen Image Edit 2511 multi-angle LoRA keeps things consistent across generations. Workflow below 👇

rob - comfyui

59,189 views • 6 months ago

Reworked my code and I can now import and manipulate multiple 3D models!! This now reminds me of the built-in Holograms apps on HoloLens. The simplest usecase is decorating your home with Sketchfab models ... would you make your home more personal with virtual objects? #visionOS

Reworked my code and I can now import and manipulate multiple 3D models!! This now reminds me of the built-in Holograms apps on HoloLens. The simplest usecase is decorating your home with Sketchfab models ... would you make your home more personal with virtual objects? #visionOS

Tina Debove ᯅ

21,603 views • 3 years 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

92,792 views • 2 years ago

The power of QuiverAI 's newest vector image models is in a workflow. Connect Arrow 1.1 to your LLMs and image models in FLORA, and it becomes a full creative system. This tutorial covers logo ideation, fashion design, and a lot more. Here are the use cases:

FLORA ©

105,085 views • 3 months ago

Generative AI is really cool but sometimes you want to drift your car through an intersection in a super specific way. Draw a spline then get 3D onion skinning so you can adjust the curves with a clear spatial reference. iCars plugin for Blender:

Generative AI is really cool but sometimes you want to drift your car through an intersection in a super specific way. Draw a spline then get 3D onion skinning so you can adjust the curves with a clear spatial reference. iCars plugin for Blender:

Bilawal Sidhu

183,667 views • 11 months ago

This is some quietly impressive work on making video world models actually controllable in 4D space. VerseCrafter lets you take an input image, use something like Blender to animate the 3D camera path and object trajectories, then uses that to condition generation. Scribbling in 2D feels so crude in comparison. The authors represent everything in a shared 4D world state - static background as a point cloud, moving objects as 3D gaussian trajectories. The gaussians are an interesting choice because they capture position, shape, and orientation probabilistically rather than forcing rigid bounding boxes or category specific models like SMPL-X for human bodies. They bolt this onto frozen Wan2.1 with a lightweight adapter, so they get a strong video prior. They also built a pipeline to auto extract 4D annotations from real world videos to train this puppy. It doesn't look sexy yet, but IMO this is the interface video world models need - actual 3D authoring tools to exert control rather than crude scribbles and prompt incantations.

This is some quietly impressive work on making video world models actually controllable in 4D space. VerseCrafter lets you take an input image, use something like Blender to animate the 3D camera path and object trajectories, then uses that to condition generation. Scribbling in 2D feels so crude in comparison. The authors represent everything in a shared 4D world state - static background as a point cloud, moving objects as 3D gaussian trajectories. The gaussians are an interesting choice because they capture position, shape, and orientation probabilistically rather than forcing rigid bounding boxes or category specific models like SMPL-X for human bodies. They bolt this onto frozen Wan2.1 with a lightweight adapter, so they get a strong video prior. They also built a pipeline to auto extract 4D annotations from real world videos to train this puppy. It doesn't look sexy yet, but IMO this is the interface video world models need - actual 3D authoring tools to exert control rather than crude scribbles and prompt incantations.

Bilawal Sidhu

25,802 views • 6 months ago

Ash Ketchum for the Pokémon x North Face winter drip collection. These fashion contact sheet videos are ridiculously easy to make with the following workflow. All you need is → character image → outfit image → a bit of manual prompting → a good idea Full workflow 👇

Ash Ketchum for the Pokémon x North Face winter drip collection. These fashion contact sheet videos are ridiculously easy to make with the following workflow. All you need is → character image → outfit image → a bit of manual prompting → a good idea Full workflow 👇

rob - comfyui

250,447 views • 6 months ago

i’ll always think it’s so cool that they introduced the tape. like it’s such an easy way for ANYONE to be able to participate. you don’t need to buy merch to be a part of everything, you just have to get your hands on a $3 roll of duct tape.

i’ll always think it’s so cool that they introduced the tape. like it’s such an easy way for ANYONE to be able to participate. you don’t need to buy merch to be a part of everything, you just have to get your hands on a $3 roll of duct tape.

ronni ♡

39,398 views • 1 year ago

AI 3D animations are pulling millions of views right now, not just as paid ads, but organically too this format can sell literally anything: ebooks, courses, supplements, peptides, apps, communities - whatever and you can make them in under 10 minutes, all you need is: - a script (claude with copywriting skill) - a strong first frame (Nano Banana Pro) - Veo 3 to animate it this workflow is so easy and repeatable you can automate the whole thing without any fancy tools that’s it. you just saved hours and $1000+ on a 3D artist

AI 3D animations are pulling millions of views right now, not just as paid ads, but organically too this format can sell literally anything: ebooks, courses, supplements, peptides, apps, communities - whatever and you can make them in under 10 minutes, all you need is: - a script (claude with copywriting skill) - a strong first frame (Nano Banana Pro) - Veo 3 to animate it this workflow is so easy and repeatable you can automate the whole thing without any fancy tools that’s it. you just saved hours and $1000+ on a 3D artist

MAX

267,338 views • 5 months ago

Generative 3d environments just became a thing with the announcement of OpenAI's new video model, Sora. Michael Rublof from took one of those videos, and turned it into a NeRF using Colmap and Nerfstudio. While people are laughing at the topology of generated models, the world is changing around us, and that's exciting and a little scary, but we'll find a way to turn Gen Ai into creative superpowers. I believe in human creativity, in our ability to surprise, to move, to change and to challenge. Here's to the future! #ai #art

Generative 3d environments just became a thing with the announcement of OpenAI's new video model, Sora. Michael Rublof from took one of those videos, and turned it into a NeRF using Colmap and Nerfstudio. While people are laughing at the topology of generated models, the world is changing around us, and that's exciting and a little scary, but we'll find a way to turn Gen Ai into creative superpowers. I believe in human creativity, in our ability to surprise, to move, to change and to challenge. Here's to the future! #ai #art

Martin Nebelong

288,988 views • 2 years ago

The context size of video world models is only a few frames. Like a human with severe memory loss! We design a long-term memory for world models based on explicit 3D representations inspired by the human mind. This enables long-term consistency. 1/3

The context size of video world models is only a few frames. Like a human with severe memory loss! We design a long-term memory for world models based on explicit 3D representations inspired by the human mind. This enables long-term consistency. 1/3

Gordon Wetzstein

35,075 views • 1 year ago

Video diffusion models have strong implicit representations of 3D shape, material, and lighting, but controlling them with language is cumbersome, and control is critical for artists and animators. GenLit connects these implicit representations with a continuous 5D control signal describing the direction and intensity of a point light source. This enables single-image near-field relighting of an image using a video diffusion model. We use a ControlNet-like approach and show that, with a small amount of synthetic data, GenLit generalizes to complex real-world images. Given a single image and the 5D lighting signal, GenLit creates a video of a moving light source that is inside the scene. It moves around and behind scene objects, producing effects such as shading, cast shadows, secularities, and interreflections with a realism that is hard to obtain with traditional inverse rendering methods. GenLit shows that it is possible to get continuous control over implicit physical processes within a video model. I think this is just the beginning and promises to make such models much more practical for creators. Shrisha Bharadwaj will present today at SIGGRAPH Asia Room: S423/S424, Level 4 @ 13:50 on 15 of Dec.

Video diffusion models have strong implicit representations of 3D shape, material, and lighting, but controlling them with language is cumbersome, and control is critical for artists and animators. GenLit connects these implicit representations with a continuous 5D control signal describing the direction and intensity of a point light source. This enables single-image near-field relighting of an image using a video diffusion model. We use a ControlNet-like approach and show that, with a small amount of synthetic data, GenLit generalizes to complex real-world images. Given a single image and the 5D lighting signal, GenLit creates a video of a moving light source that is inside the scene. It moves around and behind scene objects, producing effects such as shading, cast shadows, secularities, and interreflections with a realism that is hard to obtain with traditional inverse rendering methods. GenLit shows that it is possible to get continuous control over implicit physical processes within a video model. I think this is just the beginning and promises to make such models much more practical for creators. Shrisha Bharadwaj will present today at SIGGRAPH Asia Room: S423/S424, Level 4 @ 13:50 on 15 of Dec.

Michael Black

22,182 views • 7 months ago

Kling 2.6: A Real Killer of Other Video Models on Higgsfield. Upgrade your workflow with 70% OFF on Higgsfield + UNLIMITED image models for a year. Only for Cyber Week. Forget about manual cleanup. Kling 2.6 delivers professional results straight out of the gate. Sharper, faster, and completely unrestricted on Higgsfield AI 🧩

Kling 2.6: A Real Killer of Other Video Models on Higgsfield. Upgrade your workflow with 70% OFF on Higgsfield + UNLIMITED image models for a year. Only for Cyber Week. Forget about manual cleanup. Kling 2.6 delivers professional results straight out of the gate. Sharper, faster, and completely unrestricted on Higgsfield AI 🧩

Perks

98,231 views • 8 months ago