InvokeAI/invokeai/backend
Lincoln Stein abe4dc8ac1 Add support for yet another textual inversion embedding format
- This PR adds support for embedding files that contain a single key
  "emb_params". The only example I know of this format is the
  "EasyNegative" embedding on HuggingFace, but there are certainly
  others.

- This PR also adds support for loading embedding files that have been
  saved in safetensors format.

- It also cleans up the code so that the logic of probing for and
  selecting the right format parser is clear.
2023-03-27 09:39:03 -04:00
..
config during migration do not overwrite symlinks 2023-03-05 08:40:12 -05:00
generator fix(backend): simple typing fixes 2023-03-26 17:07:03 +11:00
image_util all vestiges of ldm.invoke removed 2023-03-03 01:02:00 -05:00
model_management fix issue with embeddings being loaded twice 2023-03-25 10:45:03 -04:00
prompting backend..conditioning: remove code for legacy model 2023-03-09 18:15:12 -08:00
restoration remove legacy ldm code 2023-03-04 18:16:59 -08:00
stable_diffusion Add support for yet another textual inversion embedding format 2023-03-27 09:39:03 -04:00
training migrate to new HF diffusers cache location 2023-03-05 08:20:24 -05:00
util feat(backend): add image_to_dataURL util 2023-03-16 20:03:08 +11:00
web feat: use the predicted denoised image for previews 2023-03-09 20:28:06 -08:00
__init__.py do not reexport PipelineIntermediateState 2023-03-25 13:57:09 -04:00
args.py fix --png_compression command line argument 2023-03-14 00:24:05 -04:00
generate.py add restoration services to nodes 2023-03-11 17:00:00 -05:00
globals.py Unified spelling of Hugging Face 2023-03-05 07:30:35 -06:00
safety_checker.py restore NSFW checker 2023-03-11 16:16:44 -05:00