stable-dreamfusion
stable-dreamfusion copied to clipboard
ashawkey
Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.
### Description When using "- O2", there is a problem with "NaN or Inf found in input tensor." Especially after updating the code, the first epoch will appear, like this:...
### Description ``` [INFO] loading DeepFloyd IF-I-XL... A mixture of fp16 and non-fp16 filenames will be loaded. Loaded fp16 filenames: [safety_checker/pytorch_model.fp16.bin, text_encoder/pytorch_model.fp16-00001-of-00002.bin, text_encoder/pytorch_model.fp16-00002-of-00002.bin, unet/diffusion_pytorch_model.fp16.bin] Loaded non-fp16 filenames: [watermarker/diffusion_pytorch_model.bin If this...
### Description Trying Image to 3d on Colab and showed this error when I came to the training process The error showed on line 29 from: can't read /var/mail/nerf.provider /bin/bash:...
Can you explain `init_tet()` for initializing DMTet? As far as I understand, with SDF, the part where the SDF value is 0 becomes the surface. I wonder if `self.sdf.data +=...
hi, I'm currently training your work on RTX3090 with 24G memory. when I tried "python main.py --text "a hamburger" --workspace trial -O --vram_O --w 300 --h 300" , my CUDA...
### Description I am trying to run the code in a Google Colab notebook, but I am encountering installation errors for several packages (raymarching, shencoder, freqencoder, and gridencoder). The installation...
https://github.com/ashawkey/stable-dreamfusion/blob/main/guidance/sd_utils.py#L112 I am encountering confusion at line 112 in the `sd_utils.py` file. Based on my understanding, the CFG should be structured as follows:  This structure corresponds to the following...
RuntimeError: Error building extension '_grid_encoder': [1/2] /usr/bin/nvcc -DTORCH_EXTENSION_NAME=_grid_encoder -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /home/u/miniconda3/envs/sdf/lib/python3.8/site-packages/torch/include -isystem /home/u/miniconda3/envs/sdf/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem /home/u/miniconda3/envs/sdf/lib/python3.8/site-packages/torch/include/TH -isystem /home/u/miniconda3/envs/sdf/lib/python3.8/site-packages/torch/include/THC -isystem /home/u/miniconda3/envs/sdf/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_70,code=compute_70 -gencode=arch=compute_70,code=sm_70...
### Description Tried setting up this project on local machine but cannot install Raymarching, and other extensions due to various errors. I have solved some step by step but stuck...
### Description when i run :"python main.py -O --image ./df_ep0100_0008_rgb_rgba.png --workspace trial_image --iters 5000 --default_polar 80", i met this problem:“/home/u/miniconda3/envs/sdf/lib/python3.8/site-packages/torch/utils/cpp_extension.py:1967: UserWarning: TORCH_CUDA_ARCH_LIST is not set, all archs for visible cards...