正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

GPT-6 Astra + Three.js = Smoothly INTERACTIVE and AWESOME. Might not even need Blender, the stuff you can build on the web now is wild. Prompt⬇️ It cut my workflow from a couple of hours down to just 30 minutes!

padphone

6,924 subscribers

62,631 次观看 • 2 个月前 •via X (Twitter)

艺术科学技术教育

Anya Rossi• Live Now

Private livecam show

32 条评论

padphone 的头像

padphone2 个月前

Web Three.js prompt: Create an elegant, responsive webpage featuring an interactive 3D peacock with grainy, painterly materials, deep teal plumage, muted gold details, and a warm ivory background. Use refined serif typography on a transparent foreground layer. Keep the Chinese logo “羽间” and offer Chinese/English switching. Render the peacock in a full-viewport Three.js scene behind the typography, with generous horizontal movement and depth. Mouse movement guides its walking direction; its head, body, and folded tail turn coherently. Hovering makes it shake its head and gradually spread its feathers. Moving away closes the fan. Animate real geometry without crossfading between poses. Scrolling down brings the peacock toward the camera, where it delivers energetic pecks. Scrolling up sends it backward. Pressing Space triggers a physically convincing jump and landing. Clicking individual feathers detaches them with a gentle falling motion. The peacock approaches, bends down, grips each feather with its beak, turns its head backward, and returns it to its original position. Add subtle procedural sounds for footsteps, spreading feathers, jumping, landing, pecking, and retrieval, with a mute toggle. Provide touch controls on mobile. Adapt camera framing to different screens, prevent accidental canvas clipping, and preserve smooth animation and the textured artistic atmosphere.

Safinaz Elhadary 的头像

Safinaz Elhadary2 个月前

This is so neat!🔥

padphone 的头像

padphone2 个月前

Yes. Thanks! You play it with ChatGPT site link I share.

Nishul 的头像

Nishul2 个月前

Broooo this is insane

padphone 的头像

padphone2 个月前

Try it plz:

Manas Joshi 的头像

Manas Joshi2 个月前

Gpt-6 Astra

Gregor 的头像

Gregor2 个月前

the 'might not even need Blender' bit got me. was this actual 3D geometry or procedural/shader stuff where Blender wouldn't have been in the workflow anyway?

padphone 的头像

padphone2 个月前

procedural apparently

Yeasin Arafat 的头像

Yeasin Arafat2 个月前

This deserves much more attention.

Cyprian Aarons 的头像

Cyprian Aarons2 个月前

beautiful!

P82 | AI NATIVE BUILDER 的头像

P82 | AI NATIVE BUILDER2 个月前

텍스트에서 바로 인터랙티브한 3D 화면으로 어지는 과정이 깔끔하네요.

padphone 的头像

padphone2 个月前

Indeed.

Shaxzod Eshonov 的头像

Shaxzod Eshonov2 个月前

that looks cool

ava mae 的头像

ava mae2 个月前

love that the 3D stays actually interactive on the web. i’ve been using krea for the visual and look dev pass first then three.js for the responsive scene.

man ki Hui 的头像

man ki Hui2 个月前

Great 👍🏻

Hole High 的头像

Hole High2 个月前

So good.

Brian Hadu 的头像

Brian Hadu2 个月前

web tools keep evolving

Brjan | AI Builder 的头像

Brjan | AI Builder2 个月前

cutting your workflow to 30 minutes is impressive, but I still love Blender's depth

AI Mastery Guide 的头像

AI Mastery Guide2 个月前

that peacock is so cute

James Labi 的头像

James Labi2 个月前

Can’t lie, this is nice.

zackbuilds 的头像

zackbuilds2 个月前

that peacock looks like he owns the place haha. a whole garden in this style would be nice

phil chacko 的头像

phil chacko2 个月前

I finally hooked up the Blender MCP this morning, and have to say, even a little bit of Blender adds enough shading and texture to make it worth it. The pure ThreeJS procedural assets look flat by comparison, IMO.

padphone 的头像

padphone2 个月前

Yeah, it depends on your needs.

Anima 的头像

Anima2 个月前

Impressive !!

padphone 的头像

padphone2 个月前

Thanks!! Try the threejs lol

manzi 的头像

manzi2 个月前

Astra + Three.js cutting hours to minutes — where does Blender still win for you?

jake 的头像

jake2 个月前

whats the repo?

Hole High 的头像

Hole High2 个月前

PS. @orbiodotso

DT K 的头像

DT K2 个月前

🤮

Michael Waitze 的头像

Michael Waitze2 个月前

The speed of building interactive assets is incredible. We actually went deeper on this here:

Cog_ 的头像

Cog_2 个月前

Astra loves brown websites lol… so does Opus

padphone 的头像

padphone2 个月前

interesting. hm. maybe they?

相关视频

You don’t need to learn After Effects anymore. all you need to know is what you want to build GPT-6 Astra + higgsfield can turn a prompt into a GPU plugin directly inside AE. now you can build advanced 3D engines inside of AE allowing you to create insane 3D animations today I created complex 3D brain > individually animated neural connections > fully editable in AE. it took a prompt and a few hours for higgsfield + gpt-6 astra to ship the motion just type in Higgsfield AI 🧩 /use-after-effects in ChatGPT try now and share your best work

You don’t need to learn After Effects anymore. all you need to know is what you want to build GPT-6 Astra + higgsfield can turn a prompt into a GPU plugin directly inside AE. now you can build advanced 3D engines inside of AE allowing you to create insane 3D animations today I created complex 3D brain > individually animated neural connections > fully editable in AE. it took a prompt and a few hours for higgsfield + gpt-6 astra to ship the motion just type in Higgsfield AI 🧩 /use-after-effects in ChatGPT try now and share your best work

Axultan

18,991 次观看 • 2 个月前

You don’t need to learn After Effects anymore. All you need to know is what you want to build GPT-6 Astra + Higgsfield can turn a prompt into a GPU plugin directly inside AE. Now you can build advanced 3D engines inside of AE allowing you to create insane 3D animations Today we created complex 3D brain > individually animated neural connections > fully editable in AE. It took a prompt and a few hours for Higgsfield + GPT-6 astra to ship the motion Just type in Higgsfield AI 🧩 /use-after-effects in ChatGPT Try now and share your best work.

You don’t need to learn After Effects anymore. All you need to know is what you want to build GPT-6 Astra + Higgsfield can turn a prompt into a GPU plugin directly inside AE. Now you can build advanced 3D engines inside of AE allowing you to create insane 3D animations Today we created complex 3D brain > individually animated neural connections > fully editable in AE. It took a prompt and a few hours for Higgsfield + GPT-6 astra to ship the motion Just type in Higgsfield AI 🧩 /use-after-effects in ChatGPT Try now and share your best work.

Higgsfield AI 🧩

112,131 次观看 • 2 个月前

MY FIRST GAME OUTPUT WITH GPT-6 ASTRA IT ONE-SHOTTED THIS CALL OF DUTY GAME IN 30 MINUTES!!! GPT-6 ASTRA IS THE FASTEST MODEL ON THE MARKET. THE SAME PROMPT TOOK FABLE 5.1 ALMOST 5 HRS AND IT CONSUMED A FRACTION OF THE TOKENS FABLE 5.1 DID.

MY FIRST GAME OUTPUT WITH GPT-6 ASTRA IT ONE-SHOTTED THIS CALL OF DUTY GAME IN 30 MINUTES!!! GPT-6 ASTRA IS THE FASTEST MODEL ON THE MARKET. THE SAME PROMPT TOOK FABLE 5.1 ALMOST 5 HRS AND IT CONSUMED A FRACTION OF THE TOKENS FABLE 5.1 DID.

hiraeth

40,821 次观看 • 2 个月前

Blender is now built into Ropilot Studio. Describe what you want. Ropilot - powered by GPT-6 Astra or Opus 5.5 - models it in Blender, brings it into Roblox Studio, and playtests it. From a prompt to a plane you can fly. Available now →

Blender is now built into Ropilot Studio. Describe what you want. Ropilot - powered by GPT-6 Astra or Opus 5.5 - models it in Blender, brings it into Roblox Studio, and playtests it. From a prompt to a plane you can fly. Available now →

Charlie

19,529 次观看 • 1 个月前

The jump from GPT-5.6 to GPT-6 Astra for world generation is honestly monstrous. This result genuinely surprised me. My first prompt was simply: “Create a cozy lake with a fisherman’s cabin on the marshy shore. Put a small island in the middle of the water, with an abandoned house hidden among the trees. Add a fishing boat beside the cabin, lily pads, reeds, jumping fish, typical wetland wildlife, a small beach, one path leading to the beach and cabin, another path returning into the forest, and a tree line around the entire scene.” I gave that description to Astra through my prompting workflow. It transformed the idea into a complete production prompt covering the semantic layout, terrain, Blender assets, GLB exports, Three.js assembly, animations, mobile controls and multi-view validation. I then gave that second prompt back to GPT-6 Astra, and this is the result. The improvement over GPT-5.6 is massive. Astra preserved the full composition, from the cabin and fishing boat to the central island and its hidden abandoned house, while handling the complete Blender-to-Three.js workflow with a level of coherence I genuinely wasn’t expecting.

The jump from GPT-5.6 to GPT-6 Astra for world generation is honestly monstrous. This result genuinely surprised me. My first prompt was simply: “Create a cozy lake with a fisherman’s cabin on the marshy shore. Put a small island in the middle of the water, with an abandoned house hidden among the trees. Add a fishing boat beside the cabin, lily pads, reeds, jumping fish, typical wetland wildlife, a small beach, one path leading to the beach and cabin, another path returning into the forest, and a tree line around the entire scene.” I gave that description to Astra through my prompting workflow. It transformed the idea into a complete production prompt covering the semantic layout, terrain, Blender assets, GLB exports, Three.js assembly, animations, mobile controls and multi-view validation. I then gave that second prompt back to GPT-6 Astra, and this is the result. The improvement over GPT-5.6 is massive. Astra preserved the full composition, from the cabin and fishing boat to the central island and its hidden abandoned house, while handling the complete Blender-to-Three.js workflow with a level of coherence I genuinely wasn’t expecting.

Givros

38,118 次观看 • 2 个月前

AGI is 100% solved. Prompt: "Take control of my computer using GPT-6 Astra and do the following: 1. design a character concept using Higgsfield Soul 2.0, 2. build a textured 3D model of it, 3. import it into Blender, 4. retopologize the mesh, 5. create a UV map, 6. build a character rig, 7. evaluate how production-ready the model is, 8. redo previous steps if you're not satisfied with results, 9. and then turn it into a cartoon using Seedance 2.5 on Higgsfield" Made in 30 minutes with GPT-6 Astra + Higgsfield MCP.

AGI is 100% solved. Prompt: "Take control of my computer using GPT-6 Astra and do the following: 1. design a character concept using Higgsfield Soul 2.0, 2. build a textured 3D model of it, 3. import it into Blender, 4. retopologize the mesh, 5. create a UV map, 6. build a character rig, 7. evaluate how production-ready the model is, 8. redo previous steps if you're not satisfied with results, 9. and then turn it into a cartoon using Seedance 2.5 on Higgsfield" Made in 30 minutes with GPT-6 Astra + Higgsfield MCP.

Higgsfield AI 🧩

166,130 次观看 • 2 个月前

Sam Altman (CEO of OpenAI): "Every night I have a few hundred agents running with GPT-6 Astra You no longer need to write prompts, if you use GPT-6 Astra” AI agents working while he sleeps, all monitored from his phone. In 55 minutes, he reveals what you can build now - and what used to require an entire team. Watch him break it down, then save the Astra-6 agents setup below👇

Sam Altman (CEO of OpenAI): "Every night I have a few hundred agents running with GPT-6 Astra You no longer need to write prompts, if you use GPT-6 Astra” AI agents working while he sleeps, all monitored from his phone. In 55 minutes, he reveals what you can build now - and what used to require an entire team. Watch him break it down, then save the Astra-6 agents setup below👇

darkzodchi

98,965 次观看 • 1 个月前

I find it so crazy that you can just prompt GPT-6 Astra to build its own Minecraft harness and record and edit a video showcasing it and it just does it

I find it so crazy that you can just prompt GPT-6 Astra to build its own Minecraft harness and record and edit a video showcasing it and it just does it

Angel 🌼

11,769 次观看 • 2 个月前

🔥 img2threejs × GPT-6 Astra × Hyper3D Live showcase: This is probably one of the most commercially valuable workflows I’ve tested so far. Image → Hyper3D → img2threejs → GPT-6 Astra → Interactive Three.js experience. 1/ Hyper3D handles the 3D reconstruction. 2/ img2threejs turns that result into a structured workflow that an AI coding model can actually work with. 3/ And GPT-6 Astra follows the img2threejs pipeline - turning the reconstructed asset into a structured, editable, and interactive Three.js experience with animation, VFX, lighting, and application logic. The important part isn’t just generating a 3D model, It’s what happens after the model exists. Instead of ending with a static asset, you can continue building around it with code: → Games → Interactive product experiences → 3D websites → Character showcases → Virtual worlds → Rapid prototypes 3D generation becomes the beginning of the workflow - not the final output. And when you combine high-quality reconstruction with an AI model capable of understanding and building the surrounding experience, the path from image → 3D → usable product becomes dramatically shorter. This is exactly the direction I want to push img2threejs. More experiments with OpenAI GPT-6 Astra × Hyper3D by Deemos are coming this month. 👨‍🍳

🔥 img2threejs × GPT-6 Astra × Hyper3D Live showcase: This is probably one of the most commercially valuable workflows I’ve tested so far. Image → Hyper3D → img2threejs → GPT-6 Astra → Interactive Three.js experience. 1/ Hyper3D handles the 3D reconstruction. 2/ img2threejs turns that result into a structured workflow that an AI coding model can actually work with. 3/ And GPT-6 Astra follows the img2threejs pipeline - turning the reconstructed asset into a structured, editable, and interactive Three.js experience with animation, VFX, lighting, and application logic. The important part isn’t just generating a 3D model, It’s what happens after the model exists. Instead of ending with a static asset, you can continue building around it with code: → Games → Interactive product experiences → 3D websites → Character showcases → Virtual worlds → Rapid prototypes 3D generation becomes the beginning of the workflow - not the final output. And when you combine high-quality reconstruction with an AI model capable of understanding and building the surrounding experience, the path from image → 3D → usable product becomes dramatically shorter. This is exactly the direction I want to push img2threejs. More experiments with OpenAI GPT-6 Astra × Hyper3D by Deemos are coming this month. 👨‍🍳

Nick

12,239 次观看 • 2 个月前

Okay, this is actually wild We generated a full 1-minute cartoon from one prompt today using And the crazy part? You can scale this to 30 minutes of consistent footage. From one short prompt Dropping the exact workflow so you can try it yourself #TextToVideo #GenerativeAI #AIart️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️

Okay, this is actually wild We generated a full 1-minute cartoon from one prompt today using And the crazy part? You can scale this to 30 minutes of consistent footage. From one short prompt Dropping the exact workflow so you can try it yourself #TextToVideo #GenerativeAI #AIart️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️

Trioma AI

10,797 次观看 • 3 个月前

GPT-6 Astra smokes Claude Fable 5.1 in Blender 💨 We compared GPT-6 Astra and Fable 5.1 on a Porsche 911 GT3 RS build and the difference is visible from the very first shot Output: Astra: $132.03 • 2.58 hours Fable: $114.41 • 2.56 hours Astra's model is not only more detailed in every aspect, but also far closer to the original car, costing almost the same as Fable's blocky funny looking model, the difference is astonishing

GPT-6 Astra smokes Claude Fable 5.1 in Blender 💨 We compared GPT-6 Astra and Fable 5.1 on a Porsche 911 GT3 RS build and the difference is visible from the very first shot Output: Astra: $132.03 • 2.58 hours Fable: $114.41 • 2.56 hours Astra's model is not only more detailed in every aspect, but also far closer to the original car, costing almost the same as Fable's blocky funny looking model, the difference is astonishing

atomic.chat

133,234 次观看 • 2 个月前

GPT 6 Astra first blender Impressions. GPT 6 Astra Extra High was used. 23 minutes 34 second to make in blender with computer use. Prompt - Create a 3d Formula one Model in blender with computer use. Whats next?

GPT 6 Astra first blender Impressions. GPT 6 Astra Extra High was used. 23 minutes 34 second to make in blender with computer use. Prompt - Create a 3d Formula one Model in blender with computer use. Whats next?

Conor Dart

19,604 次观看 • 2 个月前

I made a full original game in 24 hours using AI Stack: Opus 5.5 + Flux 3 Max + GPT Image + Tripo + Blender + Three.js Anyone can make games now. Full workflow thread and prompt below: (1/7)

I made a full original game in 24 hours using AI Stack: Opus 5.5 + Flux 3 Max + GPT Image + Tripo + Blender + Three.js Anyone can make games now. Full workflow thread and prompt below: (1/7)

NicoleCringe

61,940 次观看 • 7 天前

I made a full original game in 24 hours using AI Stack: Opus 5.5 + Flux 3 Max + GPT Image + Tripo + Blender + Three.js Anyone can make games now. Full workflow thread and prompt below: (1/7)

I made a full original game in 24 hours using AI Stack: Opus 5.5 + Flux 3 Max + GPT Image + Tripo + Blender + Three.js Anyone can make games now. Full workflow thread and prompt below: (1/7)

Shikhar

6,403,841 次观看 • 9 天前

GPT-6 Astra is cracked at making games. This runs in the browser with three.js. It even modeled the cars in Blender. The next GTA will be made by AI.

GPT-6 Astra is cracked at making games. This runs in the browser with three.js. It even modeled the cars in Blender. The next GTA will be made by AI.

Shikhar

587,225 次观看 • 2 个月前

GPT 6 Astra one shotted a bug in BridgeMind that no model could solve in 6 months. Fable 5 failed. Fable 5.1 failed. Opus 5, Sol, Grok 4.6, all failed. Astra fixed it on the first prompt. Then it rebuilt my office in Blender from photos. Built a racing game in 13 minutes that took Fable 5.1 two hours. Cut OpenAI's hallucination rate nearly in half. All while using a third of the tokens. Full review is out now. I do not know how Anthropic survives this.

GPT 6 Astra one shotted a bug in BridgeMind that no model could solve in 6 months. Fable 5 failed. Fable 5.1 failed. Opus 5, Sol, Grok 4.6, all failed. Astra fixed it on the first prompt. Then it rebuilt my office in Blender from photos. Built a racing game in 13 minutes that took Fable 5.1 two hours. Cut OpenAI's hallucination rate nearly in half. All while using a third of the tokens. Full review is out now. I do not know how Anthropic survives this.

BridgeMind

38,540 次观看 • 2 个月前

Let's keep benchmarking with the Night train this time, with GPT-6 Sol and GPT-6 Luna, so here are all four! 🚀 I gave each model the exact same prompt: “Build a Night train.” •Opus 5.5 • GPT-6 Astra • GPT-6 Sol • GPT-6 Luna Something that really surprised me: GPT-6 Sol produced almost the exact same rocket launch as Opus 5.5! The colors are slightly different, but the overall result is remarkably similar. For this prompt, I’d even put Sol ahead of Astra. I’m seriously impressed by Sol, especially at half the API price of Opus 5.5! 🤯 I’m starting to use this approach in my own workflow. I kept one Codex subscription so I can run a bunch of Sol sub-agents while keeping my main agent on Astra. Sol is so cheap for what it can do! Knowing when to switch models based on the task, the quality you need, and the cost is becoming an essential skill in this new AI era.

Let's keep benchmarking with the Night train this time, with GPT-6 Sol and GPT-6 Luna, so here are all four! 🚀 I gave each model the exact same prompt: “Build a Night train.” •Opus 5.5 • GPT-6 Astra • GPT-6 Sol • GPT-6 Luna Something that really surprised me: GPT-6 Sol produced almost the exact same rocket launch as Opus 5.5! The colors are slightly different, but the overall result is remarkably similar. For this prompt, I’d even put Sol ahead of Astra. I’m seriously impressed by Sol, especially at half the API price of Opus 5.5! 🤯 I’m starting to use this approach in my own workflow. I kept one Codex subscription so I can run a bunch of Sol sub-agents while keeping my main agent on Astra. Sol is so cheap for what it can do! Knowing when to switch models based on the task, the quality you need, and the cost is becoming an essential skill in this new AI era.

Tony

112,633 次观看 • 1 个月前

Claude Opus 5.5 is getting ridiculously good at creating Three.js experiments. This watermelon jelly experiment is actually my stress killer now 😂 The fact that you can prompt things like this and get crazy interactive web experiences is honestly insane. People are building some seriously wild stuff with Opus 5.5 right now.

Claude Opus 5.5 is getting ridiculously good at creating Three.js experiments. This watermelon jelly experiment is actually my stress killer now 😂 The fact that you can prompt things like this and get crazy interactive web experiences is honestly insane. People are building some seriously wild stuff with Opus 5.5 right now.

Abraham John 🦄🦓

11,023 次观看 • 1 个月前

🚨 STOP learning Blender !! Learning Blender in 2026..... Is officially obsolete. MiniMax Design can now automate Blender to create ANY 3d SCENE !! I just gave it a PROMPT.... And MiniMax Design used GPT-6 Astra to handle everything like: 1️⃣ Opening Blender 2️⃣ Generating the 3D elements 3️⃣ Fixing lighting 4️⃣ Camera Tracking Data etc.... It built the entire scene inside Blender. Finally, I used MiniMax H3 Max to add colors to the 3d SCENE !! Then I just rendered the 3d scene !! Best part? Using GPT-6 Astra through MiniMax Design is way more affordable than running it directly.

🚨 STOP learning Blender !! Learning Blender in 2026..... Is officially obsolete. MiniMax Design can now automate Blender to create ANY 3d SCENE !! I just gave it a PROMPT.... And MiniMax Design used GPT-6 Astra to handle everything like: 1️⃣ Opening Blender 2️⃣ Generating the 3D elements 3️⃣ Fixing lighting 4️⃣ Camera Tracking Data etc.... It built the entire scene inside Blender. Finally, I used MiniMax H3 Max to add colors to the 3d SCENE !! Then I just rendered the 3d scene !! Best part? Using GPT-6 Astra through MiniMax Design is way more affordable than running it directly.

Darshal Jaitwar

86,087 次观看 • 1 个月前

❤️‍🔥 GPT-6 Astra is insane. Just recorded a 10-min tutorial on how to use GPT 6 Astra + Three.js WebGPU to create award-winning 3D animated sites

❤️‍🔥 GPT-6 Astra is insane. Just recorded a 10-min tutorial on how to use GPT 6 Astra + Three.js WebGPU to create award-winning 3D animated sites

Viktor Oddy

195,598 次观看 • 2 个月前