The 3D Object Generation Blueprint is an end-to-end generative AI workflow that allows users to prototype 3D scenes quickly by simply describing the scene. The Blueprint takes a user’s scene idea, generates object recommendations and associated prompts using a LLM, and then generates image previews at lightning speed with NVIDIA SANA and ready-to-use 3D objects.
The user can go from a text idea to 3D assets quickly, which can then be used to prototype a scene, or to build a scene that guides image generation. This saves users tons of time, as searching for assets online or building them from scratch can be highly time-consuming.
The Blueprint is managed through a simple gradio UI. AI models for the LLM and 3D generator are deployed through NIMs for simplicity and performance.
The blueprint and corresponding instructions can be found on our AI Blueprints Github.
GOVERNING TERMS: The software and materials are governed by the NVIDIA Software License Agreement and Product-Specific Terms for AI Products; except as follows: use of the Cosmos model is governed by NVIDIA Open Models License, use of the llama-3_1-8b-instruct is governed by the NVIDIA Community Model License Agreement and the use of the Sana model is governed by NSCL v2-custom. ADDITIONAL INFORMATION: Llama 3.1 Community License Agreement for llama-3_1-8b-instruct model, and Gemma Terms of Use | Google AI for Developers for Gemma-2-2B-IT, Gemma Prohibited Use Policy | Google AI for Developers for the Sana model. Built with Llama.
The models in this blueprint are not owned or developed by NVIDIA. They have been developed and built to a third-party’s requirements; see links to:
Software Components: The blueprint does not directly contain any software, but it provides a script to download the following components:
Runtime Engines:
Supported GPUs:
Any RTX GPU with >=16 GB VRAM
Supported Operating Systems:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
Please report security vulnerabilities or NVIDIA AI Concerns here.
Transform your scene idea into ready-to-use 3D assets using Llama 3.1 8B, NV SANA, and Microsoft TRELLIS