From multiple consistent objects within a single image to fully recreated 3D objects in Blender. 100% AI-generated. Workflow detailed below 👇

Step 1/ Generate a grid of 6 consistent objects. For this, I used @Scenario_gg with the "Juicy Icons" model, which consistently creates cartoon-style, simplified 3D icons arranged in a grid. Available on

Step 2/ More specifically, I used image-to-image generation combined with a quick sketch to guide the colors and positions of each object.

Step 3/ Import the image in Claude + use the Blender MCP. Ask "Generate a collection of six high-quality 3D vehicles based on the reference image I've provided." + any other specifications you may have.

Step 4/ I used @sidahuj Blender MCP ( Make sure @DeemosTech is also enabled in the MCP menu. In no time, you'll see ALL your consistent objects, generated in 3D, arranged nicely on a 3x2 grid :)

@DeemosTech Note: The six generated 3D objects are consistent with each other but might not be 100% style-consistent with the original image. For better consistency, upload each image separately in high resolution or generate them individually in Rodin using an image reference.

Looking to automate reporting? Use AI agents to turn spreadsheets to reports in minutes without any coding.

Very good workflow, it’s time to combine it with real-world scenes to make something amazing.

This is amazing 🔥

This is awesome! Can't wait to try it

I've been trying to like scenario for gamedev, but the UI is tough pill to get through :(

Which part did you struggle with? (Training, generation, other?) There’s a complete knowledge base, 30+ tutorial on different topics and more importantly an AI bot that you can ask anything about- it’s been trained on the product documentation. MCP on the way… after we release 3D 🫣 More than happy to help otherwise 🙏🏻