There are bug in diffusers with sdxl

Nobody has claimed this yet.

software version :

diffusers == 0. 29.2

## Bug1:

> AttributeError: 'CLIPTextModelOutput' object has no attribute 'pooler_output'

Because text_encoder is CLIPTextModel , it output is [transformers.modeling_outputs.BaseModelOutputWithPooling](https://huggingface.co/docs/transformers/v4.42.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling), so the output contain **pooler_output** .

But in text_encoder_2 is CLIPTextModelWithProjection, it output is [transformers.models.clip.modeling_clip.CLIPTextModelOutput](https://huggingface.co/docs/transformers/v4.42.0/en/model_doc/clip#transformers.CLIPTextModelWithProjection.forward.returns), it not have **'pooler_output'** ,and in your code
https://github.com/lllyasviel/LayerDiffuse_DiffusersCLI/blob/3061d9aed52a6c52a13fcf2b196c0fef4d727824/diffusers_kdiffusion_sdxl.py#L101, you try to get **pooler_output** in every text_encoder (both **text_encoder** and **text_encoder_2**), so it break!!

Start with diffusers_kdiffusion_sdxl.py around line 101 and compare the reported outputs from text_encoder and text_encoder_2 under diffusers 0.29.2. Run the SDXL path that triggers the error; done means it no longer raises the reported pooler_output AttributeError for the two encoders.

Written by the indexing model from the issue text.