This engineer inside a giant monowheel is why AI... 3D should feel more like directing a small team. Astra figures out the structure, V2FUN makes the hard shapes and material details, and the asset comes together with less token waste and faster iteration. #V2Fun #GPT6 #Astra #AI3Dshow more

This feels less like ""AI image generation"" and more... like actually directing a shot. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. I started with a real photo and used GPT-6 Astra + Blender to recreate it as a clay-style scene. Then I used Seedance 2. 5 to figure out the movement and camera motion. The last step happens in Dreamina - turning that clay animation into a live-action result. The separation of structure → motion → final look is what makes this workflow interesting. #Dreamina #DreaminaPartnershow more

Astra (GPT-6) is here!!! I've had early access and... tested it like crazy with things like games, code, writing, browser control, presentations and general knowledge work. This is the best model I've ever used. Period. (Incredible demos below in this thread ⬇️) Here's my take on Astra: > It's insanely capable. This feels like a massive improvement, not just an incremental change. This is especially true with zero-shot prompts. > It's all about knowledge work. Slide creation, analysis, writing, and browser control. And oh my...it's so good at browser control. GPT-5.6 was already fantastic at doing things in the browser, Astra is another level and significantly faster. > We're closer than ever (arrived?) at prompt-to-playable game. And I don't just mean only playable, these are actually fun games. I bet if someone with a great eye for games used Astra, they could create a viral game within 1-2 weeks. > Astra is better at writing but not perfect. It removes much of the "AI Smell" we're all familiar with but some stink still survived. > It has a tendency to use the same design colors and look/feel as GPT-5.6 (forrest green anyone?) but it is more steerable in design than previous models. > It's highly steerable in general. A little nudge goes a long way. When I first started using Astra, almost every task I gave it would go for ~30 minutes. I wanted it to keep working. Adding more specifics to a prompt helped greatly with it's ability to work for a long time. > Astra's 3D understanding is unmatched. 3D asset creation was consistent and easy and its spacial awareness while building complex 3D worlds blew me away. I'm still getting familiar with Astra but this will now be my go-to model for any difficult work I have. Check out the demos below: 👇show more

People are earning 10,000$ by selling 3d Websites 💀... So I tried creating a 3d website using GPT-6 Astra + Hyper3D Rodin's MCP And they built this landing page with an INTERACTIVE 3D CAR in the hero. I didn't model the car. I didn't touch Blender. I didn't manually integrate the 3D asset. And this is the result 👇show more

This workflow is more interesting than simply “AI +... Blender.” GPT-6 Astra handles geometry generation → Blender takes care of composition → Dreamina’s Clay Renderer Plugin brings the clay model in with a single click → Seedance 2.5 delivers the final render. The camera and layout are locked in during the handoff, meaning the original 3D setup stays intact. And thanks to competitive Seedance 2.5 and 2.0 pricing, you can try more looks without extra spending. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is a genuine pipeline. Worth testing out. #Dreamina #DreaminaPartnershow more

I think people are still underestimating how important the... 3D layer could become in AI video. The problem with complex AI shots has never just been image quality. It’s spatial consistency, camera direction and knowing where everything is supposed to be. GPT-6 Astra can map the scene and keep camera + character paths within the Viewport, giving the shot a spatial structure before generation. I then manually move that scene into CapCut PC and use Seedance 2.5 to render it. From there, CapCut PC becomes the actual editing environment. That feels less like “AI generated a video” and more like a production pipeline worth experimenting with. #CapCutPC #GPT6Astra #AIVideo #Seedance25show more

This is probably the most interesting part of the... Astra workflow. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. Astra codes the geometry → Blender → Clay Renderer Plugin → final render on Dreamina. Once the clay model is ready, the plugin lets you pass the Blender setup directly into Dreamina. Seedance 2.5 then handles the rendering while preserving the scene's camera and layout. So the jump from a basic 3D structure to finished footage happens without the usual back-and-forth. And you're not paying a markup for the pipeline—full 2.5 quality stays accessible. Try it now 👇 #Dreamina #DreaminaPartnershow more

This is my first "Holy Shit" moment with GPT-6... Astra I asked GPT-6 Astra to create a ROBLOX game, and the results are stunning! Who needs to make games when it's this easy to make them in the click of a button? AI Rules! I'm super excited to see what GPT-6 Astra is capable of!show more

🚨 A single 3D website can cost clients $10,000+... to build. But you don’t need to be a 3D designer to create one anymore. No Blender ❌ No complicated 3D modeling ❌ No coding from scratch ❌ All you need is one Codex plugin to get started. I tested the workflow and this is what I created 👇 #AholoLux3D #Lux3D #GPT6 #Astra #3D Built with Manycore Tech’s AI Modelshow more

GPT-6 Astra rigged and animated a mech with digitigrade... legs walking in Godot from one prompt in 30 minutes, handling a joint setup that every other model failed to figure out, with the full workflow being a Midjourney concept, Meshy 7 for the 3D model and one prompt to Astra. → Rigging normally means building a skeleton, assigning bone weights and hand animating the walk cycle, usually weeks of work → Digitigrade is the hard version, the backwards knee setup seen on dogs and raptors → Walk cycle is not perfect but imagine what a couple more prompts would doshow more

$RVV - Powering the Future of AI Entertainment $RVV... isn’t just a token, it’s the utility core of the Astra Nova ecosystem, enabling seamless value across gameplay, creation, and community. 🔥 ▪️In-game & AI Agent upgrades ▪️ Real-world asset redemption ▪️ Platform fees & adverts in TokenPlay AI ▪️Patreon subscription in NovaToon ▪️ Black Pass quest rewards ▪️ Battle Pass seasons ...and more. As the ecosystem expands, $RVV evolves with it, bridging AI, Web3, and entertainment into one unified token economy.show more

personalized shopping with Astra is unbelievable I did something... similar with GPT-5.6-Sol (not on ultrafast) and while Sol got the job done, Astra did a way better job on reproducing my like (face + body) and was ~4x faster (1 hr 33 min versus 4 hr 24 min)show more

It doesn't ask Blender and AI to do the... same job. GPT-6 Astra handles geometry. Blender handles structure and composition. The Dreamina Clay Renderer Plugin handles the one-click transfer. Seedance 2.5 handles the final render. The camera and layout stay locked when the clay model moves into Dreamina, so you keep the precision of 3D while exploring new visual styles faster. The competitive pricing of Seedance 2.5 and 2.0 makes that experimentation even more accessible. Worth trying. #Dreamina #DreaminaPartnershow more

This workflow is more interesting than simply “AI +... Blender.” GPT-6 Astra produces the geometry → Blender constructs the composition → Dreamina’s Clay Renderer Plugin imports the clay model with one click → Seedance 2.5 renders it into the final output. The camera and layout stay unchanged during the transfer, so the original 3D setup is preserved. Plus, with competitive pricing for Seedance 2.5 and 2.0, you can explore additional looks without adding unnecessary cost. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. Worth a test. #Dreamina #DreaminaPartnershow more

Is 3D becoming the missing middle layer between AI... imagination and controllable video? Text can describe what a scene should look like. Video models can render it. But something still has to define the spatial relationships in between. That’s where GPT-6 Astra becomes interesting: it can understand the 3D environment and establish camera and character movement inside the Viewport. The resulting scene is manually brought into CapCut PC, where Seedance 2.5 handles the video generation. Then the generated footage can continue into CapCut PC for editing. It’s not really “3D replacing AI video.” It’s more like giving AI video a spatial blueprint to follow. That feels like a direction worth experimenting with in CapCut PC. #CapCutPC #GPT6Astra #AIVideo #Seedance25show more

Anime.js 4.5 is out and it's a fun one:... Introducing the Three.js adapter 🎉 - Up to 50% less code for 3D animations - CSS transform-like API for 3D objects (rotate, skew…) - Simpler material color animations - Easy instanced mesh animations - Stagger 3D And so much more! ⬇︎show more

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.show more

Prompting AI used to mean asking for an output.... With GPT-6 Astra + CapCut PC, a prompt can become an editing instruction. Upload the footage, explain the pacing and structure, and Astra can control CapCut PC to turn that direction into an actual timeline. Then I can adjust the result directly... clips, pacing, captions and other elements remain editable. It's a subtle change, but an important one: The prompt doesn't just describe what to generate. It tells AI what to do inside the editing workflow. #GPT6Astra #CapCutPC #AIVideo #Seedance25show more

🚨 Alpha Alert 🚨 Backed by NVIDIA Inception, Shiba... Inu, Sanabil, 500 Global, and NTDP 👀 Astra Nova is here to redefine gaming! 🟢So What is Astra Nova? Astra Nova is an AI-driven gaming ecosystem and NVidia Inception partner, combining AI storytelling, community-driven innovation, and real-world rewards. Partnering with web3 giants like Shiba Inu, they’re building the future of immersive experiences. 🟢Key Features ◽️AGI-Powered RPG with real-time adaptive NPCs, quests, and enemies. ◽️Community-Centric approach where players shape the game and its economy. ◽️Real-World Rewards like tokenized gold, diamonds, and vouchers. 🟢 $RVV Token Utility ◽️Power in-game transactions, AI agents, and NFTs. ◽️Access exclusive events, mini-games, and land NFTs. ◽️Redeem IRL vouchers with 2000+ global brands. 🟢What’s Next? ◽️Weighted airdrops, loyalty rewards, and beta access. ◽️Beta access, staking, and exclusive mini-games. I'm pretty bullish about $RVV token and the future of Astra Nova, make sure check them out!show more

As we move more and more into 3D, texturing... 3D assets will be essential ☝️ Repainting 3D Assets is a new AI method that can take any 3D asset and paint it with a given text prompt. The results, while low-resolution, are pretty impressive.show more

I spent my Astra tokens trying to teach small... Qwen3.5 (9B) to create lowpoly 3D rooms using Blender 🏡 you (or Astra) can take this challenge today here's what I learned: > you need to align geometry with deterministic rewards and VLM-as-a-judge (GLM-5.3-Flash which was a great judge) > I tried GEPA at first with various rewards, model learned to make valid rooms (but that's it) > after solving geometry you need the model to add more details, which is very hard > the stricter the reward function, less advantage you get because task is too hard. grpo didn't help > I tried passing image guidance to both policy (Qwen) and judge (GLM) it didn't improve > I tried tastemaxxing trick in this blog, truth is, flowers can be abstract, a house can't be shoutout to OpenEnv, environment is super simple what can you try? > experiment with different rewards or policy (teach a larger Qwen) > generate a dataset of 150-200 Blender render Bpy examples using Astra, fine-tune Qwen on it first and then try GEPA or GRPO > ???show more