Загрузка видео...

Не удалось загрузить видео

На главную

Japanese 3D artist 平の字 shared a procedural experiment: a complete, detailed fantasy village built 100% inside Blender’s Geometry Node Editor—with zero AI involved. By using geo node to drive building placements, roof angles, wooden beams, and terrain features, non-destructive node setups allow creators to build, tweak, and iterate complex...

3DxDEV7's profile picture

3DxDEV

15,061 subscribers

27,283 просмотров • 7 дней назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 4

Фото профиля braza
braza7 дней назад

@hiranoji geo nodes for the village, hand placement for the one door that has to look right 🙃

Фото профиля GGwink
GGwink6 дней назад

@hiranoji Impressive

Фото профиля Jimmy Lee
Jimmy Lee7 дней назад

@hiranoji Looks wonderful

Фото профиля COBOX
COBOX7 дней назад

@hiranoji Procedural magic 🔥

Похожие видео

You don’t need complex 3D modeling or hours of sculpting to build detailed environment assets in Blender. In fact, Ian Hubert's Ian Hubert iconic "Lazy Tutorial" technique shows how simple photo projection onto basic geometry lets you block out, extrude, and build realistic custom buildings in under a minute. By mapping real-world photos onto simple cubes and using basic knife cuts and extrusions, you let the photo texture do 90% of the visual heavy lifting. Do you prefer building environments procedurally with geometry nodes, or sticking to fast, photographic projection techniques like this? #b3d #Blender3D #GameDev
0:44

You don’t need complex 3D modeling or hours of sculpting to build detailed environment assets in Blender. In fact, Ian Hubert's Ian Hubert iconic "Lazy Tutorial" technique shows how simple photo projection onto basic geometry lets you block out, extrude, and build realistic custom buildings in under a minute. By mapping real-world photos onto simple cubes and using basic knife cuts and extrusions, you let the photo texture do 90% of the visual heavy lifting. Do you prefer building environments procedurally with geometry nodes, or sticking to fast, photographic projection techniques like this? #b3d #Blender3D #GameDev

3DxDEV

57,792 просмотров • 1 месяц назад

Procedural mesh fracturing in Blender usually means slow calculations, messy topology, or relying on heavy third-party add-ons. Environment and technical artist Jolan Huijskes built a custom Geometry Nodes fracturing solution that splits 3D models into clean, procedural stone blocks and cracked surface tiles in real time—and he's releasing the nodes for free. By leveraging Blender's Manifold booleans and accumulating cuts across individual mesh islands, the setup generates realistic stone cracks and edge damage without tanking viewport performance. Do you rely on Geometry Nodes for procedural destruction and asset variation, or do you still prefer destructible physics tools and manual sculpting? #b3d #GeometryNodes #Blender3D #TechArt #EnvironmentArt
0:20

Procedural mesh fracturing in Blender usually means slow calculations, messy topology, or relying on heavy third-party add-ons. Environment and technical artist Jolan Huijskes built a custom Geometry Nodes fracturing solution that splits 3D models into clean, procedural stone blocks and cracked surface tiles in real time—and he's releasing the nodes for free. By leveraging Blender's Manifold booleans and accumulating cuts across individual mesh islands, the setup generates realistic stone cracks and edge damage without tanking viewport performance. Do you rely on Geometry Nodes for procedural destruction and asset variation, or do you still prefer destructible physics tools and manual sculpting? #b3d #GeometryNodes #Blender3D #TechArt #EnvironmentArt

3DxDEV

33,133 просмотров • 18 дней назад

Is starting an anime head model from a single quad face actually the cleanest way to control topology in Blender? NPR 3D character artist Katsu Natsumori / 夏森轄 mesmerized thousands of creators by sharing a hypnotic timelapse depicting a cute 3D anime witch head being built step-by-step from scratch. Starting from a single 2D quad plane, Natsumori uses face extrusions and loop cuts to build out perfect cel-shaded facial features, eye sockets, and hair volume—proving that precise 2D topology planning is essential for clean 3D anime rendering. Do you start character head modeling with base primitives like a sphere, or do you extrude face geometry quad-by-quad from a single plane? #b3d #Blender3D #3DModeling #AnimeArt #CharacterArt
0:50

Is starting an anime head model from a single quad face actually the cleanest way to control topology in Blender? NPR 3D character artist Katsu Natsumori / 夏森轄 mesmerized thousands of creators by sharing a hypnotic timelapse depicting a cute 3D anime witch head being built step-by-step from scratch. Starting from a single 2D quad plane, Natsumori uses face extrusions and loop cuts to build out perfect cel-shaded facial features, eye sockets, and hair volume—proving that precise 2D topology planning is essential for clean 3D anime rendering. Do you start character head modeling with base primitives like a sphere, or do you extrude face geometry quad-by-quad from a single plane? #b3d #Blender3D #3DModeling #AnimeArt #CharacterArt

3DxDEV

30,518 просмотров • 4 дней назад

great to see more people generating 3d avatars with our new text-to-3d feature in forge. this marks a step in the right direction in putting powerful creation tools directly in the hands of everyone. we built forge entirely from the ground up over the past months as one of the key releases on our roadmap. having full proprietary ownership of the technology gives us complete control to shape its direction without depending on external platforms or third-party licenses. building on this foundation, our upcoming studio feature will let users generate high-quality accessories, clothing, and environments simply by typing natural language prompts. a single description can produce fully textured, production-ready 3d assets in seconds, with options to create multiple variations and refine them through follow-up instructions.every asset created in studio integrates seamlessly with the 3d ai agents made in forge on users can instantly apply clothing and accessories with automatic fitting, layer multiple items, and place their agents inside custom-generated environments. all clothing and accessories come pre-rigged and optimized, while environments include proper lighting and geometry for immediate use in games, animation, virtual worlds, and more. we have spent months thoughtfully designing how can deliver real, sustainable value back to the community. we will continue to share more details on token utility use cases and the economic flywheel we have built. the goal is to create a self-reinforcing system where creators earn through royalties, autonomous agents drive on-chain activity, and platform growth directly benefits active community members and token holders. together, these features enable a complete creative flow. from a simple idea, anyone can quickly build fully realized 3d ai agents standing in rich, custom scenes. we are excited to see what the community builds next.
0:24

great to see more people generating 3d avatars with our new text-to-3d feature in forge. this marks a step in the right direction in putting powerful creation tools directly in the hands of everyone. we built forge entirely from the ground up over the past months as one of the key releases on our roadmap. having full proprietary ownership of the technology gives us complete control to shape its direction without depending on external platforms or third-party licenses. building on this foundation, our upcoming studio feature will let users generate high-quality accessories, clothing, and environments simply by typing natural language prompts. a single description can produce fully textured, production-ready 3d assets in seconds, with options to create multiple variations and refine them through follow-up instructions.every asset created in studio integrates seamlessly with the 3d ai agents made in forge on users can instantly apply clothing and accessories with automatic fitting, layer multiple items, and place their agents inside custom-generated environments. all clothing and accessories come pre-rigged and optimized, while environments include proper lighting and geometry for immediate use in games, animation, virtual worlds, and more. we have spent months thoughtfully designing how can deliver real, sustainable value back to the community. we will continue to share more details on token utility use cases and the economic flywheel we have built. the goal is to create a self-reinforcing system where creators earn through royalties, autonomous agents drive on-chain activity, and platform growth directly benefits active community members and token holders. together, these features enable a complete creative flow. from a simple idea, anyone can quickly build fully realized 3d ai agents standing in rich, custom scenes. we are excited to see what the community builds next.

nich

19,611 просмотров • 3 месяцев назад

Created an animated convertible car with AI! The part that got me excited from the house experiment was watching Blender assemble everything. Initially I tried the same workflow for the car, but as you can see, assembling a bunch of separately generated parts doesn’t really give a great result here. So I went with a simpler setup. Now Atlas has a new Blender Node, which basically runs Blender MCP inside the workflow. This meant I didn’t have to leave the canvas. It created the reference images, generated the high-poly Tripo 3.1 mesh, baked the low-poly version with the Blender Node, and did the full assembly of the car with the body and wheels. I could even give it images of the badges and license plate, and it created the geometry and placed everything correctly inside the node. The convertible roof rig needed a bit more directing though. But still, I didn’t have to do any weight painting or manually place bones. With some back and forth, Astra created a working skeletal mesh for me to use. In UEFN / Unreal Engine i made everything work together with Control Rig and Level Sequencer.
1:24

Created an animated convertible car with AI! The part that got me excited from the house experiment was watching Blender assemble everything. Initially I tried the same workflow for the car, but as you can see, assembling a bunch of separately generated parts doesn’t really give a great result here. So I went with a simpler setup. Now Atlas has a new Blender Node, which basically runs Blender MCP inside the workflow. This meant I didn’t have to leave the canvas. It created the reference images, generated the high-poly Tripo 3.1 mesh, baked the low-poly version with the Blender Node, and did the full assembly of the car with the body and wheels. I could even give it images of the badges and license plate, and it created the geometry and placed everything correctly inside the node. The convertible roof rig needed a bit more directing though. But still, I didn’t have to do any weight painting or manually place bones. With some back and forth, Astra created a working skeletal mesh for me to use. In UEFN / Unreal Engine i made everything work together with Control Rig and Level Sequencer.

Jerome | InsaneUnreal

10,744 просмотров • 12 дней назад

With GPT-6 Astra, my 3D character came to life in Blender and started modeling her own clothes right inside the viewport. The video shows the real process: the character is literally redesigning her wardrobe in real time. Selecting polygons, extruding sleeves, adding modifiers, and tailoring the hoodie pattern to her body. All by herself. From the first vertex to deleting discarded meshes. OpenAI claims GPT-6 Astra can already operate software through the interface: opening apps, clicking buttons, extruding geometry, and making edits like a seasoned 3D artist. In tests with 3D and CAD environments, the new model hit record accuracy across complex workflows, leaving older versions far behind. And through agentic pipelines, it generates production-ready assets, clothing, and full scenes from simple text prompts without manual grind. Would you trust routine 3D modeling to AI or keep moving vertices by hand?
0:46

With GPT-6 Astra, my 3D character came to life in Blender and started modeling her own clothes right inside the viewport. The video shows the real process: the character is literally redesigning her wardrobe in real time. Selecting polygons, extruding sleeves, adding modifiers, and tailoring the hoodie pattern to her body. All by herself. From the first vertex to deleting discarded meshes. OpenAI claims GPT-6 Astra can already operate software through the interface: opening apps, clicking buttons, extruding geometry, and making edits like a seasoned 3D artist. In tests with 3D and CAD environments, the new model hit record accuracy across complex workflows, leaving older versions far behind. And through agentic pipelines, it generates production-ready assets, clothing, and full scenes from simple text prompts without manual grind. Would you trust routine 3D modeling to AI or keep moving vertices by hand?

Damir Akaza

167,678 просмотров • 1 месяц назад

At Avalon we are building "Real-time creating" - the ability to generate gameplay ready persistent worlds prompted from text. While others are building real-time video world models, Avalon is building real-time world generation inside a fully playable, persistent multiplayer engine. Internally running at 3840×2180 at 60 FPS. Built on Unreal Engine. Multiplayer by default. Persistent by default. Gameplay-ready by default. This is not a video latent replay. Not a simulation of interaction. It is a real 3D world with physics, logic, and authoritative multiplayer state. Avalon is trained on proprietary Avalon interaction data and powered by a hybrid system that combines language understanding, 3D model generation, procedural systems, and structured gameplay logic synthesis. Players can walk through a live world and generate environments, assets, mechanics, and entirely new gameplay modes using natural language. We accomplish this through a combination of 3D model generation, game logic generation based on our proprietary systems, and AI driven world creation. While other players are inside it. Changes persist instantly. State is synchronized in real time. Creation happens inside the world, not outside of it. Describe a biome. Spawn a civilization. Create a survival mode. Build a dungeon crawler. Launch a new game inside the world. Avalon interprets intent and integrates it directly into the live multiplayer environment. This is not a world model predicting video. This is a gameplay engine that understands language. If you can describe it, you can build it. And others can walk into it instantly.
1:09

At Avalon we are building "Real-time creating" - the ability to generate gameplay ready persistent worlds prompted from text. While others are building real-time video world models, Avalon is building real-time world generation inside a fully playable, persistent multiplayer engine. Internally running at 3840×2180 at 60 FPS. Built on Unreal Engine. Multiplayer by default. Persistent by default. Gameplay-ready by default. This is not a video latent replay. Not a simulation of interaction. It is a real 3D world with physics, logic, and authoritative multiplayer state. Avalon is trained on proprietary Avalon interaction data and powered by a hybrid system that combines language understanding, 3D model generation, procedural systems, and structured gameplay logic synthesis. Players can walk through a live world and generate environments, assets, mechanics, and entirely new gameplay modes using natural language. We accomplish this through a combination of 3D model generation, game logic generation based on our proprietary systems, and AI driven world creation. While other players are inside it. Changes persist instantly. State is synchronized in real time. Creation happens inside the world, not outside of it. Describe a biome. Spawn a civilization. Create a survival mode. Build a dungeon crawler. Launch a new game inside the world. Avalon interprets intent and integrates it directly into the live multiplayer environment. This is not a world model predicting video. This is a gameplay engine that understands language. If you can describe it, you can build it. And others can walk into it instantly.

AVALON

66,133 просмотров • 8 месяцев назад

You don't need to be a 3D artist to start building 3D websites anymore 💛 Built this cool 3D jet drone website in Three.js using Claude Opus 5 and Tripo in < 1 hour. A lot of people still think AI is great for generating code, but not for building something that actually feels polished and interactive or "complex". But it has been changing super fast these days. The model you see here is only 946KB, compressed from its original 13.6MB size automatically by Claude without losing any quality. This kind of intelligence has been developed in many other AI tools for anything related to 3D (except GPT 5.6 sol lol). You just have to describe what you want and they handle everything "engineerly" (that's not even a word but okay :D) Anyway, also you don't really have to learn anything about 3D modeling to create these models. All you need is a good image and put it in Tripo. For this case, i generated model using "smart mesh" feature that generated a cleaner low-poly topology and edge flow. That helps keep your actual 3D asset even more lightweight. Earlier, with HD model feature, my model size with 8k texture was around 60-70MB but with Smart Mesh, it's around 13-16MB with 8k texture applied separately. Of course, this isn't something I knew from the beginning. All I did was "try" out different features and see what happens. Live: Code: Design:
0:27

You don't need to be a 3D artist to start building 3D websites anymore 💛 Built this cool 3D jet drone website in Three.js using Claude Opus 5 and Tripo in < 1 hour. A lot of people still think AI is great for generating code, but not for building something that actually feels polished and interactive or "complex". But it has been changing super fast these days. The model you see here is only 946KB, compressed from its original 13.6MB size automatically by Claude without losing any quality. This kind of intelligence has been developed in many other AI tools for anything related to 3D (except GPT 5.6 sol lol). You just have to describe what you want and they handle everything "engineerly" (that's not even a word but okay :D) Anyway, also you don't really have to learn anything about 3D modeling to create these models. All you need is a good image and put it in Tripo. For this case, i generated model using "smart mesh" feature that generated a cleaner low-poly topology and edge flow. That helps keep your actual 3D asset even more lightweight. Earlier, with HD model feature, my model size with 8k texture was around 60-70MB but with Smart Mesh, it's around 13-16MB with 8k texture applied separately. Of course, this isn't something I knew from the beginning. All I did was "try" out different features and see what happens. Live: Code: Design:

The Bugged Dev

51,558 просмотров • 1 месяц назад

Introducing the "Geo Method" - A way of filmmaking that tethers AI video to something physically real, and unmistakably human. Our method bridges traditional cinema and the incredibly impressive AI future. "Geo" represents earth, ground, geometry, location. How it works: we build scenes and sets as physical miniatures, hand-crafted, lit, and shot practical on cinema cameras and lenses. That footage becomes our source plate: a live-action anchor with real light, real depth, and real texture that brings unmatched intention and direction to the generative AI process. Then, inside our proprietary software ("ST00DIO"), we bring the plate to life with additional elements. Our mixture of original 3D models and AI-generated assets are integrated into the scene, giving us greater control over performance and animation, directed by humans. AI handles relighting, asset-based set extensions, and atmosphere, but the world itself is born from photographic live action. The final piece is our "Shot Composer" tool for micro adjustments if needed, or entirely new scene framing. From a single still frame from the miniature capture source plate, it generates procedural geometry and a matching, fully directable virtual camera. From there, if we desire, we can further direct the shot with precise control: camera moves that were never physically possible on the practical tabletop, specific composition rebuilds, and explicit blocking for animated characters, then render the new result against the original live-action plate (video). What you get is a true hybrid production for AI animation: the grounded realism of practical miniatures with the creative freedom and speed of AI. The scene is real. The camera becomes editable. The visual effects are picture-perfect. The storytelling is human-led. The Geo Method. Developed at m00m Studios (m00m 🛰) by Jordan Freda and Ben Lam.
2:19

Introducing the "Geo Method" - A way of filmmaking that tethers AI video to something physically real, and unmistakably human. Our method bridges traditional cinema and the incredibly impressive AI future. "Geo" represents earth, ground, geometry, location. How it works: we build scenes and sets as physical miniatures, hand-crafted, lit, and shot practical on cinema cameras and lenses. That footage becomes our source plate: a live-action anchor with real light, real depth, and real texture that brings unmatched intention and direction to the generative AI process. Then, inside our proprietary software ("ST00DIO"), we bring the plate to life with additional elements. Our mixture of original 3D models and AI-generated assets are integrated into the scene, giving us greater control over performance and animation, directed by humans. AI handles relighting, asset-based set extensions, and atmosphere, but the world itself is born from photographic live action. The final piece is our "Shot Composer" tool for micro adjustments if needed, or entirely new scene framing. From a single still frame from the miniature capture source plate, it generates procedural geometry and a matching, fully directable virtual camera. From there, if we desire, we can further direct the shot with precise control: camera moves that were never physically possible on the practical tabletop, specific composition rebuilds, and explicit blocking for animated characters, then render the new result against the original live-action plate (video). What you get is a true hybrid production for AI animation: the grounded realism of practical miniatures with the creative freedom and speed of AI. The scene is real. The camera becomes editable. The visual effects are picture-perfect. The storytelling is human-led. The Geo Method. Developed at m00m Studios (m00m 🛰) by Jordan Freda and Ben Lam.

Jordan 🛰️ Freda

121,139 просмотров • 16 дней назад

A really impressive set of Three.js graphics experiments just got open sourced, and these are much more than little visual demos. They are basically reusable procedural systems for oceans, vegetation, fluids and even whole planets. 🔹 Poseidon A real-time FFT ocean running on WebGPU. It simulates large swells, smaller ripples, foam, reflections, choppy displacement and physically inspired wave spectra entirely in the browser. 🔹 Gaia A procedural grass generator where every blade, seed head and field comes from a deterministic genome and environmental parameters. No authored grass models. 🔹 Dryad A procedural flora system that generates trees and other plant forms from physics, environmental conditions and a seed. No authored 3D models or textures are needed for the plants themselves. 🔹 Tiamat A real-time GPU fluid simulation using around 100,000 SPH particles, with the resulting water rendered directly in the browser. 🔹 Demiurge Probably the craziest one. It procedurally builds an entire planet from tectonic plates, then lets uplift drive erosion, erosion and latitude drive climate, and climate drive biomes, wind and weather. You can move seamlessly from orbit down to the surface. What I really like here is that these are not just pretty outputs. They are actual building blocks. Ocean simulation, vegetation generation, fluid dynamics and procedural worlds are exactly the kinds of systems that can be plugged into games, simulations and agent-built 3D environments. Project by: Owen
1:17

A really impressive set of Three.js graphics experiments just got open sourced, and these are much more than little visual demos. They are basically reusable procedural systems for oceans, vegetation, fluids and even whole planets. 🔹 Poseidon A real-time FFT ocean running on WebGPU. It simulates large swells, smaller ripples, foam, reflections, choppy displacement and physically inspired wave spectra entirely in the browser. 🔹 Gaia A procedural grass generator where every blade, seed head and field comes from a deterministic genome and environmental parameters. No authored grass models. 🔹 Dryad A procedural flora system that generates trees and other plant forms from physics, environmental conditions and a seed. No authored 3D models or textures are needed for the plants themselves. 🔹 Tiamat A real-time GPU fluid simulation using around 100,000 SPH particles, with the resulting water rendered directly in the browser. 🔹 Demiurge Probably the craziest one. It procedurally builds an entire planet from tectonic plates, then lets uplift drive erosion, erosion and latitude drive climate, and climate drive biomes, wind and weather. You can move seamlessly from orbit down to the surface. What I really like here is that these are not just pretty outputs. They are actual building blocks. Ocean simulation, vegetation generation, fluid dynamics and procedural worlds are exactly the kinds of systems that can be plugged into games, simulations and agent-built 3D environments. Project by: Owen

Token Gremlin

34,448 просмотров • 1 месяц назад

We are going big this year and into next! 2026 will be a Radiant year. The Radiant community is thrilled to announce the release of TWO MAJOR open-source projects that showcase the power of collaborative development: Radiant-Core Node! RXinDexer! 1. Radiant-Core Node 2.0-Project Phoenix Our next-generation blockchain node implementation! 🔗 -Built with modern C++20, Radiant-Core represents a significant evolution in our blockchain infrastructure: -Enhanced Performance: Support for transactions up to 12 MB with ~81,000 inputs. -Developer-Friendly: Native Prometheus metrics endpoint for easy monitoring. -Flexible Configuration: Node profiles from the system design paper (archive/agent/mining) for different use cases. -Glyph Token Swap Protocol Upgrades: **On-chain** broadcasted atomic swaps via PSRT. The classic advertised swaps will still work but this ushers in a whole new era for DEX and atomic swaps on-chain. -Cross-Platform: Docker-based CI for consistent builds across Linux, macOS, and Windows. -Available soon on testnet and aiming for mainnet activation by block 400k. 2. RXinDexer - Blockchain indexer for RXD and Glyphs 🔗 -A powerful Python-based indexing solution that enables developers to efficiently query and track Radiant blockchain data and Glyph assets. These releases embody our commitment to transparent, community-driven development. Open source isn't just about code—it's about empowering developers worldwide to: ✅ Contribute improvements and innovations ✅ Audit security and verify integrity ✅ Build complementary tools and services ✅ Learn from production-grade blockchain implementations Get Involved! Whether you're a seasoned blockchain developer or just getting started, your contributions matter. Check out the repositories, review the documentation, submit issues, or contribute code. You are the Proof of Work! And together, we're building the future of decentralized digital value transfer and sound money with no trusted third parties. The way Satoshi intended. The future is Radiant!
2:41

We are going big this year and into next! 2026 will be a Radiant year. The Radiant community is thrilled to announce the release of TWO MAJOR open-source projects that showcase the power of collaborative development: Radiant-Core Node! RXinDexer! 1. Radiant-Core Node 2.0-Project Phoenix Our next-generation blockchain node implementation! 🔗 -Built with modern C++20, Radiant-Core represents a significant evolution in our blockchain infrastructure: -Enhanced Performance: Support for transactions up to 12 MB with ~81,000 inputs. -Developer-Friendly: Native Prometheus metrics endpoint for easy monitoring. -Flexible Configuration: Node profiles from the system design paper (archive/agent/mining) for different use cases. -Glyph Token Swap Protocol Upgrades: **On-chain** broadcasted atomic swaps via PSRT. The classic advertised swaps will still work but this ushers in a whole new era for DEX and atomic swaps on-chain. -Cross-Platform: Docker-based CI for consistent builds across Linux, macOS, and Windows. -Available soon on testnet and aiming for mainnet activation by block 400k. 2. RXinDexer - Blockchain indexer for RXD and Glyphs 🔗 -A powerful Python-based indexing solution that enables developers to efficiently query and track Radiant blockchain data and Glyph assets. These releases embody our commitment to transparent, community-driven development. Open source isn't just about code—it's about empowering developers worldwide to: ✅ Contribute improvements and innovations ✅ Audit security and verify integrity ✅ Build complementary tools and services ✅ Learn from production-grade blockchain implementations Get Involved! Whether you're a seasoned blockchain developer or just getting started, your contributions matter. Check out the repositories, review the documentation, submit issues, or contribute code. You are the Proof of Work! And together, we're building the future of decentralized digital value transfer and sound money with no trusted third parties. The way Satoshi intended. The future is Radiant!

Radiant Blockchain

41,416 просмотров • 9 месяцев назад

Probably I vibe coded a lil startup here? 😭 It has been such a loooong wish of mine to build some kind of 3D experience where I could customize a T-shirt in literally any way possible and it’s finally here. Built with Three.js using GPT 6 Astra, this is a full 3D T-shirt customization studio where you can visualize and customize a realistic shirt directly in the browser. That T-shirt itself was modeled by Astra using Tripo right inside Codex through Tripo Plugin. And you can pretty much do anything with it. You can paint directly on any side of the shirt using different brushes and colors, or even spray paint it in real time just like you would spray on a wall. There are also stickers generated using GPT Image 2.5 that you can place anywhere on the T-shirt, resize, reposition, recolor, layer, and customize however you want. On top of that, there’s support for things like fabric customization, sizing, layers, colors, and even wind simulation to push the realism a little further. Once you’re done, you can export the entire design as a 3D view or export individual images of the T-shirt so you could technically take the design, print it, and maybe even sell it. One of my favorite parts is how the spray painting effect works directly on the 3D T-shirt in real time. I also loved seeing how Astra managed to keep the whole experience performant across devices using a custom BVH implementation along with several CPU side optimizations. And the process of building it was super simple. I generated the initial studio design using GPT Image 2.5, gave that image to Astra with the Tripo Plugin enabled, and it basically handled everything from there. I didn’t have to separately generate a 3D reference, upload it to Tripo, download the asset, give it back to Astra, or manually coordinate any of that. Astra handled the entire flow on its own without needing any additional input from me. Really happy with both the process and how the final result turned out. Live:
1:04

Probably I vibe coded a lil startup here? 😭 It has been such a loooong wish of mine to build some kind of 3D experience where I could customize a T-shirt in literally any way possible and it’s finally here. Built with Three.js using GPT 6 Astra, this is a full 3D T-shirt customization studio where you can visualize and customize a realistic shirt directly in the browser. That T-shirt itself was modeled by Astra using Tripo right inside Codex through Tripo Plugin. And you can pretty much do anything with it. You can paint directly on any side of the shirt using different brushes and colors, or even spray paint it in real time just like you would spray on a wall. There are also stickers generated using GPT Image 2.5 that you can place anywhere on the T-shirt, resize, reposition, recolor, layer, and customize however you want. On top of that, there’s support for things like fabric customization, sizing, layers, colors, and even wind simulation to push the realism a little further. Once you’re done, you can export the entire design as a 3D view or export individual images of the T-shirt so you could technically take the design, print it, and maybe even sell it. One of my favorite parts is how the spray painting effect works directly on the 3D T-shirt in real time. I also loved seeing how Astra managed to keep the whole experience performant across devices using a custom BVH implementation along with several CPU side optimizations. And the process of building it was super simple. I generated the initial studio design using GPT Image 2.5, gave that image to Astra with the Tripo Plugin enabled, and it basically handled everything from there. I didn’t have to separately generate a 3D reference, upload it to Tripo, download the asset, give it back to Astra, or manually coordinate any of that. Astra handled the entire flow on its own without needing any additional input from me. Really happy with both the process and how the final result turned out. Live:

The Bugged Dev

52,858 просмотров • 1 месяц назад

"Hah - generative ai can't even make an image of a hand with the right number of fingers.." "Stop pushing this slop" It's way past the point now where it must be clear to everyone, that generative ai is here to stay AND that the quality will continue to increase. I've been talking about this trajectory for years now, and I've been working towards finding ways to combine the strength of these models, with the best of what I love about "old-school" creation. Building with my hands, moving a pencil across the paper and seeing shapes emerge, moving a building slightly to the right to get just that composition I had in mind. Being fully immersed in a scene I'm building in VR, being inspired by the immersion to take the story in a new direction. For years I've been talking about how powerful the combination of 3d and generative ai is, be it traditional 3d, SDF volumes in Dreams or Gaussian splats - with experiments around using V2V as a "render pass" or with experiments around realtime ai. Enough talk you might think, where's the proof? It's all around us these days honestly and here's a small test I did during some OOO. Blender MPC + Fable - a pretty powerful combination! With a bit of Google Omni Fast on top as a "render" pass. What do you think of where this is heading? Hopeful, disheartened, inspired or the opposite? Can you imagine working with tools like this in a way where we still retain the human "spark" and the creative nerve that makes each persons creation unique?
0:25

"Hah - generative ai can't even make an image of a hand with the right number of fingers.." "Stop pushing this slop" It's way past the point now where it must be clear to everyone, that generative ai is here to stay AND that the quality will continue to increase. I've been talking about this trajectory for years now, and I've been working towards finding ways to combine the strength of these models, with the best of what I love about "old-school" creation. Building with my hands, moving a pencil across the paper and seeing shapes emerge, moving a building slightly to the right to get just that composition I had in mind. Being fully immersed in a scene I'm building in VR, being inspired by the immersion to take the story in a new direction. For years I've been talking about how powerful the combination of 3d and generative ai is, be it traditional 3d, SDF volumes in Dreams or Gaussian splats - with experiments around using V2V as a "render pass" or with experiments around realtime ai. Enough talk you might think, where's the proof? It's all around us these days honestly and here's a small test I did during some OOO. Blender MPC + Fable - a pretty powerful combination! With a bit of Google Omni Fast on top as a "render" pass. What do you think of where this is heading? Hopeful, disheartened, inspired or the opposite? Can you imagine working with tools like this in a way where we still retain the human "spark" and the creative nerve that makes each persons creation unique?

Martin Nebelong

49,689 просмотров • 2 месяцев назад

In 2026, AI world models will take the spotlight in storytelling - powering new types of interactive experiences & digital economies not seen before World models are progressing rapidly - Marble World Labs and Genie 3 Google DeepMind already generate 3D environments from text prompts, allowing users to explore them as if they were video games As creators adopt these tools, new storytelling formats will emerge. One genre I'm excited about is "generative Minecraft" - where players co-create virtual worlds together by vibe coding with world models. Game mechanics could be programmable with natural language - ex. "create a paintbrush that changes the color of anything I touch to pink" World models will also likely give rise to not just a single game, but an entire new category of generative world experiences - you could have a horror experience where you’re hiding from generated monsters, or a D&D experience where you’re roaming an infinite fantasy world with friends And with a common base model for the underlying worlds, these experiences could be inter-connected in a multiverse we could only dream about previously in science fiction A key affordance here is the role of consumers as co-creators - you can wander the multiverse as a tourist, or break out your pickaxe and become a creator anytime. This in turn would give rise to new digital economies - with creators making a living building and selling interoperable assets, serving as a guide for new players, etc The opportunity is enormous - a new category of generative worlds would not only create a new storytelling medium unlike any we’ve seen before, but also be rich training grounds for agents, robotics, and AGI If you’re excited about building new interactive experiences or the virtual economy stack with world models - we’d love to hear from you!
2:18

In 2026, AI world models will take the spotlight in storytelling - powering new types of interactive experiences & digital economies not seen before World models are progressing rapidly - Marble World Labs and Genie 3 Google DeepMind already generate 3D environments from text prompts, allowing users to explore them as if they were video games As creators adopt these tools, new storytelling formats will emerge. One genre I'm excited about is "generative Minecraft" - where players co-create virtual worlds together by vibe coding with world models. Game mechanics could be programmable with natural language - ex. "create a paintbrush that changes the color of anything I touch to pink" World models will also likely give rise to not just a single game, but an entire new category of generative world experiences - you could have a horror experience where you’re hiding from generated monsters, or a D&D experience where you’re roaming an infinite fantasy world with friends And with a common base model for the underlying worlds, these experiences could be inter-connected in a multiverse we could only dream about previously in science fiction A key affordance here is the role of consumers as co-creators - you can wander the multiverse as a tourist, or break out your pickaxe and become a creator anytime. This in turn would give rise to new digital economies - with creators making a living building and selling interoperable assets, serving as a guide for new players, etc The opportunity is enormous - a new category of generative worlds would not only create a new storytelling medium unlike any we’ve seen before, but also be rich training grounds for agents, robotics, and AGI If you’re excited about building new interactive experiences or the virtual economy stack with world models - we’d love to hear from you!

Jon Lai

29,871 просмотров • 10 месяцев назад

Today I'm excited to share Sigilum! This is Payman's solution for Auditable Identity for AI Agents. (think One Password-ish but for AI Agents) I recorded a quick walkthrough showing how it all works (video below). This answers three pains we've seen within Financial Services (Banking) AI Agents we've built and OpenClaw🦞 AI Agents we deploy. Security, Auditability, and Control. 1. Security Making sure keys are secure and not just freely given to an AI Agent is a big deal. When working with money, you can't just expose these or skip putting controls in place. Sigilum provides a local gateway that prevents access to keys by the AI Agent without explicit authorization from a person. We provide namespaces through the service so you always know who authorized what key, for what service, to which agent. 2. Auditability If I could hit on the importance of this 100 times I would. It comes up in every financial services conversation. Sigilum provides you with the answer to "Who authorized this AI Agent to act on my behalf?" Audit logs trace back to the person, the service, and the AI Agent. With more audit logs being built through our managed service, this will be the key source for determining how an AI Agent is behaving on your behalf. This is needed for agents from OpenClaw, and especially for banking/money movement. 3. Control Revoke keys, limit access, grant authorization. All seemingly simple things, but complex to implement and make elegant. These controls dictate what the AI Agent can or cannot do. Sigilum allows you to do all of this through the managed Dashboard. We've made Sigilum open source and encourage others to contribute and keep building on the gateway. It's been a source of a lot of visibility and productization of AI Agents for us. We'll keep contributing and adding to it. Link in comments. If you want to try it out, we do have a managed service that makes it easy to spin up. Go to to sign up. Note: even though we've been pushing 100+ commits a day to get this out to folks, there are still some noticeable areas for improvement we're working on, which should get resolved soon (by us or you!): - Deeper audit trails - More providers (currently supports all OpenClaw providers) - Deeper scanning of existing keys your agent is hiding from you (we'll find them) - OpenClaw gateway persistence - Auto-purging keys - And more... If you want to contribute or have feedback, please DM or go to the GH. Happy building!
4:30

Today I'm excited to share Sigilum! This is Payman's solution for Auditable Identity for AI Agents. (think One Password-ish but for AI Agents) I recorded a quick walkthrough showing how it all works (video below). This answers three pains we've seen within Financial Services (Banking) AI Agents we've built and OpenClaw🦞 AI Agents we deploy. Security, Auditability, and Control. 1. Security Making sure keys are secure and not just freely given to an AI Agent is a big deal. When working with money, you can't just expose these or skip putting controls in place. Sigilum provides a local gateway that prevents access to keys by the AI Agent without explicit authorization from a person. We provide namespaces through the service so you always know who authorized what key, for what service, to which agent. 2. Auditability If I could hit on the importance of this 100 times I would. It comes up in every financial services conversation. Sigilum provides you with the answer to "Who authorized this AI Agent to act on my behalf?" Audit logs trace back to the person, the service, and the AI Agent. With more audit logs being built through our managed service, this will be the key source for determining how an AI Agent is behaving on your behalf. This is needed for agents from OpenClaw, and especially for banking/money movement. 3. Control Revoke keys, limit access, grant authorization. All seemingly simple things, but complex to implement and make elegant. These controls dictate what the AI Agent can or cannot do. Sigilum allows you to do all of this through the managed Dashboard. We've made Sigilum open source and encourage others to contribute and keep building on the gateway. It's been a source of a lot of visibility and productization of AI Agents for us. We'll keep contributing and adding to it. Link in comments. If you want to try it out, we do have a managed service that makes it easy to spin up. Go to to sign up. Note: even though we've been pushing 100+ commits a day to get this out to folks, there are still some noticeable areas for improvement we're working on, which should get resolved soon (by us or you!): - Deeper audit trails - More providers (currently supports all OpenClaw providers) - Deeper scanning of existing keys your agent is hiding from you (we'll find them) - OpenClaw gateway persistence - Auto-purging keys - And more... If you want to contribute or have feedback, please DM or go to the GH. Happy building!

tyllen

18,497 просмотров • 7 месяцев назад

So these researchers figured out you can basically hallucinate 3D cities into existence using just satellite photos & a diffusion model. The problem's pretty straightforward: satellites only see rooftops. Building facades? Invisible. Street-level detail? Doesn't exist. But people want flyable 3D environments, which means you need all that occluded geometry. When I worked on google maps photogrammetry, we could only use satellite-based 3D for isolated stuff like the pyramids - anything city-scale required airplane flyovers. Which is fine until you hit aerial-denied regions where you literally can't fly. Huge chunks of the world just unavailable. Their trick is honestly kind of beautiful. They train gaussian splats on satellite views, but as it descends toward ground level, the renders turn to absolute garbage - artifacts everywhere. Instead of fighting this, they just treat those nightmare renders as the input to a diffusion model. Basically - "hey FLUX, fix this mess." Then here's where it gets clever: they generate multiple diffusion samples per view instead of committing to one. Because any single denoising path is probably wrong in 3D space, but if you generate a couple and let the GS optimization find consensus across them, you get actual geometric consistency. They do this in episodes, curriculum style - start high, gradually descend (hence the name Skyfall-GS!). With each iteration the ground-level views get less fucked. By the end you've got real-time flyable cities that look surprisingly real, and the geometry still matches the satellite input. No 3D training data. No street-level photos. Just satellites + diffusion doing what it does best - filling in the blanks. It's like neural scene completion but actually practical, and it unlocks basically the entire world.
0:29

So these researchers figured out you can basically hallucinate 3D cities into existence using just satellite photos & a diffusion model. The problem's pretty straightforward: satellites only see rooftops. Building facades? Invisible. Street-level detail? Doesn't exist. But people want flyable 3D environments, which means you need all that occluded geometry. When I worked on google maps photogrammetry, we could only use satellite-based 3D for isolated stuff like the pyramids - anything city-scale required airplane flyovers. Which is fine until you hit aerial-denied regions where you literally can't fly. Huge chunks of the world just unavailable. Their trick is honestly kind of beautiful. They train gaussian splats on satellite views, but as it descends toward ground level, the renders turn to absolute garbage - artifacts everywhere. Instead of fighting this, they just treat those nightmare renders as the input to a diffusion model. Basically - "hey FLUX, fix this mess." Then here's where it gets clever: they generate multiple diffusion samples per view instead of committing to one. Because any single denoising path is probably wrong in 3D space, but if you generate a couple and let the GS optimization find consensus across them, you get actual geometric consistency. They do this in episodes, curriculum style - start high, gradually descend (hence the name Skyfall-GS!). With each iteration the ground-level views get less fucked. By the end you've got real-time flyable cities that look surprisingly real, and the geometry still matches the satellite input. No 3D training data. No street-level photos. Just satellites + diffusion doing what it does best - filling in the blanks. It's like neural scene completion but actually practical, and it unlocks basically the entire world.

Bilawal Sidhu

242,039 просмотров • 11 месяцев назад

Sora 2 + n8n is an absolute cheat code for AI UGC 🤯 One Airtable form generates multiple videos with the exact same AI creator. Same face, same vibe. Every single clip. All inside n8n + Airtable. Perfect for DTC brands and agencies who need consistent AI creators across entire ad campaigns. You're trying to test 10 different hooks with the same AI "creator", but every time you prompt Sora 2 manually, you get a different person in every video. And even when you nail consistency, you're still downloading, organizing, and tracking everything by hand. This n8n automation handles all of it: → Fill out one Airtable form (character, scene, video count) → Claude auto-generates detailed Sora 2 prompts → Sora 2 creates videos with your consistent character cameo → Videos auto-upload to ImageKit → Everything lands in Airtable with shareable URLs No Frankenstein characters, manual prompting, or file management nightmare. What you get: > Multiple videos with the exact same AI creator > UGC-style formatting (selfie angles, natural delivery) > Full status tracking in Airtable (queued → generating → complete) > Production-ready clips in minutes Built 100% in n8n + Airtable. Want the full workflow for free? > Like this post > Comment "SORA" And I'll send it over (must be following so I can DM)
0:22

Sora 2 + n8n is an absolute cheat code for AI UGC 🤯 One Airtable form generates multiple videos with the exact same AI creator. Same face, same vibe. Every single clip. All inside n8n + Airtable. Perfect for DTC brands and agencies who need consistent AI creators across entire ad campaigns. You're trying to test 10 different hooks with the same AI "creator", but every time you prompt Sora 2 manually, you get a different person in every video. And even when you nail consistency, you're still downloading, organizing, and tracking everything by hand. This n8n automation handles all of it: → Fill out one Airtable form (character, scene, video count) → Claude auto-generates detailed Sora 2 prompts → Sora 2 creates videos with your consistent character cameo → Videos auto-upload to ImageKit → Everything lands in Airtable with shareable URLs No Frankenstein characters, manual prompting, or file management nightmare. What you get: > Multiple videos with the exact same AI creator > UGC-style formatting (selfie angles, natural delivery) > Full status tracking in Airtable (queued → generating → complete) > Production-ready clips in minutes Built 100% in n8n + Airtable. Want the full workflow for free? > Like this post > Comment "SORA" And I'll send it over (must be following so I can DM)

Mike Futia

12,174 просмотров • 8 месяцев назад