Question about I2V
#423
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
{{ message }}
-
In the diffusers I2V pipeline, I found that cfg only dropped the text prompt. However, in train_cogvideox_image_to_video_lora.py, I found that only image_latents were dropped without text prompt. What kind of drop mode is used in I2V pre-training of cogvideox？
Beta Was this translation helpful? Give feedback.
All reactions