'SD3ClipModel' object has no attribute 't5_attention_mask'

[doogyhatts]

After updating ComfyUI for SD35L, it appears that the SD3ClipModel cannot access the t5_attention_mask attribute.
So the PixArt T5 from SD3 Clip, which outputs T5, cannot be used to input into the CLIP Text Encode, which previously worked.

(I realised this should be in the ExtraModels github instead.)