Spaces:
Runtime error
Apply for community grant: Academic project (gpu)
LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes
In this paper, we propose an algorithm that converts a single text/image prompt into a 3D Gaussian splatting scene. The algorithm is model-agnostic, meaning that any StableDiffusion checkpoint can be used to create a Gaussian dream.
Code 🧬: https://github.com/luciddreamer-cvlab/LucidDreamer
Paper 📃: https://arxiv.org/abs/2311.13384
Project page 👉: https://luciddreamer-cvlab.github.io
This project is the minimal implementation (without SD checkpoint support) to minimize the possible conflict of the demo.
Hi @ironjr , we have assigned a gpu to this space. Note that GPU Grants are provided temporarily and might be removed after some time if the usage is very low.
To learn more about GPUs in Spaces, please check out https://huggingface.co/docs/hub/spaces-gpus