CypherQube

Training on the v.2.0 512 weights creates the wrong .yaml file

9

Training on the v.2.0 512 weights creates the wrong .yaml After training on the v2.0 512 weights then testing the new weights it generates tan images exactly like it is...

SDXL, is this an issue? "missing {'cond_stage_model.clip_g.transformer.text_model.embeddings.position_ids'}"

1

building MemoryEfficientAttnBlock with 512 in_channels... missing {'cond_stage_model.clip_g.transformer.text_model.embeddings.position_ids'}

Can't Train without a huggingface token even when using a local model

1

Can't start training without a huggingface token even when using a local model