Unverified Commit 7f323f0f authored by Xiangchendong's avatar Xiangchendong Committed by GitHub
Browse files

fix cogvideox autoencoder decode (#9569)


Co-authored-by: default avatarAryan <aryan@huggingface.co>
parent 61d37640
...@@ -1234,7 +1234,7 @@ class AutoencoderKLCogVideoX(ModelMixin, ConfigMixin, FromOriginalModelMixin): ...@@ -1234,7 +1234,7 @@ class AutoencoderKLCogVideoX(ModelMixin, ConfigMixin, FromOriginalModelMixin):
return self.tiled_decode(z, return_dict=return_dict) return self.tiled_decode(z, return_dict=return_dict)
frame_batch_size = self.num_latent_frames_batch_size frame_batch_size = self.num_latent_frames_batch_size
num_batches = num_frames // frame_batch_size num_batches = max(num_frames // frame_batch_size, 1)
conv_cache = None conv_cache = None
dec = [] dec = []
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment