DreamShaper upload

#41
by Lykon - opened

Add Diffusers weights converted from checkpoint

I am now getting the following error with this check-in.

Some weights of the model checkpoint at PATH were not used when initializing AutoencoderKL: ['encoder.mid_block.attentions.0.to_q.weight', 'encoder.mid_block.attentions.0.to_k.bias', 'decoder.mid_block.attentions.0.to_out.0.weight', 'encoder.mid_block.attentions.0.to_out.0.bias', 'encoder.mid_block.attentions.0.to_q.bias', 'decoder.mid_block.attentions.0.to_k.bias', 'decoder.mid_block.attentions.0.to_k.weight', 'encoder.mid_block.attentions.0.to_v.weight', 'decoder.mid_block.attentions.0.to_q.bias', 'encoder.mid_block.attentions.0.to_v.bias', 'decoder.mid_block.attentions.0.to_v.bias', 'decoder.mid_block.attentions.0.to_v.weight', 'decoder.mid_block.attentions.0.to_out.0.bias', 'decoder.mid_block.attentions.0.to_q.weight', 'encoder.mid_block.attentions.0.to_out.0.weight', 'encoder.mid_block.attentions.0.to_k.weight']

  • This IS expected if you are initializing AutoencoderKL from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
  • This IS NOT expected if you are initializing AutoencoderKL from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
    Some weights of AutoencoderKL were not initialized from the model checkpoint at C:\Users\sarus.cache\huggingface\hub\models--Lykon--DreamShaper\snapshots\2023b93d140bf68aceff85474bfbfa5bd5afbaaf\vae and are newly initialized: ['encoder.mid_block.attentions.0.key.bias', 'decoder.mid_block.attentions.0.key.weight', 'decoder.mid_block.attentions.0.key.bias', 'decoder.mid_block.attentions.0.value.weight', 'encoder.mid_block.attentions.0.proj_attn.weight', 'encoder.mid_block.attentions.0.query.bias', 'decoder.mid_block.attentions.0.query.bias', 'encoder.mid_block.attentions.0.value.bias', 'encoder.mid_block.attentions.0.proj_attn.bias', 'decoder.mid_block.attentions.0.proj_attn.weight', 'decoder.mid_block.attentions.0.value.bias', 'encoder.mid_block.attentions.0.key.weight', 'decoder.mid_block.attentions.0.query.weight', 'encoder.mid_block.attentions.0.query.weight', 'encoder.mid_block.attentions.0.value.weight', 'decoder.mid_block.attentions.0.proj_attn.bias']
    You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

you need to update your diffusers lib to 0.17.1 or use a previous commit with DS6 instead of DS6.31

How do we load a previous commit with diffusers library?

Lykon changed pull request status to closed

Sign up or log in to comment