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
SD3 pipeline currently uses dual CLIP (L+G) only, zero-padding the T5 portion of encoder_hidden_states. Adding T5-XXL (256 token seq len) would significantly improve text comprehension for complex prompts.
SD3 pipeline currently uses dual CLIP (L+G) only, zero-padding the T5 portion of encoder_hidden_states. Adding T5-XXL (256 token seq len) would significantly improve text comprehension for complex prompts.