Via Get3D I understand it can take around 30 minutes or so to generate 3D models from text description at this point. What are the expectations on the ability to speed up that time? Is it in the realm of possibility to watch that time decrease as quickly as the image generators did?
zgojcic
2
Text-guided shape generation takes around 30min as we use a relatively simple approach of finetuning the 3D generator with a directional CLIP loss. The time to generate shapes based on the text description could be largely reduced by training a text-conditioned 3D generative model in the first place.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Does GET3D have image-guided shape generation feature? | 5 | 874 | May 4, 2023 | |
| Regarding generating 3D shapes of Cars, bikes and chairs | 1 | 498 | May 4, 2023 | |
| How Nemotron Made three.ws Text-to-3D Pipeline Usable | 0 | 171 | July 10, 2026 | |
| Does the training dataset contain 3D models for the Simpsons character? | 2 | 707 | May 4, 2023 | |
| GET3D takes 3D CAD data in training | 6 | 830 | May 4, 2023 | |
| About the GET3D Team- AMA May 4th, 2023 | 0 | 4965 | April 18, 2023 | |
| Introductry Research Efforts in Generative AI | 1 | 596 | June 28, 2023 | |
| AI Model Can Generate Images from Natural Language Descriptions | 0 | 329 | August 21, 2022 | |
| Creating full 3D scene using AI : diffusion model and ComfyUI | 0 | 393 | June 4, 2024 | |
| Is Nvidia also thinking about actual 3D images? | 1 | 574 | May 4, 2023 |