threestudio

threestudio copied to clipboard

NerfAcc: No CUDA toolkit found. NerfAcc will be disabled.

2

When I use Pycharm, I use the code, I got NerfAcc: No CUDA toolkit found. NerfAcc will be disabled. ``` "/home/dubaiprince/miniconda3/envs/threestudio/bin/python /home/dubaiprince/Projects/threestudio/launch.py --config configs/dreamfusion-if.yaml --train --gpu 1 system.prompt_processor.prompt=a zoomed out...

yuchenlichuck

Unconditioned noise of LoRA

1

Hi, I'm trying to learn your implementation of VSD loss and have a question. To get the noise with CFG, one should compute both conditioned and unconditioned noise. So why...

ziye3001

required python cuda is not all compliant and suitable

1

Nvidia Driver Version: 510.108.03 CUDA Version: 11.6 Operating System + Version: Ubuntu 20.04.1 LTS Python Version: Python 3.8.17 GCC Version : 9.4.0 This kind of config can't fit to torch...

yuchenlichuck

How to get finer implicit sdf?

1

I want to initialize the implicit SDF from an obj file, when the obj has rich details, the implicit SDF can't restore these details well, what adjustments do I need...

Gaodzlearn

RuntimeError: tinycudann/bindings.cpp:81 check failed params.device().is_cuda()

2

The program worked fine before, but an error was reported when I opened it today. After debugging, I felt that it was not a program error. I don't know whether...

flawzhang

zero123 doesn't work

3

Thank for great work! I tried `python launch.py --config configs/zero123.yaml --train --gpu 0 data.image_path=./load/images/dog1_rgba.png`, but I encountered the following error. How can I fix this? ``` bin /home/lambdasix/anaconda3/envs/threestudio/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda117.so /home/lambdasix/anaconda3/envs/threestudio/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning:...

YJ-142150

Support optimization of texture map given a custom mesh

1

Hi, is it possible to implement the optimization of the texture map given a custom mesh?

MrTornado24

Poor sample quality when using V-prediction model for unet in VSD

2

Hi! I tried using a v-prediction model (SD 2-1) for VSD guidance as suggested in #179 , and I applied v to epsilon conversion for the unet predictions as well....

leejielong

Controlnet vsd

1

Recreated and modified #244. Found a good guidance scale via tuning. Some results: condition_scale: 2.0 with guidance_scale 7.5: https://github.com/threestudio-project/threestudio/assets/36912641/73a7c4b8-1ff3-4c60-90a3-475f07f53a22 condition_scale 1.5 with guidance_scale 7.5: https://github.com/threestudio-project/threestudio/assets/36912641/c6f19ac1-0c10-410c-bd2b-dc1680496c72

yankeesong

Can't reproduce fantasia3D result showed in README

3

just follow the instruction showed in README： > python launch.py --config configs/fantasia3d.yaml --train --gpu 0 system.prompt_processor.prompt="a DSLR photo of an ice cream sundae" > python launch.py --config configs/fantasia3d-texture.yaml --train --gpu...

vinowan