showlab / Tune-A-Video

[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
https://tuneavideo.github.io
Apache License 2.0
4.15k stars 377 forks source link

What does this mean: “encoder_hidden_states = encoder_hidden_states”? #77

Open XuejiFang opened 1 year ago

XuejiFang commented 1 year ago

/Tune-A-Video/tuneavideo/models/attention.py line 276

encoder_hidden_states is just reassigned toencoder_hidden_states without even changing the name of the variable. What does that mean?