This started as a test workflow to test hand fixing... I just dont know when to stop sometimes. I needed a break from the videos workflow.
Tips :
Each pose is not limited to one person, 2 people, or a crowd per pose works, lowering the image ref helps in this case.
Background people can be picked up and included sometimes.
Slightly overlapping subjects is possible, can produce interactions.
V1 works entirely different from beta. I think both have uses so beta can stay up
Image Composer v1
Features
- Poses generated from your images
- Combine 3 poses into one image.
- Select Ip refs for each pose
- Openpose/lineart and aux (densepose/segs/etc) pose generations
描述:
训练词语:
名称: ipAdaptorImage_beta.zip
大小 (KB): 730
类型: Archive
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
