82978d3ee5
Update Combinatorial Setting Information
2023-07-06 11:28:21 -04:00
b250d1ec86
Merge branch 'main' into doc_updates_23
2023-07-06 11:24:42 -04:00
48258c4bb8
wip(docs): ELI5 Tutorial For Invocations
2023-07-06 11:24:05 -04:00
d5f90b1a02
Improved loading for UI ( #3667 )
...
* load images on gallery render
* wait for models to be loaded before you can invoke
---------
Co-authored-by: Mary Hipp <maryhipp@Marys-MacBook-Air.local >
2023-07-06 14:48:42 +00:00
7a0154a7b8
expose max_cache_size to invokeai-configure interface ( #3664 )
...
This PR allows the user to set the model manager cache size from within
the `invokeia-configure` TUI.
2023-07-07 01:58:22 +12:00
b229fe19aa
Merge branch 'main' into lstein/configure-max-cache-size
2023-07-07 01:52:12 +12:00
2595c1d86f
LoRA model loading fixes ( #3663 )
...
This PR enables model manager importation of diffusers-style .bin LoRAs.
However, since there is no backend support for this type of LoRA yet,
attempts to use them will result in an unimplemented error.
It closes #3636 and #3637
2023-07-07 01:09:13 +12:00
c2eb6c33b9
Merge branch 'main' into lstein/more-model-loading-fixes
2023-07-07 01:00:02 +12:00
94e38e9769
feat(ui): remove delete image button in gallery
...
it was really easy to accidentally click, just commented out, easy to add back or add a setting for it in the future
2023-07-06 22:35:50 +10:00
984121d682
only show delete icon if big enough
2023-07-06 22:35:50 +10:00
6f1268e2b1
Merge branch 'main' into lstein/more-model-loading-fixes
2023-07-07 00:32:22 +12:00
405054d802
feat: Add Embedding Picker to Linear UI ( #3654 )
2023-07-07 00:29:19 +12:00
a901a37433
feat(ui): improve no loaded loras UI
2023-07-06 22:26:54 +10:00
e09c07a97d
fix(ui): fix board auto-add
2023-07-06 22:25:05 +10:00
87feae959d
feat(ui): improve no loaded embeddings UI
2023-07-06 22:24:50 +10:00
fbd6b25b4d
feat(ui): improve ux on TI autcomplete
...
- cursor reinserts at the end of the trigger
- `enter` closes the select
- popover styling
2023-07-06 14:56:37 +10:00
267f0408bb
Update PROMPTS with Dynamic Prompts docs
2023-07-05 23:50:04 -04:00
cc8c34311c
Update LICENSE
2023-07-05 23:46:27 -04:00
2415dc1235
feat(ui): refactor embedding ui; now is autocomplete
2023-07-06 13:40:13 +10:00
a7cbcae176
expose max_cache_size to invokeai-configure interface
2023-07-05 20:59:57 -04:00
43c51ff157
Merge branch 'main' into lstein/more-model-loading-fixes
2023-07-05 20:48:15 -04:00
71dad6d404
Merge branch 'main' into ti-ui
2023-07-05 16:57:31 -04:00
c21bd806f0
default LoRA weight to 0.75
2023-07-05 16:54:23 -04:00
007d125e40
Update README.md
2023-07-05 16:53:37 -04:00
716d154957
Update LICENSE
2023-07-05 16:41:28 -04:00
685a47cc7d
fix crash during lora application
2023-07-05 16:40:47 -04:00
52498cc0b9
Put tokenizer and text encoder in same clip-vit-large-patch14 ( #3662 )
...
This PR fixes the migrate script so that it uses the same directory for
both the tokenizer and text encoder CLIP models. This will fix a crash
that occurred during checkpoint->diffusers conversions
This PR also removes the check for an existing models directory in the
target root directory when `invokeai-migrate3` is run.
2023-07-05 16:29:33 -04:00
cb947bcbf0
Merge branch 'main' into lstein/fix-migrate3-textencoder
2023-07-05 16:23:00 -04:00
bbfb5bb1d4
Remove hardcoded cuda device in model manager init ( #3624 )
...
There was a line in model_manager.py in which the GPU device was
hardcoded to "cuda". This has now been removed.
2023-07-05 16:22:45 -04:00
863336acbb
Recognize and load diffusers-style LoRAs (.bin)
...
Prevent double-reporting of autoimported models
- closes #3636
Allow autoimport of diffusers-style LoRA models
- closes #3637
2023-07-05 16:19:16 -04:00
90ae8ce26a
prevent model install crash "torch needs to be restarted with spawn"
2023-07-05 16:18:20 -04:00
9f9ce08e44
Merge branch 'main' into lstein/remove-hardcoded-cuda-device
2023-07-05 13:38:33 -04:00
17c5568661
build: remove web ui dist from gitignore ( #3650 )
...
The web UI should manage its own .gitignore
I think would explain why certain files were not making it into the pypi
release
2023-07-05 13:36:16 -04:00
94740e440d
Merge branch 'main' into build/gitignore
2023-07-05 13:35:54 -04:00
cf173b522b
allow clip-vit-large-patch14 text encoder to coexist with tokenizer in same directory
2023-07-05 13:14:41 -04:00
ea81ce9489
close modal when user clicks cancel ( #3656 )
...
* close modal when user clicks cancel
* close modal when delete image context cleared
---------
Co-authored-by: Mary Hipp <maryhipp@Marys-MacBook-Air.local >
2023-07-05 17:12:27 +00:00
8283b80b58
Fix ckpt scanning on conversion ( #3653 )
2023-07-06 05:09:13 +12:00
9e2d63ef97
Merge branch 'main' into fix/ckpt_convert_scan
2023-07-06 05:01:34 +12:00
dd946790ec
Fix loading diffusers ti ( #3661 )
2023-07-06 05:01:11 +12:00
0ac9dca926
Fix loading diffusers ti
2023-07-05 19:46:00 +03:00
acd3b1a512
build: remove web ui dist from gitignore
...
The web UI should manage its own .gitignore
2023-07-06 00:39:36 +10:00
e4d92da3a9
fix: Make space for icons in prompt box
2023-07-06 01:48:50 +12:00
9204b72383
feat: Make Embedding Picker a mini toggle
2023-07-06 01:45:00 +12:00
a556bf45bb
Merge branch 'main' into ti-ui
2023-07-05 23:42:48 +12:00
818616a0c5
fix(ui): fix prompt resize & style resizer ( #3652 )
2023-07-05 23:42:23 +12:00
8c9266359d
feat: Add Embedding Select To Linear UI
2023-07-05 23:41:15 +12:00
3b324a7d0a
Merge branch 'main' into fix/ui/fix-prompt-resize
2023-07-05 23:40:47 +12:00
c8cb43ff2d
Fix clip path in migrate script ( #3651 )
...
Update path for clip model according to path used in ckpt conversion and
invokeai-configure
2023-07-05 23:38:45 +12:00
ee042ab76d
Fix ckpt scanning on conversion
2023-07-05 14:18:30 +03:00
596c791844
fix(ui): fix prompt resize & style resizer
2023-07-05 21:02:31 +10:00
