Lincoln Stein c87497fd54 record model_variant in t2i and clip_vision configs (#5989) ... - Move base of t2i and clip_vision config models to DiffusersBase, which contains a field to record the model variant (e.g. "fp16") - This restore the ability to load fp16 t2i and clip_vision models - Also add defensive coding to load the vanilla model when the fp16 model has been replaced (or more likely, user's preferences changed since installation) Co-authored-by: Lincoln Stein <lstein@gmail.com>		2024-03-19 20:14:12 +00:00
..
load	record model_variant in t2i and clip_vision configs (#5989)	2024-03-19 20:14:12 +00:00
metadata	fix(mm): config.json to indicates diffusers model	2024-03-13 21:02:29 +11:00
util	install model if diffusers or single file, cleaned up backend logic to not mess with existing model install	2024-03-13 21:02:29 +11:00
__init__.py	chore: ruff	2024-03-01 10:42:33 +11:00
config.py	record model_variant in t2i and clip_vision configs (#5989)	2024-03-19 20:14:12 +00:00
convert_ckpt_to_diffusers.py	Remove core safetensors->diffusers conversion models	2024-03-17 19:13:18 -04:00
libc_util.py	Tidy names and locations of modules	2024-03-01 10:42:33 +11:00
merge.py	fix(config): use new get_config across the app, use correct settings	2024-03-19 09:24:28 +11:00
probe.py	Pull format type setting out of model_type if statement	2024-03-19 01:16:11 -04:00
search.py	docs(mm): format docstrings for ModelSearch	2024-03-10 12:09:47 +11:00