InstantMesh

InstantMesh copied to clipboard

texture problem

6

thanks for the great work. i have a problem when I am running the code on colab environment . the results given doesn't include the texture of the body. however...

AzizAydin97

AttributeError: 'WindowsPath' object has no attribute '_str'

3

here is the error,I dont know how to solve please help,I dont know if its diffusers library problem or here,can somehow help debug? ``` Seed set to 42 Loading diffusion...

hgftrdw45ud67is8o89

多卡运行

2

作者您好， 直接使用python app.py还是会只在一张卡上运行，且24Gtitan卡单卡运行会out of memory，是正常的吗

donutn

how to increase the quality of mesh

5

In the config file i see texture resolution does it really helps in improving the quality of meshes generated ? Please comment what all these parameters mean ? 1. texture_resolution...

sumanttyagi

Removal of logos/brand names

3

I tried to generate a 3d model of a hoodie and there were holes at places where there's a logo. Tried it on a couple different examples and same result,...

aditdesai

I have discovered some weird problem:the size of the generated obj is limited to 2m ×2m in blender,and there are some obvious grids on the texture. 

Asianfleet

Camera Augmentation in the released training code

2

I notice that the paper metioned "Considering that the multi-view images generated by Zero123++ may be inconsistent with their pre-defined camera poses, we also add random noise to the camera...

JINNMnm

/home/zhangzhilong/tools/anaconda/envs/instantmesh/lib/python3.10/site-packages/torch/include/torch/csrc/profiler/util.h:34:10: 致命错误：x86intrin.h：No such file or directory 34 | #include | ^~~~~~~~~~~~~ 编译中断。 ninja: build stopped: subcommand failed. Traceback (most recent call last): File "/home/zhangzhilong/tools/anaconda/envs/instantmesh/lib/python3.10/site-packages/torch/utils/cpp_extension.py", line 2100, in _run_ninja_build subprocess.run( File...

huahai2022

怎么配置数据集文件

2

您好，我运行了您的生成代码，发现运行的效果很不错，对您的模型很感兴趣，所以想继续深入了解一下训练代码，但是我发现您的配置文件中关于数据的文件配置项，data: target: src.data.objaverse.DataModuleFromConfig params: batch_size: 2 num_workers: 8 train: target: src.data.objaverse.ObjaverseData params: root_dir: data/objaverse meta_fname: filtered_obj_name.json input_image_dir: rendering_random_32views target_image_dir: rendering_random_32views input_view_num: 6 target_view_num: 4 total_view_n: 32 fov: 50 camera_rotation: true...

throb081

Error building extension 'nvdiffrast_plugin'

1

I found the same issue on jtydhr88 / ComfyUI-InstantMesh, but it's been archievied. I also read that in the past a user solved the same issue by updating to CUDA...

Obambaaaa