-
Notifications
You must be signed in to change notification settings - Fork 5.9k
fix wan i2v pipeline bugs #10975
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
fix wan i2v pipeline bugs #10975
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
thanks!
@bot /style |
Style fixes have been applied. View the workflow run here. |
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you!
@@ -204,7 +222,7 @@ def _get_t5_prompt_embeds( | |||
def encode_image(self, image: PipelineImageInput): | |||
image = self.image_processor(images=image, return_tensors="pt").to(self.device) | |||
image_embeds = self.image_encoder(**image, output_hidden_states=True) | |||
return image_embeds.hidden_states[-1] | |||
return image_embeds.hidden_states[-2] |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@a-r-r-o-w the change of output is probably from here
@@ -137,7 +155,7 @@ def __init__( | |||
self, | |||
tokenizer: AutoTokenizer, | |||
text_encoder: UMT5EncoderModel, | |||
image_encoder: CLIPVisionModelWithProjection, | |||
image_encoder: CLIPVisionModel, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
need to match with here https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-480P-Diffusers/blob/main/model_index.json#L6
I fix some bug in wan i2v pipeline and add a new example