Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[BUG] #222

Closed
killporter opened this issue Sep 4, 2023 · 1 comment
Closed

[BUG] #222

killporter opened this issue Sep 4, 2023 · 1 comment

Comments

@killporter
Copy link

i'm trying to run the model in comfy, but i get missing {'first_stage_model.decoder.mid.attn_1.proj_out.bias', 'first_stage_model.decoder.mid.attn_1.k.weight', 'first_stage_model.decoder.mid.attn_1.proj_out.weight', 'first_stage_model.encoder.mid.attn_1.v.bias', 'first_stage_model.decoder.mid.attn_1.v.weight', 'first_stage_model.encoder.mid.attn_1.q.bias', 'first_stage_model.encoder.mid.attn_1.v.weight', 'first_stage_model.encoder.mid.attn_1.q.weight', 'first_stage_model.encoder.mid.attn_1.k.weight', 'first_stage_model.encoder.mid.attn_1.k.bias', 'first_stage_model.decoder.mid.attn_1.q.bias', 'first_stage_model.decoder.mid.attn_1.v.bias', 'first_stage_model.decoder.mid.attn_1.k.bias', 'first_stage_model.decoder.mid.attn_1.q.weight', 'first_stage_model.encoder.mid.attn_1.proj_out.weight', 'first_stage_model.encoder.mid.attn_1.proj_out.bias'}
missing {'cond_stage_model.text_projection', 'cond_stage_model.logit_scale'}
left over keys: dict_keys(['first_stage_model.encoder.mid.attn_1.to_q.weight', 'first_stage_model.encoder.mid.attn_1.to_q.bias', 'first_stage_model.encoder.mid.attn_1.to_k.weight', 'first_stage_model.encoder.mid.attn_1.to_k.bias', 'first_stage_model.encoder.mid.attn_1.to_v.weight', 'first_stage_model.encoder.mid.attn_1.to_v.bias', 'first_stage_model.encoder.mid.attn_1.to_out.0.weight', 'first_stage_model.encoder.mid.attn_1.to_out.0.bias', 'first_stage_model.decoder.mid.attn_1.to_q.weight', 'first_stage_model.decoder.mid.attn_1.to_q.bias', 'first_stage_model.decoder.mid.attn_1.to_k.weight', 'first_stage_model.decoder.mid.attn_1.to_k.bias', 'first_stage_model.decoder.mid.attn_1.to_v.weight', 'first_stage_model.decoder.mid.attn_1.to_v.bias', 'first_stage_model.decoder.mid.attn_1.to_out.0.weight', 'first_stage_model.decoder.mid.attn_1.to_out.0.bias', 'cond_stage_model.transformer.text_model.embeddings.position_ids'])
loaded straight to GPU

ComfyUI_00334_

it was trained with the ed2 repo

the problem happens in automatics as well, it generates the image well, but in the end, it just outputs a noise paste

@victorchall
Copy link
Owner

ED2 now only produces safetensors files and I think this has resolved issues loading files into auto1111.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants