Want to generate a batch of consistent 3D models? Start with guided image generation using custom LoRA models or structure references. Then process them in parallel. In no time, your pack of 3D assets is ready to export in Unity, Blender, or any 3D tool for final polish.

"Bro trust me, AI-generated meshes will never be production-ready" The AI-generate mesh:

Alix Ollivier is Building Balloon Bats! On the Generative 3D side, we've already implemented all these models 👇 and we're exploring some additional ones (plus retopology/rigging to come later). See youtube.com/watch?v=ajBYXl… On the video/image side, all the usual suspects from Veo to Kling, Seedance etc.

When I say the Holodeck will be AI run, this is a great taste. All sorts of new innovation is about to ship.

The entire feed of replies rn 😂🫠

We are thrilled to release the next leap in art-grade 3D generative models. Our single-click model pipeline gives unprecedented mesh outputs, with mesh parts-based topology. It is available now for all Cube tiers to start for free. ☑️ Our multi-stage hierarchical AI models

you know who has one of my favorite /models API endpoint? Scenario they give you a lot of information about the model cc: Emm | scenario.com

Anyone can join Founders Inc, just come to SF and build something cool. I couldn’t care less where you went to school (I didn’t even finish high school), so credentials won’t win you a spot—your ambition and idea will.

Runway, promptla görsel düzenleme yapabilen Gen4 modelini duyurdu. GPT image ile pandoranın kutusu açıldı, artık yeni istikamet bu yönde. Benzer işleri yapan modelleri Scenario. com üzerinden aynı prompt/görselle kıyasladım. => #reklam degildir.

🚨 Gen‑4 References just dropped in Scenario, and it’s all about control. Use up to 3 input images to remix characters, outfits, backgrounds or even poses & lighting. Consistent. Sharp. Controlled at app.scenario.com/edit-with-prom…

100% AI generated mobile game ads! “You just write a single prompt and the whole video is created!” Don’t believe that big lie. However, if you use different AI models correctly, you can actually pull it off in about 40 minutes. I turned an imaginary mobile game mascot into a

Haluk nails it here👇 People expect magic from a click on a single model. And sometimes it may work. But real production-quality results come from chaining multiple models (image gen, editing, video gen…), in sequence. Still 10x faster than any non-AI workflows.

I revamped my Substack - if you want to learn more about brand-building in a generative-AI world, check out the latest articles and behind-the-scenes tutorials on Substack. Link in thread.

Introducing mcp-three An MCP server for Three.js made with xmcp Add toolkit for your AI to work with .gltf/.glb files: ✅ Understand model structure and animations ✅ Generate types & code with gltfjsx ✅ Less bugs when working with AI & 3D files Instructions below 🧵

Quick shoutout to Stef Hamerlinck, a top-tier brand marketer & designer from Ghent, behind dozens of epic mascots including Alan's iconic blue marmot! 💙 He’s now using AI (and Scenario) to level up storytelling, crafting unforgettable mascot variations using custom

I wrote this thread a while ago detailing how I write my initial prompts for a game project. I think it’s still relevant now, especially with more powerful models. Hope it’s helpful if you want to “vibe code” some games. Have fun and enjoy the process!

Horse wood sculpture generated with Scenario from a single image. On Sketchfab: skfb.ly/pz6Bt

Veo has an incredible "hidden" ability. It's one of my absolute favorite aspects of Veo 3 i2v. It's ability to transport elements through the latent space, with this simple but very powerful prompt structure: “Instantly jump/cut on frame 1. [Describe the new context]" With

📣 New Image generation models just dropped on Scenario. Imagen 3 & 4, Ideogram v3, Seedream 3, Luma Photon, Recraft v3, now live. Run the same prompt across models, compare side by side, and pick what fits at app.scenario.com/https://app.sc…