diffusion-rig

diffusion-rig copied to clipboard

Thank you for your excellent work. I am very interested and will soon reference it. Could you please share with me the code for directly generating edited images using only...

gaoyixuan111

Controlling the eye pose

1

Inside the inference script, we can control the pose with [here](https://github.com/adobe-research/diffusion-rig/blob/d9b266102e1900032efc62e66a7f6c66dde5ff79/scripts/inference.py#L80C1-L81C1). Is it also possible to control or condition on the eye pose since FLAME has controllable eye joints? I...

atgao

Abnormal green spots for Lambertian rendering

1

First I want to show my sincere gratitude for this great work! When I was trying to train my own model of stage 1, learning face priors, I used 1024×1024...

mumukawayi

请问有开放训练好阶段一和阶段二的模型用于跑推理吗？

1

非常感谢博主的开源以及对科学的贡献。我貌似没看到有直接能跑推理的模型文件？请问能否提供该模型文件可以直接跑推理代码查看效果？非常感谢

FelixChan9527

test data album in stage2

1

Thanks for your incredible work. Could you please provide your data album in stage2 for me for research purpose?

Kelu007

How to generate myself expression face?

2

when I run the scrpit you provide the scripts,I find it just swap the face,but I want to edit the expression .

sunzhe09

meanshape

1

大佬，请问meanshape是什么作用，为何我第一阶段生成效果很离谱

hamigualisingl

Question about transferring expression.

1

https://github.com/adobe-research/diffusion-rig/blob/d9b266102e1900032efc62e66a7f6c66dde5ff79/scripts/inference.py#L82 Hi, thanks for sharing your great work. Why first three dimension of pose codes are changed when transferring expression.

NickChang97

Hello, first of all, thank you so much for your open source. I am very interested in your work.

4

I have finished the finetuning exm in my personal album flowing your Redme.md. The result remains good and fantastic! But I have a question: as stated in your paper, the...

thebestYezhang