配置难度较高,需要手动克隆仓库、安装依赖、构建 CUDA 扩展,并必须提前手动下载所需的多个预训练模型权重。最快成功路径为 `git clone` 后执行 `pip install -r requirements.txt`,再运行 `python main.py --text "a hamburger" --workspace trial -O`。
核验依据
README: A pytorch implementation of the text-to-3D model **Dreamfusion**, powered by the [Stable Diffusion](https://github.com/CompVis/stable-diffusion) text-to-2D model.
README: This project is a **work-in-progress**, and contains lots of differences from the paper. **The current generation quality cannot match the results from the original paper, and man…
README: python main.py --text "a hamburger" --workspace trial -O
README: To use image-conditioned 3D generation, you need to download some pretrained checkpoints manually: * [Zero-1-to-3](https://github.com/cvlab-columbia/zero123) for diffusion backend.