233869b56a
Mac MPS FP16 fixes
...
This PR is to allow FP16 precision to work on Macs with MPS. In addition, it centralizes the torch fixes/workarounds
required for MPS into a new backend utility file `mps_fixes.py`. This is conditionally imported in `api_app.py`/`cli_app.py`.
Many MANY thanks to StAlKeR7779 for patiently working to debug and fix these issues.
2023-07-04 18:10:53 -04:00
96bf92ead4
add the import model router
2023-07-04 14:35:47 +10:00
cfd09214d3
Merge branch 'main' into lstein/fix-vae-conversion-crash
2023-07-03 14:03:13 -04:00
10d513c5f7
add runtime root path to relative vaes and other submodels
2023-07-03 11:19:33 -04:00
2465c7987b
Revert "restore 3.9 compatibility by replacing | with Union[]"
...
This reverts commit 76bafeb99e
2023-07-03 10:56:41 -04:00
76bafeb99e
restore 3.9 compatibility by replacing | with Union[]
2023-07-03 10:55:04 -04:00
06694d465d
add missing k-* legacy sampler names to init file migrate list
2023-07-01 21:45:14 -04:00
c74bb5cdbf
Merge branch 'main' into lstein/fix-vae-convert
2023-07-01 11:18:21 +12:00
1347fc2f00
fix incorrect VAE config file path during conversion of ckpts
2023-06-30 19:14:06 -04:00
5be1e71d1b
Merge branch 'main' into lstein/fix-model-scan-on-rel-root
2023-06-29 17:54:12 +12:00
30a917f70c
Fix Typo in migrate_to_3.py
2023-06-29 14:45:55 +10:00
ace4f6d586
fix duplicate model key addition when root directory is a relative path
2023-06-28 17:02:03 -04:00
ac46b129bf
Merge branch 'main' into feat/lora_model_patch
2023-06-28 22:43:58 +03:00
79fc708580
warn but do not crash when model scan finds random cruft in models directory
2023-06-28 15:26:42 -04:00
e8ed0fad6c
autoimport from embedding/controlnet/lora folders designated in startup file
2023-06-27 12:30:53 -04:00
044fe6bb20
remove dangling debug statement
2023-06-26 17:48:06 -04:00
823e098b7c
prompt user for prediction type when autoimporting a v2 model without .yaml file
...
don't ask user for prediction type of a config.yaml provided
2023-06-26 16:30:34 -04:00
011adfc958
merge with main
2023-06-26 13:53:59 -04:00
befd95eb19
rename root_dir to root_path attributes to emphasize return of a Path
2023-06-26 13:52:25 -04:00
a2ddb3823b
fix add_model() logic
2023-06-26 13:33:38 -04:00
7b97639961
Merge branch 'main' into lstein/installer-for-new-model-layout
2023-06-26 01:24:30 -04:00
91c3a58fb6
Fix lycoris layers init
2023-06-26 04:33:37 +03:00
5cebf67ee4
Apply lora by patching lora instead of hooks
2023-06-26 03:57:33 +03:00
1ba94a92b3
Fixes
2023-06-26 03:54:42 +03:00
23c22ac933
Refactor logic/small fixes
2023-06-26 03:07:54 +03:00
160b5d7992
add support for an autoimport models directory scanned at startup time
2023-06-25 18:50:15 -04:00
c91d1eacba
Merge branch 'lstein/installer-for-new-model-layout' of github.com:invoke-ai/InvokeAI into lstein/installer-for-new-model-layout
2023-06-25 16:04:48 -04:00
60b37b7ff4
fix model manager documentation
2023-06-25 16:04:43 -04:00
a3c22b5fe6
Remove upcast_attention and prediction_type from stable diffusion model logic, fix ckpt conversion according to this
2023-06-25 21:06:22 +03:00
c5faffc18b
Merge branch 'main' of github.com:invoke-ai/InvokeAI into feat/controlnet-control-modes
...
Only "real" conflicts were in:
invokeai/frontend/web/src/features/controlNet/components/ControlNet.tsx
invokeai/frontend/web/src/features/controlNet/store/controlNetSlice.ts
2023-06-24 17:05:57 -07:00
c3c4a71173
implemented Stalker's suggested improvements
2023-06-24 12:37:26 -04:00
ba1371a88f
rename ModelType.Pipeline to ModelType.Main
2023-06-24 11:45:49 -04:00
539d1f3bde
remove redundant prediction_type and attention_upscaling flags
2023-06-23 16:54:52 -04:00
466ec3ab5e
add router API support for model manager heuristic_import()`
2023-06-23 16:35:39 -04:00
54b74427f4
adjust for change in list_models() API
2023-06-23 14:13:37 -04:00
58d1857ab6
merge with main
2023-06-23 13:57:25 -04:00
3043af4620
implement vae passthru
2023-06-23 13:56:30 -04:00
56bd873d7a
make relative model paths work in model manager
2023-06-23 10:52:59 -04:00
5aaaaf64a1
Fix ckpt conversion
2023-06-23 17:29:54 +03:00
9140e2c0f2
Merge branch 'main' into fix/vae_conversion
2023-06-23 15:03:59 +03:00
a910403003
correctly migrate models that have relative paths
2023-06-22 21:10:31 -04:00
c7b7e087e4
Merge branch 'main' into lstein/installer-for-new-model-layout
2023-06-23 01:45:05 +01:00
d65c833b90
migration now integrated into invokeai-configure
2023-06-22 16:44:55 -04:00
33b04f6386
migration script working well
2023-06-22 15:47:12 -04:00
b937b7da01
feat(models): update model manager service & route to return list of models
2023-06-22 17:34:12 +10:00
21245a0fb2
Set model type to const value in openapi schema, add model format enums to model schema(as they not not referenced in case of Literal definition)
2023-06-22 16:51:53 +10:00
da566b59e8
Update model format field to use enums
2023-06-22 16:51:53 +10:00
e4dc9c5a04
Rename format to model_format(still named format when work with config)
2023-06-22 16:51:53 +10:00
aceadacad4
Remove default model logic
2023-06-22 16:51:53 +10:00
727293d722
fix: 2.1 models breaking generation
...
Co-Authored-By: StAlKeR7779 <7768370+StAlKeR7779@users.noreply.github.com >
2023-06-22 16:42:59 +10:00
