crapthings

@DN6 i've upgraded to 0.28.0, i still got this error, what is wrong? its working on 0.27.2 i try to load one, but still error ``` clip_model_id = 'laion/CLIP-ViT-B-32-laion2B-s34B-b79K' feature_extractor...

> Is it possible for you to host the `base.safetensors` checkpoint you're using on the HF Hub and share it? https://huggingface.co/crapthings/diffusers-issue/tree/main

> Hi @crapthings it appears that the `cond_stage_model.transformer.text_model.embeddings.position_ids` key is missing from your checkpoint, which is what `from_single_file` in `0.28.0` uses to identify the CLIP model in the checkpoint. >...

0.27.2 have such warning but model can still load ``` Some weights of the model checkpoint were not used when initializing CLIPTextModel: ['text_model.embeddings.position_ids'] ``` does this effect image quality?

@DN6 the main branch is working now~

yes taggui is great

this happend when negative embed present remove dimage https://github.com/damian0815/compel/assets/1147704/d91eb603-ab49-44bd-b9ec-2e26033b0d8b i do have textual inversion, https://github.com/damian0815/compel#textual-inversion-support when use DiffusersTextualInversionManager the quality degrade which i don't think its a compel problem, if...

> @damian0815 @pdoane > > and ,one more question. The lora tagger's words in prompt and negative prompt's text-inversion embedding with tagger's word, how do the "Comple" affect these trigger...