STACKED
This experiment focused on how far simple Blender shapes could guide a fast product ad in Seedance 2.5. Camera movement, rhythm, and the order of actions were planned in Blender, with the final appearance coming from an image reference.
The biggest challenge was avoiding stiff, stop-start motion. Earlier versions followed the blocking too literally. Revising the Blender timing and allowing more overlap, deformation, and material response in the prompt helped move the result toward something more natural.
It took multiple rounds to get there, but the final take was genuinely satisfying. This test gave me a much clearer sense of how much to specify in Blender and how much freedom to leave in the generation.
Created with @PixVerse
#bolakokgitu #karyabangjumawa #pixversecpp #Blender #Seedance25
Scenario MCP + GPT Astra = your actual room in 3D.
I photographed my office and walked through it an hour later.
> shoot a room on your phone, nothing measured or scanned
> Scenario MCP pulls the real materials out of the photos, down to the carpet's 500mm tile grid
> Astra builds the geometry in Blender, opens in a browser
I'm currently testing a new way to make assets for my game so I don't have to spend all my tokens having Astra build them from scratch in Blender.
Reference - > @tripoai - > Blender to split into models - > @unity
Let's see how it goes.
It takes 42s to render the latest Blender splash art using Cycles on my machine. That's ~0.02FPS and clearly not suitable for real-time applications.
But what if we wanted to?
@SpenserFX recently described how they created a 3D Gaussian Splat (follow him!) from the Blender file and they kindly uploaded the splat to SuperSplat, which was then compressed into a 50MB .ssog file.
Now anyone with a browser can inspect this masterpiece from any angle in real time (thanks to the powerful @playcanvas engine).
Link in the comment below (download available).
GPT-6 is one of most noticable jumps you can't argue. And 3D is where it shows the hardest.
I ran it through Blender few days: assembled a whole car from primitives, rigged and animated my quadruped creature, built a stylized island town and more. The full video with every test is out.
My recommendation: run it through MCP. Computer Use is more of a fun demo, but with the right MCP tools it gets close to magic. If you don't want to wait forever and burn all your tokens, use the full setup. I break down mine in the video.
https://t.co/zW250N42Fb
What is really useful is how GPT-6 Astra got better in spatial understanding. I'm still shocked how good it navigates 3D space.
Here I gave it Blender MCP and Tripo P2.0 to generate optimized 3D models and put them together, rig and animate. Result is freaking awesome!
Doing 3D objects procedurally with Astra is fun, but quality is not compared with what 3D Gen can do. Like you don't ask GPT to draw image with pen when there is GPT Image, same here. And token cost also speaks for it, 3D gen simply cheaper.
But the way it assemble thing together, characters and scene, that is shocking ngl. And rigging of course, I have so much hope on it, it is most annoying part of 3d for me lol
Whoever wonder how good is Computer Use by GPT-6 Astra - It's overhype ahah
I mean, official trailer definitely shows more that it is. Don't get me wrong, it is crazy smart but unimaginable slow lol.
Attached is 1h time-lapse of making character from image. It took 5 min to just save file ahaha. I waited for 1h and abandoned this idea, too long and impractical.
PATUNGAN UNTUK HUTAN!!!
Gaiss, Bang Ferry Irwandi mau luncurkan program untk beli hutan Indonesia buat ditanami lagi, terus bapaknya Andre kalaweit juga lagi galang donasi buat selamatkan satwa liar Kalimantan. Yuk bisa yuk kita beli lagi hutan kalimantan. Selain teriak teriak di medsos, yuk kita bantu sebisanya.🥺🥺🥺🥺
ok @higgsfield_ai saying they prompt clicked blender into this
they just threw 3d people at the render lmao
if this actually worked id walk into their interview in underwear
scams gotta be more modest
Googles Omni Flash model is such a great combination with Dreams 3d artwork.
For most of the generations here, simple prompts like these were all it took: "Wrap the video in stark realism" or "Wrap the video in the realism of the provided image".
Reposting with the correct edit of the video.
Ai workflows that allows us to push, pull, shape and move elemenrs around. Like clay, but powered by underlying world knowledge.. that's why I was excited about generative ai from the beginning - because I know there's plenty of room for us to raise the ceiling in our creative tools and workflows .
I know I've been pushing this type of workflows for years and it's pretty crazy to see that the Ai systems we use are now at a level where this sort of workflow seems to be within reach.
This whole mocap pipeline was built and is operated end-to-end by an AI agent.
Left: AI-generated video.
Right : automatic retarget onto a Mixamo rig in Blender real foot contact, zero manual keyframes.
Any Mixamo character.
Open source: https://t.co/cq58JxTVX5
#b3d #mixamo #mocap #vibecoding
We’re currently working on an Auto Generate Picker feature for BGEN Picker. It lets you Automatically generate a complete picker for your rig without building from scratch.
you can customize it however you like or build from scratch if you prefer so you can get to animating faster from a clean interface.
#bgenpicker #blender3d #rigging #maya
MotionGen now can generate faces from video and animate. The beta is free!
Follow us on YouTube, X, Instagram for chance to win the full version we give away 20 free Pro upgrades to our followers every month.
#MotionGen#mocap#Animation#FaceGeneration#FreeBeta#Giveaway