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.

Astra built this three.js game with gorgeous graphics, then recreated every scene in Blender and made the trailer too. It feels like a massive upgrade from Sol for 3D graphics and front-end design. The UI feels way more polished and less like AI slop. The rocks, trees, monuments, and... show more

Meng To

185,513 subscribers

132,023 views • 6 days ago •via X (Twitter)

Science & Technology Gaming

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Vibe coding a game character selection screen | Part 2 Tried a new set of characters and the level of detail is wild. Everything here was made with AI tools Nano Banana: character design + UI Tencent Hunyuan3D: image to 3D Gemini Pro: UI Tips ↓

Vibe coding a game character selection screen | Part 2 Tried a new set of characters and the level of detail is wild. Everything here was made with AI tools Nano Banana: character design + UI Tencent Hunyuan3D: image to 3D Gemini Pro: UI Tips ↓

Dilum Sanjaya

45,588 views • 8 months ago

Players told us: interactive video stories feel more immersive with game-like UI. So we built it. Yoroll now auto-generates contextual Game UI for your video scenes — powered by GPT Image 2. It reads your story, matches the vibe, and overlays the right interface. No design work. Just more immersion. See it in action 👇

Players told us: interactive video stories feel more immersive with game-like UI. So we built it. Yoroll now auto-generates contextual Game UI for your video scenes — powered by GPT Image 2. It reads your story, matches the vibe, and overlays the right interface. No design work. Just more immersion. See it in action 👇

Yoroll

68,091 views • 4 months ago

I asked Astra to create a Catan game in three.js and it came out incredibly well. I played it, and the animations make it so much fun. The instructions and info cards make the game easy to learn. It even has AI players and trading. Astra used another game I had started building as a reference. The more games I build, the more skills and assets I have for the next one. It can remix the UI, 3D models, pages, and sounds instead of rebuilding everything. Now I want to see how many other board games I can make from this foundation.

I asked Astra to create a Catan game in three.js and it came out incredibly well. I played it, and the animations make it so much fun. The instructions and info cards make the game easy to learn. It even has AI players and trading. Astra used another game I had started building as a reference. The more games I build, the more skills and assets I have for the next one. It can remix the UI, 3D models, pages, and sounds instead of rebuilding everything. Now I want to see how many other board games I can make from this foundation.

Meng To

566,205 views • 3 days ago

well, i connected GPT-5.6 Sol to Blender and... let's just say the world of 3D graphics (at least via Blender's MCP) is safe for now... but still... this whole scene was generated by GPT-5.6 with very little human intervention feels like *EARLY* pixar, like too early lol

well, i connected GPT-5.6 Sol to Blender and... let's just say the world of 3D graphics (at least via Blender's MCP) is safe for now... but still... this whole scene was generated by GPT-5.6 with very little human intervention feels like EARLY pixar, like too early lol

Gavin Purcell

71,438 views • 2 months ago

GPT Image 2 + Codex: or how to make Codex not suck at UI. Step 1: Generate a UI image (native in Codex) Step 2: Get Codex to implement the UI based on it Step 3: Get Codex to iterate until it aligns with the image as much as possible Codex is bad at initial UI, but very good at implementing a reference design, so this is your way out - iterate with the image model first and then Codex will do a good job.

GPT Image 2 + Codex: or how to make Codex not suck at UI. Step 1: Generate a UI image (native in Codex) Step 2: Get Codex to implement the UI based on it Step 3: Get Codex to iterate until it aligns with the image as much as possible Codex is bad at initial UI, but very good at implementing a reference design, so this is your way out - iterate with the image model first and then Codex will do a good job.

Peter Gostev

67,245 views • 4 months ago

Day 9. Building the game I've dreamed of for 15 years with AI. I'm still in shock from GPT-6. Today I handed it my game's UI. I'd started working on it last week with Fable 5.1 and design skills. I built it in HTML first, preparing the images and icons along the way. Figuring out what I wanted and how it should work took time. I needed that time. I also made animated character portraits. I tried Seedance 2.5 for those, and MiniMax H3 gave me much better results for this job. By the end, I had an interactive prototype with the UI logic worked out and all the assets ready. I could click through it and test how everything behaved before taking it into the game. Once I'd tested it and worked through the remaining questions, I opened GPT-6 in the same project. Gave it the interface and all the materials, and asked it to implement everything in Unity. About two hours later, I had a working UI and nothing to complain about. GPT-6 even went through different resolutions on its own. I'd expected this part to be difficult. It ended up being one of the easiest parts so far. I'd recommend building your UI in HTML first. Iterations are faster, you can click through it just like a real interface, and it's easier to catch the things you missed. Once you've worked those out, connect it to the game. You still have to wait for the engine to compile, whether you write the code yourself or use AI.

Day 9. Building the game I've dreamed of for 15 years with AI. I'm still in shock from GPT-6. Today I handed it my game's UI. I'd started working on it last week with Fable 5.1 and design skills. I built it in HTML first, preparing the images and icons along the way. Figuring out what I wanted and how it should work took time. I needed that time. I also made animated character portraits. I tried Seedance 2.5 for those, and MiniMax H3 gave me much better results for this job. By the end, I had an interactive prototype with the UI logic worked out and all the assets ready. I could click through it and test how everything behaved before taking it into the game. Once I'd tested it and worked through the remaining questions, I opened GPT-6 in the same project. Gave it the interface and all the materials, and asked it to implement everything in Unity. About two hours later, I had a working UI and nothing to complain about. GPT-6 even went through different resolutions on its own. I'd expected this part to be difficult. It ended up being one of the easiest parts so far. I'd recommend building your UI in HTML first. Iterations are faster, you can click through it just like a real interface, and it's easier to catch the things you missed. Once you've worked those out, connect it to the game. You still have to wait for the engine to compile, whether you write the code yourself or use AI.

Stefan 3D AI

155,912 views • 1 day ago

GPT Image 2 is actually insane I made this video with the images from it and it looks so much better than NBP but imo NBP is still way better GPT was a pain in the arse to work with >Constant NSFW tags (on gym pics) >Cant create backgrounds like NBP >Cant swap characters as good as NBP >Less consistent So yeh I’ll be sticking with NBP for now Im going to test making the back grounds and character swaps in NBP then changing them to higher quality with GPT though

GPT Image 2 is actually insane I made this video with the images from it and it looks so much better than NBP but imo NBP is still way better GPT was a pain in the arse to work with >Constant NSFW tags (on gym pics) >Cant create backgrounds like NBP >Cant swap characters as good as NBP >Less consistent So yeh I’ll be sticking with NBP for now Im going to test making the back grounds and character swaps in NBP then changing them to higher quality with GPT though

Pounds

42,082 views • 4 months ago

Someone vibe coded a fully interactive 3D human anatomy app using GPT-5.6 Sol and Codex, and it started from a single design image. GPT Image 2.0 generated the design. Every organ image was generated from it and converted to 3D models through Tripo AI. Codex took those models, a master prompt and the design image and built the first version. The models were nearly 150MB each and running at 16fps, so Codex optimized everything down to 2 to 5.5MB per model and reduced total assets from 900MB to 28.6MB while keeping the visual quality intact. Codex also generated the anatomical illustrations showing where each organ sits, and created the interactive hotspot markers explaining different parts of every organ. Live and fully open source.

Someone vibe coded a fully interactive 3D human anatomy app using GPT-5.6 Sol and Codex, and it started from a single design image. GPT Image 2.0 generated the design. Every organ image was generated from it and converted to 3D models through Tripo AI. Codex took those models, a master prompt and the design image and built the first version. The models were nearly 150MB each and running at 16fps, so Codex optimized everything down to 2 to 5.5MB per model and reduced total assets from 900MB to 28.6MB while keeping the visual quality intact. Codex also generated the anatomical illustrations showing where each organ sits, and created the interactive hotspot markers explaining different parts of every organ. Live and fully open source.

0xMarioNawfal

57,012 views • 1 month ago

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.

Tom Krcha

1,432,927 views • 8 days ago

I recreated the #ArcaneSeason2 Piltover Garden scene using #Blender. I roughly built a 3D scene, made a draft render, and then painted over it in 2D. All moving parts like foliage, characters and spinner are 3D elements. Breakdown coming soon. More info:

I recreated the #ArcaneSeason2 Piltover Garden scene using #Blender. I roughly built a 3D scene, made a draft render, and then painted over it in 2D. All moving parts like foliage, characters and spinner are 3D elements. Breakdown coming soon. More info:

trungduyng

34,849 views • 1 year ago

this is the wildest website i've seen so far, all made with ai (gpt-image-2 and seedance-2.0) and it changes on every refresh! unreal work, congrats Pear

this is the wildest website i've seen so far, all made with ai (gpt-image-2 and seedance-2.0) and it changes on every refresh! unreal work, congrats Pear

kyzo

391,993 views • 1 month ago

Here is a game that looks like it was made with 2D sprites on a tilemap But it’s actually a three.js scene Also, no external assets. It’s all code and a bit of shader magic The player can switch between the pixel view and the 3D scene Made with Opus 5

Here is a game that looks like it was made with 2D sprites on a tilemap But it’s actually a three.js scene Also, no external assets. It’s all code and a bit of shader magic The player can switch between the pixel view and the 3D scene Made with Opus 5

Dilum Sanjaya

53,670 views • 23 days ago

GPT-6 Astra just vibe-coded the Oval Office in 3D. We described the set design > GPT-6 Astra generated the scene code > Higgsfield built the location model in Blender and rendered it with Cycles. The whole pipeline ran end-to-end on Higgsfield Supercomputer.

GPT-6 Astra just vibe-coded the Oval Office in 3D. We described the set design > GPT-6 Astra generated the scene code > Higgsfield built the location model in Blender and rendered it with Cycles. The whole pipeline ran end-to-end on Higgsfield Supercomputer.

Higgsfield AI 🧩

1,230,509 views • 8 days ago

Fable 5.1 is an absolute beast for game dev. I took my Opus 5 space game and told Fable to "just make it look better". It overhauled everything with a TON of detail, AND made it 2x faster 🤯 Code: Demo: Every pixel you see is made by AI. Fable modeled everything in Blender, generated textures with code, and in a few cases ran image models via CLI. In mere months we'll be vibe-coding AAA graphics at this rate. Just insane. Of course, Fable recorded and edited this comparison video too (with a little help from Opus at the end, because of the Fable outage)

Fable 5.1 is an absolute beast for game dev. I took my Opus 5 space game and told Fable to "just make it look better". It overhauled everything with a TON of detail, AND made it 2x faster 🤯 Code: Demo: Every pixel you see is made by AI. Fable modeled everything in Blender, generated textures with code, and in a few cases ran image models via CLI. In mere months we'll be vibe-coding AAA graphics at this rate. Just insane. Of course, Fable recorded and edited this comparison video too (with a little help from Opus at the end, because of the Fable outage)

Anshu

48,983 views • 8 days ago

I recreated Townscaper with GPT-6 Astra using Three.js on Happycapy The result is surprisingly close to the original, and it took way less time than I expected 🤯 Astra is seriously good at this kind of 3D coding task.

I recreated Townscaper with GPT-6 Astra using Three.js on Happycapy The result is surprisingly close to the original, and it took way less time than I expected 🤯 Astra is seriously good at this kind of 3D coding task.

Min Zhou

10,482 views • 4 days ago

Only if education could be this interactive ❤️‍🔥 I've had a looong wish to build something genuinely useful through vibe coding, and I finally did it. A 3D human anatomy application built with Three.js using GPT 5.6 Sol. It all started with a single design image that I created using GPT Image 2.0. I then used it to generate every 3D organ image, one by one. Next, I converted each of those images into 3D models using Tripo (and no, they didn't sponsor this 😄). After that, I opened Codex, wrote a master prompt based on the design, and gave it the prompt, the design image, and all the 3D models. Codex built the first version beautifully, but there was one big problem. Every single 3D model was nearly 120-150 MB. That obviously wasn't practical for the web and was giving a performance of 16fps. After a few iterations, Codex optimized each model down to roughly 2–5.5 MB while preserving the visual quality, reducing the total asset size from ~900 MB to just 28.6 MB. And each model loads on demand. Along the way, Codex also generated those anatomical illustrations showing where each organ sits in the human body, and even created the interactive hotspot markers that explain different parts of every organ. It handled all of that. The process wasn't exactly one shot, but it also wasn't difficult. You just have to do it step by step. It genuinely felt like building something that could make learning anatomy much more engaging. The inspiration came from Dilum Sanjaya's 3D animal plant cell project. I remember seeing it and thinking, "I want to build something like this one day." And I did it :D Live: Code:

Only if education could be this interactive ❤️‍🔥 I've had a looong wish to build something genuinely useful through vibe coding, and I finally did it. A 3D human anatomy application built with Three.js using GPT 5.6 Sol. It all started with a single design image that I created using GPT Image 2.0. I then used it to generate every 3D organ image, one by one. Next, I converted each of those images into 3D models using Tripo (and no, they didn't sponsor this 😄). After that, I opened Codex, wrote a master prompt based on the design, and gave it the prompt, the design image, and all the 3D models. Codex built the first version beautifully, but there was one big problem. Every single 3D model was nearly 120-150 MB. That obviously wasn't practical for the web and was giving a performance of 16fps. After a few iterations, Codex optimized each model down to roughly 2–5.5 MB while preserving the visual quality, reducing the total asset size from ~900 MB to just 28.6 MB. And each model loads on demand. Along the way, Codex also generated those anatomical illustrations showing where each organ sits in the human body, and even created the interactive hotspot markers that explain different parts of every organ. It handled all of that. The process wasn't exactly one shot, but it also wasn't difficult. You just have to do it step by step. It genuinely felt like building something that could make learning anatomy much more engaging. The inspiration came from Dilum Sanjaya's 3D animal plant cell project. I remember seeing it and thinking, "I want to build something like this one day." And I did it :D Live: Code:

The Bugged Dev

2,095,226 views • 1 month ago

$This is running in a browser tab. No engine. No install. No download. Six spells, real-time particle simulation, refracting ice geometry, and a live VFX editor on the right side where every parameter is tunable while the scene runs. A studio VFX artist builds this in weeks. It is genuinely the hardest discipline in 3D - nothing about particle work is intuitive. The thing that changed is not that AI got better at art. It is that Astra writes geometry and shaders as CODE instead of as files. A game made of .fbx files is a game an AI can only rearrange. A game made of code is a game an AI can edit. That is why the good demos this week are all three.js and Blender-scripted, and why they run at 60fps in a tab. Dude built a full game this way and it came out under 2 MB before audio. Every rock, tree and character - procedural code, not assets. The cost consequence is the part almost nobody understood: → let the model CLICK in Blender: burns your weekly cap in two minutes → let the model WRITE Blender Python: ~100x cheaper One builder shipped a complete 3D roguelike level - day/night cycle, weather, modeling, texturing, enemies - for 3% of his quota. That is the entire reason why. Scripts, not clicks. It's the single rule that decides your bill. Full breakdown + the 7-day guide in the article below ↓$

This is running in a browser tab. No engine. No install. No download. Six spells, real-time particle simulation, refracting ice geometry, and a live VFX editor on the right side where every parameter is tunable while the scene runs. A studio VFX artist builds this in weeks. It is genuinely the hardest discipline in 3D - nothing about particle work is intuitive. The thing that changed is not that AI got better at art. It is that Astra writes geometry and shaders as CODE instead of as files. A game made of .fbx files is a game an AI can only rearrange. A game made of code is a game an AI can edit. That is why the good demos this week are all three.js and Blender-scripted, and why they run at 60fps in a tab. Dude built a full game this way and it came out under 2 MB before audio. Every rock, tree and character - procedural code, not assets. The cost consequence is the part almost nobody understood: → let the model CLICK in Blender: burns your weekly cap in two minutes → let the model WRITE Blender Python: ~100x cheaper One builder shipped a complete 3D roguelike level - day/night cycle, weather, modeling, texturing, enemies - for 3% of his quota. That is the entire reason why. Scripts, not clicks. It's the single rule that decides your bill. Full breakdown + the 7-day guide in the article below ↓

Aleiah

37,652 views • 5 days ago

Astra can create beautiful three.js UIs entirely in code. You don't need an assets library or MCP to create detailed 3D models. These are all code and are easy to customize for your agent. Give Astra a video, URL, or code reference, then ask it to keep comparing the result against the reference and fixing mistakes. Liquid Glass, shaders, motion design, procedural three.js models, and full environments. All from a few prompts. Some prompts I used: "Recreate this in a single HTML file with three.js. Keep comparing it against the reference and fix any differences." "Add Liquid Glass buttons. On hover, animate the lighting around the borders and make the background gradients move slightly with the pointer. Add subtle particles." "Improve the lighting, edges, and modeling. Give the keys more depth and verify the result against the real MacBook." Too many projects I could open-source. Let me know which one should I release.

Astra can create beautiful three.js UIs entirely in code. You don't need an assets library or MCP to create detailed 3D models. These are all code and are easy to customize for your agent. Give Astra a video, URL, or code reference, then ask it to keep comparing the result against the reference and fixing mistakes. Liquid Glass, shaders, motion design, procedural three.js models, and full environments. All from a few prompts. Some prompts I used: "Recreate this in a single HTML file with three.js. Keep comparing it against the reference and fix any differences." "Add Liquid Glass buttons. On hover, animate the lighting around the borders and make the background gradients move slightly with the pointer. Add subtle particles." "Improve the lighting, edges, and modeling. Give the keys more depth and verify the result against the real MacBook." Too many projects I could open-source. Let me know which one should I release.

Meng To

105,156 views • 5 days ago

GPT-6 Astra turned a single floor plan into a full 3D walkthrough. It reconstructed the layout in Blender, furnished every room, lit the scene with natural light, and rendered the tour with ray tracing. Made end to end on Higgsfield Supercomputer.

GPT-6 Astra turned a single floor plan into a full 3D walkthrough. It reconstructed the layout in Blender, furnished every room, lit the scene with natural light, and rendered the tour with ray tracing. Made end to end on Higgsfield Supercomputer.

Higgsfield AI 🧩

58,163 views • 8 days ago

I built a playable zombie game with MiniMax Code, then used its new H3 Skill to generate the opening cinematic. The result feels less like a coding demo and more like the start of an actual game. H3 handles the story sequence. MiniMax Code handles the game. All from the same workflow.

I built a playable zombie game with MiniMax Code, then used its new H3 Skill to generate the opening cinematic. The result feels less like a coding demo and more like the start of an actual game. H3 handles the story sequence. MiniMax Code handles the game. All from the same workflow.

Farhan

56,401 views • 12 days ago