Wonder3D
Wonder3D copied to clipboard
xxlong0
Single Image to 3D using Cross-Domain Diffusion for 3D Generation
I encountered this after running `accelerate launch --config_file 1gpu.yaml test_mvdiffusion_seq.py --config configs/mvdiffusion-joint-ortho-6views.yaml`, where the output images are all black: ``` C:\ProgramData\anaconda3\envs\wonder3d\lib\site-packages\torch\nn\modules\conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor...
I've trained the first-stage model for 30,000 iterations, bg_color is set to 'three_choices', and the resulting background color is still gray, and the grayness of each image is different. How...
I appreciate your wonderful work! the demo is excellent! However when I try to reproduce the result using your default settings (just running accelerate launch --config_file 8gpu.yaml train_mvdiffusion_image.py --config configs/train/stage1-mix-6views-lvis.yaml,...
For me it almost takes 3 ~ 5 minutes to process one sample. Would there be any alternative to faster generation?
 其他的地方都没有发现问题，就是在这个gradio图像界面生成六视角图片的时候超时，然后生成不出来，以下是报错代码： (wonder3d) C:\Users\26596\Wonder3D>python gradio_app.py A matching Triton is not available, some optimizations will not be enabled. Error caught was: No module named 'triton' C:\Users\26596\AppData\Local\conda\conda\envs\wonder3d\lib\site-packages\huggingface_hub\file_download.py:1132: FutureWarning: `resume_download` is deprecated and...
Hey, Thanks for your wonderful work! I‘d like to ask a question about fine-tuning on other dataset. Now I follow your rendering script to render another dataset but change the...
How do I use Wonder3D's 3D reconstruction with 6 different muti-views images (different poses, different angles)? Is it sufficient to only change the fixed_poses found in `Wonder3D/instant-nsr-pl/datasets/fixed_poses` ?
 请问这个报错是什么意思呢？怎么解决？
