frank-xwang / InstanceDiffusion

[CVPR 2024] Code release for "InstanceDiffusion: Instance-level Control for Image Generation"

Home Page:https://people.eecs.berkeley.edu/~xdwang/projects/InstDiff/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

about mask condition support

jsg921019 opened this issue · comments

Hello, I got another question,

according to this inference.py code, binary mask is reset to zero, erasing binary mask condition.

binay_masks = []
for i in range(len(locations) - len(binay_masks)):
binay_masks.append(np.zeros((512,512,1)))

Is there any reason this is set this way?

Hi, when generating images based on boxes or points without accompanying masks, we utilize all-zero masks as placeholders. If you have any further questions, please feel free to ask!