yjhong89

I use voxceleb2, bupt, vggface2 - Get FAN landmarks and skinmask - Did landmark preprocess (cleaning) for every image as paper mentioned.

@sangeetajha 1. I use another skin segmentation mask. Acturally if rendering works well, uv_mask would work without skinmask 2. I've used all images per person, not actually select 5 images...

@ccyyatnet My configurations are 1. Make object file of fg2018 images (Subset_2D_FG2018 2000 images (HQ 656, LQ 1344)) using [TestData class](https://github.com/YadiraF/DECA/blob/7750da206f0f957c354f4a17d3f95c65b1ca15b4/decalib/datasets/datasets.py#L47), same crop and scale arguments. 2. Compute distances referenced...

@choyingw, thank you!

How did you make this files ? I downloaded AFLW2000 from [here](http://www.cbsr.ia.ac.cn/users/xiangyuzhu/projects/3DDFA/main.htm) and there is only mat file containing Pose param and pts3d. Is Pose param containing yaw/pitch/roll ? https://github.com/choyingw/SynergyNet/blob/d34e4afd6adbb9d5339366e3e74cde709d5895ae/benchmark.py#L189

@choyingw Thank you!

@choyingw Sorry for bothering you agian. As you mentioned and based on script, I followed this code (https://github.com/shamangary/FSA-Net/blob/master/data/type1/TYY_create_db_type1.py) and remove data which have yaw angles outside the range [-99, 99]...

When I change the code as below, the number of filtered samples is exactly 31 ``` pose_para = mat_contents["Pose_Para"][0] pitch = pose_para[0] * 180 / np.pi yaw = pose_para[1] *...

Set `default=True` of this argument. (Skipping test at the end of training) - https://github.com/Stability-AI/generative-models/blob/9d759324e914de6c96dbd1468b3a4a50243c6528/main.py#L98

Is there any in-paint configs for SDXL 1.0 (base)?