Lincoln Stein 4f44b64052 fix ckpt_convert module to work with dreambooth v2 models ... - Discord member @marcus.llewellyn reported that some civitai 2.1-derived checkpoints were not converting properly (probably dreambooth-generated): https://discord.com/channels/1020123559063990373/1078386197589655582/1078387806122025070 - @blessedcoolant tracked this down to a missing key that was used to derive vector length of the CLIP model used by fetching the second dimension of the tensor at "cond_stage_model.model.text_projection". His proposed solution was to hardcode a value of 1024. - On inspection, I found that the same second dimension can be recovered from key 'cond_stage_model.model.ln_final.bias', and use that instead. I hope this is correct; tested on multiple v1, v2 and inpainting models and they converted correctly. - While debugging this, I found and fixed several other issues: - model download script was not pre-downloading the OpenCLIP text_encoder or text_tokenizer. This is fixed. - got rid of legacy code in `ckpt_to_diffuser.py` and replaced with calls into `model_manager` - more consistent status reporting in the CLI.		2023-02-23 15:43:58 -05:00
..
__init__.py	(config) move configure_invokeai script to the config module for easier importing	2023-01-28 17:39:32 -05:00
invokeai_configure.py	fix ckpt_convert module to work with dreambooth v2 models	2023-02-23 15:43:58 -05:00
invokeai_update.py	(updater) style 'pip' progress to use dark background	2023-02-12 19:10:11 -05:00
model_install_backend.py	fix several issues with Windows installs	2023-02-23 00:49:59 -05:00
model_install.py	fix several issues with Windows installs	2023-02-23 00:49:59 -05:00
widgets.py	fix several issues with Windows installs	2023-02-23 00:49:59 -05:00