You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi,
I find that your FlowControlNet injects landmarks except flow. Through my experiments, I find that landmarks condition is actually stronger than flow condition. Below is my result:
output_flow.mp4
This is the result only using flow condition.
output_ldmk.mp4
This is the result only using landmark condition.
output_flow_ldmk.mp4
This is the result using landmark and flow condition simultaneously.
Can you explain this result? How can we get good results using only flow?
The text was updated successfully, but these errors were encountered:
To make the model work with only motion flow inputs, you'll need to retrain it. The current model relies on both motion flow and landmarks, so it won't function correctly if either input is missing.
We have trained two versions of our landmark-based model: one that uses landmarks as conditional inputs and one that doesn't. We found that using only motion flow can already achieve control, but incorporating landmarks further stabilizes and enhances controllability, and this does not violate with the hybrid control mechanism of our entire model.
Also, we will release the training codes soon after we finished submitting the camera-ready of ECCV.
Hi,
I find that your
FlowControlNet
injects landmarks except flow. Through my experiments, I find that landmarks condition is actually stronger than flow condition. Below is my result:output_flow.mp4
This is the result only using flow condition.
output_ldmk.mp4
This is the result only using landmark condition.
output_flow_ldmk.mp4
This is the result using landmark and flow condition simultaneously.
Can you explain this result? How can we get good results using only flow?
The text was updated successfully, but these errors were encountered: