LHM

LHM copied to clipboard

support gender configuration

1

Hello, thank you for your great work! I’m trying to perform novel pose synthesis (animation), but I only have SMPL-X parameters for male and female models, not the neutral one....

amcs-echo-0

When will the training code be released?

1

XiaoQiangSHI

训练代码开源计划—Training Code Open Source Plan

1

嗨，感谢分享这项出色的成果！ 我想知道你是否有发布训练代码的计划——如果有的话，能否分享一下大概什么时候可以发布？ 再次感谢你们的贡献！ Hi, thanks for sharing this great work! I was wondering if you have any plans to release the training code — and if so, could you share...

CzJamesZhao

部署首次运行LHM-MINI报错 assert torch_missing == missing, f"{torch_missing} != {missing}"

6

--- Querying model: LHM-MINI --- Step 1: Checking local ModelScope cache... Checking cache for ModelScope model: Damo_XR_Lab/LHM-MINI ModelScope model base path /root/LHM-main/pretrained_models/Damo_XR_Lab/LHM-MINI not found in local cache. Info: Not found...

daiya1235

为什么显示我的模型匹配不上呢？

13

 执行python app.py为什么显示下载的models--3DAIGC--LHM-1B-HF模型缺少层，匹配不上呢？报错

HarrySZUNKD

Thanks for your great work. As mentioned in the paper, for the 2k2k dataset, 30 azimuthal views per model with uniform angular spacing are rendered. Could you please provide more...

amcs-echo-0

Training Code

1

Can you tell me when the training code will probably be released?I'm very much looking forward to it.

xiaoTan12

现在单个图片侧面与背面生成效果不太行，支持多视图生成吗？

4

类似混元3d,2-4视图或更多

wing158

推理重建出来的图像与原始图像的空间位置不能对齐

3

使用video2motion准备原始的motion参数， pad_ratio设置为0，然后使用推理脚本(inference.sh)推理出的同形象的图像和原始图像的空间位置不能够严格对齐，请教大家

Guan-chen-lu

SMPLX upsample/densify difference

8

Hi, good job for the great work! I have some questions regarding to the SMPLX mesh upsample/densify strategy. In Expressive Avatar, it uses pytorch3d subdivide to upsample the mesh, while...

MakingBigNewsWallace