Lincoln Stein
0b11f309ca
instead of crashing when a corrupted model is detected, warn and move on
2023-08-11 15:05:14 -04:00
Ryan Dick
6a8eb392b2
Add support for loading SDXL LoRA weights in diffusers format.
2023-08-11 14:40:22 -04:00
Sergey Borisov
f3ae52ff97
Fix error at high denoising_start, fix unipc(cpu_only)
2023-08-11 15:46:16 +03:00
blessedcoolant
231e665675
Merge branch 'main' into feat/refactor_generation_backend
2023-08-11 20:53:38 +12:00
Sergey Borisov
c0c2ab3dcf
Format by black
2023-08-11 03:20:56 +03:00
Sergey Borisov
56023bc725
Add support for LyCORIS IA3 format
2023-08-11 02:08:08 +03:00
Lincoln Stein
d0fee93aac
round slider values to nice numbers
2023-08-10 18:00:45 -04:00
Lincoln Stein
1bfe9835cf
clip cache settings to permissible values; remove redundant imports in install __init__ file
2023-08-10 18:00:45 -04:00
Kent Keirsey
f6522c8971
Merge branch 'main' into fix/detect-more-loras
2023-08-10 17:33:16 -04:00
Lincoln Stein
a969707e45
prevent vae: '' from crashing model
2023-08-10 17:33:04 -04:00
Sergey Borisov
17fed1c870
Fix merge conflict errors
2023-08-10 05:03:33 +03:00
Sergey Borisov
ade78b9591
Merge branch 'main' into feat/refactor_generation_backend
2023-08-10 04:32:16 +03:00
Lincoln Stein
cd2c688562
Merge branch 'main' into refactor/remove_unused_pipeline_methods
2023-08-09 17:26:09 -04:00
Lincoln Stein
2f68a1a76c
use Stalker's simplified LoRA vector-length detection code
2023-08-09 09:21:29 -04:00
Lincoln Stein
7d4ace962a
Merge branch 'main' into fix/detect-more-loras
2023-08-09 08:48:27 -04:00
Millun Atluri
8b39b67ec7
Merge branch 'main' into feat/select-vram-in-config
2023-08-09 12:17:27 +10:00
StAlKeR7779
dfb41d8461
Merge branch 'main' into bugfix/autodetect-sdxl-ckpt-config
2023-08-09 03:57:44 +03:00
Sergey Borisov
e98f7eda2e
Fix total_steps in generation event, order field added
2023-08-09 03:34:25 +03:00
Sergey Borisov
f7aec3b934
Move conditioning class to backend
2023-08-08 23:33:52 +03:00
Lincoln Stein
4d5169e16d
Merge branch 'main' into feat/select-vram-in-config
2023-08-08 13:50:02 -04:00
Sergey Borisov
a7e44678fb
Remove legacy/unused code
2023-08-08 20:49:01 +03:00
Lincoln Stein
f56f19710d
allow user to interactively resize screen before UI runs
2023-08-08 12:27:25 -04:00
Sergey Borisov
96b7248051
Add mask to l2l
2023-08-08 18:50:36 +03:00
Lincoln Stein
13347f6aec
blackified
2023-08-08 08:33:30 -07:00
Lincoln Stein
a9bf387e5e
turned on Pydantic validate_assignment
2023-08-08 08:33:30 -07:00
Lincoln Stein
8258c87a9f
refrain from writing deprecated legacy options to invokeai.yaml
2023-08-08 08:33:30 -07:00
Lincoln Stein
a8d3e078c0
Merge branch 'main' into fix/detect-more-loras
2023-08-08 10:42:45 -04:00
Lincoln Stein
6ed7ba57dd
Merge branch 'main' into bugfix/fix-model-updates
2023-08-08 09:05:25 -04:00
Lincoln Stein
f0918edf98
improve error reporting on unrecognized lora models
2023-08-07 16:38:58 -04:00
Lincoln Stein
22f7cf0638
add stalker's complicated but effective code for finding token vector length in LoRAs
2023-08-07 16:19:57 -04:00
Kevin Turner
25c669b1d6
Merge remote-tracking branch 'origin/main' into refactor/remove_unused_pipeline_methods
2023-08-07 13:03:10 -07:00
Lincoln Stein
0fd13d3604
Merge branch 'main' into feat/select-vram-in-config
2023-08-07 15:51:59 -04:00
Lincoln Stein
72a3e776b2
fix logic error introduced in PR 4109
2023-08-07 15:38:22 -04:00
Lincoln Stein
af044007d5
pick correct config file for sdxl models
2023-08-07 15:19:49 -04:00
Sergey Borisov
1db2c93f75
Fix preview, inpaint
2023-08-07 21:27:32 +03:00
Sergey Borisov
2539e26c18
Apply denoising_start/end, add torch-sdp to memory effictiend attention func
2023-08-07 19:57:11 +03:00
Sergey Borisov
b0738b7f70
Fixes, zero tensor for empty negative prompt, remove raw prompt node
2023-08-07 18:37:06 +03:00
Lincoln Stein
f3d3316558
probe LoRAs that do not have the text encoder
2023-08-06 16:00:53 -04:00
Kevin Turner
5bfd6cb66f
Merge remote-tracking branch 'origin/main' into refactor/model_manager_instantiate
...
# Conflicts:
# invokeai/backend/model_management/model_manager.py
2023-08-05 22:02:28 -07:00
Kevin Turner
59caff7ff0
refactor(diffusers_pipeline): remove unused img2img wrappers 🚮
...
invokeai.app no longer needs this as a single method, as it builds on latents2latents instead.
2023-08-05 21:50:52 -07:00
Kevin Turner
6487e7d906
refactor(diffusers_pipeline): remove unused ModelGroup 🚮
...
orphaned since #3550 removed the LazilyLoadedModelGroup code, probably unused since ModelCache took over responsibility for sequential offload somewhere around #3335 .
2023-08-05 21:50:52 -07:00
Kevin Turner
77033eabd3
refactor(diffusers_pipeline): remove unused precision 🚮
2023-08-05 21:50:52 -07:00
Kevin Turner
b80abdd101
refactor(diffusers_pipeline): remove unused image_from_embeddings 🚮
2023-08-05 21:50:52 -07:00
Kevin Turner
006d782cc8
refactor(diffusers_pipeline): tidy imports 🚮
2023-08-05 21:50:52 -07:00
psychedelicious
66f524cae7
fix(mm): fix a lot of typing issues
...
Most fixes are just things being typed as `str` but having default values of `None`, but there are some minor logic changes.
2023-08-06 14:09:04 +10:00
Sergey Borisov
9aaf67c5b4
wip
2023-08-06 05:05:25 +03:00
Kevin Turner
44bf308192
test(model_management): add a couple tests for _get_model_path
2023-08-05 15:22:23 -07:00
Kevin Turner
65ed224bfc
Merge branch 'main' into refactor/model_manager_instantiate
2023-08-04 21:34:38 -07:00
psychedelicious
b6e369c745
chore: black
2023-08-05 12:28:35 +10:00
gogurtenjoyer
ecabfc252b
devices.py - Update MPS FP16 check to account for upcoming MacOS Sonoma
...
float16 doesn't seem to work on MacOS Sonoma due to further changes with Metal. This'll default back to float32 for Sonoma users.
2023-08-05 12:28:35 +10:00
psychedelicious
da96a41103
Merge branch 'main' into feat/select-vram-in-config
2023-08-05 12:11:50 +10:00
psychedelicious
eb6c317f04
chore: black
2023-08-05 12:05:24 +10:00
psychedelicious
6d7223238f
fix: fix typo in message
2023-08-05 12:05:24 +10:00
Damian Stewart
8607d124c5
improve message about the consequences of the --ignore_missing_core_models flag
2023-08-05 12:05:24 +10:00
Damian Stewart
23497bf759
add --ignore_missing_core_models CLI flag to bypass checking for missing core models
2023-08-05 12:05:24 +10:00
Kevin Turner
b10cf20eb1
Merge branch 'main' into refactor/model_manager_instantiate
...
# Conflicts:
# invokeai/backend/model_management/model_manager.py
2023-08-04 18:28:18 -07:00
StAlKeR7779
9bacd77a79
Merge branch 'main' into bugfix/fp16-models
2023-08-05 01:42:43 +03:00
Lincoln Stein
1b158f62c4
resolve vae overrides correctly
2023-08-04 18:24:47 -04:00
Lincoln Stein
6ad565d84c
folded in changes from 4099
2023-08-04 18:24:47 -04:00
Sergey Borisov
04229082d6
Provide ti name from model manager, not from ti itself
2023-08-04 18:24:47 -04:00
Sergey Borisov
f0613bb0ef
Fix merge conflict resolve - restore full/diff layer support
2023-08-04 19:53:27 +03:00
StAlKeR7779
0e9f92b868
Merge branch 'main' into feat/sdxl_lora
2023-08-04 19:22:13 +03:00
psychedelicious
7d0cc6ec3f
chore: black
2023-08-05 02:04:22 +10:00
Sergey Borisov
2f8b928486
Add support for diff/full lora layers
2023-08-05 02:04:22 +10:00
Lincoln Stein
1d5d187ba1
model probe detects sdxl lora models
2023-08-04 11:44:56 -04:00
Sergey Borisov
1ac14a1e43
add sdxl lora support
2023-08-04 11:44:56 -04:00
Lincoln Stein
1deca89fde
Merge branch 'main' into feat/select-vram-in-config
2023-08-03 19:27:58 -04:00
Lincoln Stein
446fb4a438
blackify
2023-08-03 19:24:23 -04:00
Lincoln Stein
ab5d938a1d
use variant instead of revision
2023-08-03 19:23:52 -04:00
Brandon
9942af756a
Merge branch 'main' into remove-onnx-model-check-from-pipeline-download
2023-08-03 10:10:51 -04:00
Kevin Turner
91ebf9f76e
Merge branch 'main' into refactor/model_manager_instantiate
2023-08-02 19:01:21 -07:00
Lincoln Stein
e080fd1e08
blackify
2023-08-03 11:25:20 +10:00
Lincoln Stein
eeef1e08f8
restore ability to convert merged inpaint .safetensors files
2023-08-03 11:25:20 +10:00
Kevin Turner
02d2cc758d
Merge branch 'main' into refactor/model_manager_instantiate
2023-08-02 17:11:23 -07:00
Damian Stewart
4e0949fa55
fix .swap() by reverting improperly merged @classmethod change
2023-08-03 10:00:43 +10:00
Lincoln Stein
ec48779080
blackify
2023-08-02 14:28:19 -04:00
Lincoln Stein
5de42be4a6
reduce VRAM cache default; take max RAM from system
2023-08-02 14:27:13 -04:00
Lincoln Stein
29ac252501
blackify
2023-08-02 09:44:06 -04:00
Lincoln Stein
880727436c
fix default vram cache size calculation
2023-08-02 09:43:52 -04:00
Lincoln Stein
77c5c18542
add slider for VRAM cache
2023-08-02 09:11:24 -04:00
Brandon Rising
ed76250dba
Stop checking for unet/model.onnx when a model_index.json is detected
2023-08-02 07:21:21 -04:00
Lincoln Stein
4d22cafdad
Installer should download fp16 models if user has specified 'auto' in config
...
- Closes #4127
2023-08-01 22:06:27 -04:00
Kevin Turner
5998509888
Merge branch 'main' into refactor/model_manager_instantiate
2023-08-01 11:09:43 -07:00
Kent Keirsey
746afcd235
Merge branch 'main' into feat/onnx
2023-07-31 16:56:34 -04:00
Brandon Rising
aeac557c41
Run python black, point out that onnx is an alpha feature in the installer
2023-07-31 16:47:48 -04:00
Kevin Turner
bacdf985f1
doc(model_manager): docstrings
2023-07-31 09:16:32 -07:00
Brandon Rising
f5ac73b091
Merge branch 'main' into feat/onnx
2023-07-31 10:58:40 -04:00
psychedelicious
2c07f54b6e
Merge branch 'main' into fix-optional
2023-07-31 16:31:01 +10:00
Kevin Turner
adfd1e52f4
refactor(model_manager): avoid copy/paste logic
2023-07-30 11:53:12 -07:00
Kevin Turner
0e48c98330
Merge remote-tracking branch 'origin/main' into refactor/model_manager_instantiate
...
# Conflicts:
# invokeai/backend/model_management/model_manager.py
2023-07-30 11:33:13 -07:00
Lincoln Stein
83d3f2347e
fix "unrecognized arguments: --yes" bug on unattended upgrade
2023-07-30 11:07:06 -04:00
Alexandre Macabies
50e00feceb
Add missing Optional on a few nullable fields.
2023-07-30 16:25:12 +02:00
Lincoln Stein
2537ff0280
Merge branch 'main' into bugfix/model-manager-rel-paths
2023-07-30 08:17:36 -04:00
Lincoln Stein
e20c4dc1e8
blackified
2023-07-30 08:17:10 -04:00
Lincoln Stein
ac84a9f915
reenable display of autoloaded models
2023-07-30 08:05:05 -04:00
Lincoln Stein
844578ab88
fix lora loading crash
2023-07-30 07:57:10 -04:00
Kevin Turner
ff1c40747e
lint: formatting
2023-07-29 20:02:31 -07:00
Lincoln Stein
73f3b7f84b
remove dangling comment
2023-07-29 17:32:33 -04:00
Lincoln Stein
348bee8981
blackified
2023-07-29 17:30:54 -04:00
Lincoln Stein
e82eb0b9fc
add correct optional annotation to precision arg
2023-07-29 17:30:21 -04:00
Lincoln Stein
1de783b1ce
fix mistake in indexing flat_ema_key
2023-07-29 17:20:26 -04:00
Lincoln Stein
3f9105be50
make convert script respect setting of use_ema in config file
2023-07-29 17:17:45 -04:00
Lincoln Stein
2a2d988928
convert script handles more ckpt variants
2023-07-29 15:28:39 -04:00
Kevin Turner
ccceb32a85
lint: formatting
2023-07-29 11:50:04 -07:00
Lincoln Stein
72c519c6ad
fix incorrect key construction
2023-07-29 13:51:47 -04:00
Lincoln Stein
24b19166dd
further refactoring
2023-07-29 13:13:22 -04:00
Lincoln Stein
0fb7328022
blackify code
2023-07-29 13:00:43 -04:00
Lincoln Stein
99daa97978
more refactoring; fixed place where rel conversion missed
2023-07-29 13:00:07 -04:00
Lincoln Stein
982a568349
blackify pr
2023-07-29 10:47:55 -04:00
Lincoln Stein
d79d5a4ff7
modest refactoring
2023-07-29 10:45:26 -04:00
Lincoln Stein
9968ff2893
fix relative model paths to be against config.models_path, not root
2023-07-29 10:30:27 -04:00
Kevin Turner
86b8b69e88
internal(ModelManager): add instantiate method
2023-07-28 22:30:25 -07:00
Kevin Turner
bc9a5038fd
refactor(ModelManager): factor out get_model_path
2023-07-28 22:29:36 -07:00
Kevin Turner
b163ae6a4d
refactor(ModelManager): factor out get_model_config
2023-07-28 21:30:20 -07:00
Kevin Turner
dca685ac25
refactor(ModelManager): refactor rescan-on-miss to exists() method
2023-07-28 21:11:00 -07:00
Kevin Turner
e70bedba7d
refactor(ModelManager): factor out _get_implementation method
2023-07-28 21:03:27 -07:00
Brandon Rising
390ce9f249
Fix onnx installer
2023-07-28 16:54:03 -04:00
Brandon Rising
a2aa66f43a
Run Python black
2023-07-28 10:00:09 -04:00
Brandon Rising
da751da3dd
Merge branch 'main' into feat/onnx
2023-07-28 09:59:35 -04:00
Brandon Rising
2b7b3dd4ba
Run python black
2023-07-28 09:46:44 -04:00
Lincoln Stein
4c79350300
persist LoRA model info in models.yaml
2023-07-28 11:38:52 +10:00
Brandon Rising
1ea9ba84f5
Release session if applying ti or lora
2023-07-27 15:20:38 -04:00
Lincoln Stein
0d8f9cbe55
resolved conflicts with main
2023-07-27 15:11:25 -04:00
Brandon Rising
bfdc8c80f3
Testing caching onnx sessions
2023-07-27 14:13:29 -04:00
Brandon Rising
59716938bf
Remove TensorRT support at the current time until we validate it works, remove time step recorder
2023-07-27 11:18:50 -04:00
Martin Kristiansen
218b6d0546
Apply black
2023-07-27 10:54:01 -04:00
Brandon Rising
f7bb4c3f05
Remove more files no longer needed in main
2023-07-27 10:49:43 -04:00
Brandon Rising
989d3d7f3c
Remove onnx changes from canvas img2img, inpaint, and linear image2image
2023-07-27 10:08:45 -04:00
Brandon Rising
eb1ba8d74b
Merge branch 'main' into feat/onnx
2023-07-27 09:54:30 -04:00
Brandon Rising
024f92f9a9
Add onnx models to the model manager UI
2023-07-27 09:37:37 -04:00
Lincoln Stein
b67041dd29
Merge branch 'main' into bugfix/convert-sdxl-models
2023-07-27 00:24:37 -04:00
Lincoln Stein
c02b9db064
Merge branch 'main' into bugfix/convert-sdxl-models
2023-07-27 00:08:15 -04:00
Lincoln Stein
2e19b23eed
Merge branch 'main' into feat/install-finetune-sdxl-vae
2023-07-27 00:06:00 -04:00
Lincoln Stein
61aff8540c
fix refiner conversion
2023-07-27 00:02:10 -04:00
Lincoln Stein
2b7807e6a0
Merge branch 'main' into fix/yaml-file-delete
2023-07-26 23:45:43 -04:00
Lincoln Stein
77946bfea5
restore ability to convert SDXL checkpoints to diffusers
2023-07-26 23:28:58 -04:00
Lincoln Stein
d4d4d749f2
Merge branch 'release/invokeai-3-0-1'
2023-07-26 23:15:26 -04:00
Lincoln Stein
43fe8b1dda
Merge branch 'main' into fix/reduce-configure-vertical
2023-07-26 23:12:25 -04:00
Lincoln Stein
9c4acb9d3f
install SDXL "fixed" VAE
2023-07-26 23:06:27 -04:00
Lincoln Stein
451b8c96e5
do not overwrite models.yaml if it is well formed
2023-07-26 22:29:39 -04:00
Lincoln Stein
83a981b585
merge with main; fix SDXL repo_ids
2023-07-26 17:38:06 -04:00
Lincoln Stein
049645d66e
updated LICENSE files and added information about watermarking
2023-07-26 17:27:33 -04:00
Lincoln Stein
0100ac8f2d
Merge branch 'main' into release/invokeai-3-0-1
2023-07-26 15:27:06 -04:00
Lincoln Stein
020031f376
add all legacy model .yaml files to configs directory unconditionally
2023-07-26 15:17:00 -04:00
Lincoln Stein
bf1f6619df
fix conversion for sd1 and sd2 models
2023-07-26 15:02:32 -04:00
Brandon Rising
861c0fe76b
Correct issues caused by merging main
2023-07-26 12:25:46 -04:00
Lincoln Stein
af8fc6ff82
final polish before release candidate
...
- Fix issue that prevented web ui from starting if
ROOT/databases/invokeai.db not found.
- Rebuild front end
2023-07-26 10:59:23 -04:00
Brandon Rising
c16da75ac7
Merge branch 'main' into feat/onnx
2023-07-26 10:42:31 -04:00
Lincoln Stein
c7f883d22a
Merge branch 'main' into patch
2023-07-26 10:19:02 -04:00
Lincoln Stein
4bea846199
Merge branch 'main' into feat/safety-checker-node
2023-07-26 10:04:23 -04:00
Lincoln Stein
58c0bee325
improved error message for running configure
2023-07-26 08:30:01 -04:00
Lincoln Stein
b8f43f444a
implemented startup sanity checks on core models
2023-07-26 08:26:29 -04:00
Lincoln Stein
da76f6fee4
compress height needed by configure script
2023-07-26 08:00:19 -04:00
Lincoln Stein
3e206d4d6a
removed nsfw/watermark from invokeai.yaml
2023-07-26 06:53:35 -04:00
Lincoln Stein
85ad5ef204
refactored code; added watermark and nsfw facilities to app config route
2023-07-26 15:27:04 +10:00
Lincoln Stein
e32cd794f7
add safetychecker and watermark nodes
2023-07-26 15:26:45 +10:00
Lincoln Stein
dbc3d42afc
install all recommended models with --yes; don't alter starter model screen
2023-07-25 22:24:03 -04:00
Lincoln Stein
2db9b3b2ae
Merge branch 'main' into patch
2023-07-25 16:27:10 -04:00
Lincoln Stein
e43e198102
rework configure/install TUI to require less space
2023-07-25 11:25:26 -04:00
Lincoln Stein
2aefa921fe
fix "unknown model type" error when rebasing a model with API
...
- Add command-line model probing script for dev use
- Minor documentation tweak
2023-07-25 08:36:57 -04:00
Lincoln Stein
11e6ecc1bf
Merge branch 'main' into feat/controlnet-and-sdxl-convert
2023-07-25 08:05:17 -04:00
Lincoln Stein
fc4e104c61
tested on 3.11 and 3.10
2023-07-24 17:13:32 -04:00
blessedcoolant
d6bf6513ef
Merge branch 'main' into fix-types-2
2023-07-24 20:01:48 +12:00
camenduru
cbb90cbdbb
Download all model types.
2023-07-24 10:59:59 +03:00
blessedcoolant
0cf7a10c5c
fix: Other lora missing type
2023-07-24 18:58:24 +12:00
Alexandre Macabies
0beec08d38
Add missing import.
2023-07-23 16:40:05 +02:00
Lincoln Stein
f2a6f0cf21
SDXL & SDXL-refiner models convert correctly
2023-07-23 09:31:14 -04:00
Alexandre Macabies
07a90c0198
Fix incorrect use of a singleton list.
...
This was found through pylance type errors. Go types!
2023-07-23 15:28:05 +02:00
Lincoln Stein
5e59edfaf1
SDXL checkpoint models now convert and load; needs refactor
2023-07-23 00:00:31 -04:00
Lincoln Stein
b1d7c9b306
save text_encoder_2 config, not whole model
2023-07-22 21:33:40 -04:00
Lincoln Stein
5607794dbb
add support for controlnet & sdxl conversion - not fully working
2023-07-22 20:12:16 -04:00
Lincoln Stein
845d1524ad
warn, do not crash, when duplicate models encountered
2023-07-21 15:00:55 -04:00
Brandon Rising
78750042f5
Pass in dim overrides
2023-07-21 12:16:24 -04:00
psychedelicious
3f79812dc6
fix: mps attention fix for sd2
2023-07-21 09:22:37 -04:00
Lincoln Stein
5962d96f27
Merge branch 'main' into fix/long_tensors_mps
2023-07-20 23:24:47 -04:00
Lincoln Stein
9370572169
prettify startup messages
2023-07-20 22:45:35 -04:00
Sergey Borisov
e6d890888c
Replace SlicedAttnProcessor with patched to chunk memory consumption less then 4gb in each attention calculation pass
2023-07-21 04:08:49 +03:00
Lincoln Stein
85ef3f51e7
extra check for empty hftoken
2023-07-20 15:16:06 -04:00
Brandon Rising
ba1a934297
Fix Lora typings
2023-07-20 14:02:23 -04:00
Brandon Rising
4e90376d11
Allow passing in of precision, use available providers if none provided
2023-07-20 13:15:45 -04:00
Lincoln Stein
7deafa838b
merge with main
2023-07-20 11:45:54 -04:00
Lincoln Stein
b1a6ba552b
reinitialize models.yaml if corrupt or missing
2023-07-20 11:26:20 -04:00
Lincoln Stein
89a15f78dd
collapse all autoimport directories into a single folder
2023-07-20 09:01:49 -04:00
Lincoln Stein
cb29ac63a8
prevent crashes on quick install when hftoken not defined
2023-07-20 08:38:37 -04:00
user1
bab8b6d240
Removed diffusers_pipeline prepare_control_image() -- replaced with controlnet_utils.prepare_control_image()
...
Added resize_mode to ControlNetData class.
2023-07-20 00:41:49 -07:00
Lincoln Stein
12cae33dcd
fix inpaint model detection ( #3843 )
...
Co-authored-by: Lincoln Stein <lstein@gmail.com>
2023-07-20 12:57:14 +12:00
Brandon Rising
43b6a077fb
io binding seems to be massively resource intensive compared to session.run
2023-07-19 17:42:28 -04:00
Lincoln Stein
a1251c8e04
fix inpaint model detection
2023-07-19 13:30:00 -04:00
Lincoln Stein
8439e30798
Merge branch 'main' into release/invokeai-3-0-beta
2023-07-19 12:09:32 -04:00
Lincoln Stein
9c3a556813
Merge branch 'main' into fix/transformers_4_31_0
2023-07-19 09:35:52 -04:00
Lincoln Stein
0b6ef7eb7d
make the convert VAE available to model manager for use in UI
2023-07-19 09:05:24 -04:00
Brandon Rising
e8299d0abb
Comment out erroniously removed del statement, comment out opt tests
2023-07-18 23:23:34 -04:00
Sergey Borisov
2e7fc055c4
Support both pre and post 4.31.0 transformers
2023-07-19 06:15:17 +03:00
Brandon Rising
f4e52fafac
Fix as part of merging main in
2023-07-18 23:05:33 -04:00
Lincoln Stein
0f7e329e76
restore access token-saving code
2023-07-18 22:58:56 -04:00
Brandon Rising
ee7b36cea5
Merge branch 'main' into onnx-testing
2023-07-18 22:56:41 -04:00
Lincoln Stein
a690cca5b5
make convert work with both 4.30.2 and 4.31.0
2023-07-18 22:18:13 -04:00
Brandon Rising
e201ad2f51
Switch to io_binding for run, testing different session options
2023-07-18 21:54:54 -04:00
Sergey Borisov
0aa7193d3b
Load text_model.embeddings.position_ids outsude state_dict
2023-07-19 04:18:43 +03:00
Lincoln Stein
2fbf245c3d
Merge branch 'main' into release/invokeai-3-0-beta
...
-- this adds the upscaling support
2023-07-18 21:17:15 -04:00
Lincoln Stein
39c14eb2ac
fix pretrained model download to work with xl
2023-07-18 21:10:33 -04:00
Lincoln Stein
893e199677
Merge branch 'main' into feat/ui/upscale
2023-07-18 19:18:55 -04:00
blessedcoolant
186e98da5e
Merge branch 'main' into fix/mem_cleanup
2023-07-19 10:10:32 +12:00
Eugene Brodsky
dea9a5da7a
Avoid crash if unable to modify the model config file ( #3824 )
...
* fix whitespace; remove invisible characters
* log error and proceed if unable to modify the model config
2023-07-18 16:33:19 -04:00
Sergey Borisov
bda0000acd
Cleanup vram after models offloading, tweak to cleanup local variable references on ram offload
2023-07-18 23:21:18 +03:00
Brandon Rising
35d5ef9118
Emit step completions
2023-07-18 12:35:07 -04:00
StAlKeR7779
889b77d3d6
Merge branch 'main' into save_vram
2023-07-18 16:55:48 +03:00
Sergey Borisov
bc11296a5e
Disable lazy offloading on disabled vram cache, move resulted tensors to cpu(to not stack vram tensors in cache), fix - text encoder not freed(detach)
2023-07-18 16:20:25 +03:00
psychedelicious
42c440c73f
Merge branch 'main' into feat/ui/upscale
2023-07-18 22:08:02 +10:00
Lincoln Stein
9c3c393b84
merge with main
2023-07-18 07:00:55 -04:00
psychedelicious
56098f370c
feat(nodes): add RealESRGAN_x2plus.pth, update upscale nodes
...
- add `RealESRGAN_x2plus.pth` model to installer
- add `RealESRGAN_x2plus.pth` to `realesrgan` node
- rename `RealESRGAN` to `ESRGAN` in nodes
- make `scale_factor` optional in `img_scale` node
2023-07-18 14:55:18 +10:00
Lincoln Stein
1353bf98b3
add specific exception for model probe failures
2023-07-17 23:08:39 -04:00
Lincoln Stein
025cda3815
fix 424 error on model import
2023-07-17 22:21:11 -04:00
blessedcoolant
13da881953
Merge branch 'main' into sdxl-support
2023-07-18 13:34:07 +12:00
blessedcoolant
ec3c15ead0
Merge branch 'main' into mm-ui
2023-07-18 12:58:57 +12:00
Sergey Borisov
0fce35c54c
Cleanup, fix variable name, fix controlnet for sequential and cross attention guidance
2023-07-17 23:53:50 +03:00
Brandon Rising
bcce70fca6
Testing different session opts, added timings for testing
2023-07-17 16:27:33 -04:00
Sergey Borisov
1c680a7147
Fix - encoder_attention_mask not passed before to unet, even if passed it will broke sequential guidance run, so rewrite logic
2023-07-17 23:13:37 +03:00
Lincoln Stein
0ea8d3c30c
prevent crash on rename operation on models in models directory
2023-07-17 07:50:06 -04:00
Lincoln Stein
84a13ff8e1
Merge branch 'mm-ui' of github.com:blessedcoolant/InvokeAI into mm-ui
2023-07-17 07:29:35 -04:00
Lincoln Stein
3fba262c94
expose paths as absolute to web api
2023-07-17 07:29:26 -04:00
Lincoln Stein
107ca6bf47
expose model paths as absolute to web models API
2023-07-17 07:26:05 -04:00
blessedcoolant
cbfd1d1b27
Merge branch 'main' into feat/standalone_diffusers_ti
2023-07-17 22:01:52 +12:00
blessedcoolant
aebd595607
Merge branch 'main' into mm-ui
2023-07-17 13:49:25 +12:00
Lincoln Stein
ed88e72412
correct cannot assign to field 'unconditioned_embeddings' error
2023-07-16 21:06:40 -04:00
Sergey Borisov
6aefd8600a
Fix error with long prompts when controlnet used
2023-07-16 21:06:40 -04:00
Lincoln Stein
ccb43d5a91
make check for 2.3 root directory more stringent
2023-07-16 20:43:15 -04:00
Kent Keirsey
675a92401c
Merge branch 'main' into lstein/default-model-install
2023-07-16 19:32:59 -04:00
Sergey Borisov
b61c83e836
Allow bin extension to detect diffusers-ti provided as file
2023-07-17 00:32:17 +03:00
Lincoln Stein
2bc3e36bc0
add missing exception name
2023-07-16 16:14:28 -04:00
Lincoln Stein
6fbb5ce780
add renaming capabilities to model update API route
2023-07-16 14:17:05 -04:00
Brandon Rising
932112b640
testing being super wasteful with data
2023-07-16 00:17:33 -04:00
Lincoln Stein
b767b5d44c
user must adjust terminal size on Windows
2023-07-15 23:19:50 -04:00
Lincoln Stein
e95cb3aa71
Merge branch 'lstein/default-model-install' into release/invokeai-3-0-beta
2023-07-15 20:16:51 -04:00
Lincoln Stein
5b5d5ec978
Merge branch 'main' into sdxl-support
2023-07-15 19:49:57 -04:00
Lincoln Stein
ccbfa5d862
resolve conflicts
2023-07-15 19:47:50 -04:00
Lincoln Stein
7fa394912d
Merge branch 'main' into lstein/default-model-install
2023-07-15 18:26:35 -04:00
Lincoln Stein
6b0a158ffa
Merge branch 'main' into lstein/default-model-install
2023-07-15 18:23:34 -04:00
Lincoln Stein
c90345d6a3
deprecate the face restoration option
2023-07-15 18:23:32 -04:00
Lincoln Stein
f66ead0819
Merge branch 'main' into update-textual-inversion-training
2023-07-15 17:44:45 -04:00
Kent Keirsey
77b0129b4c
Merge branch 'main' into lstein/migrate-fix
2023-07-15 10:37:56 -04:00
Lincoln Stein
e01706f5f5
add fp16 support to controlnet models
2023-07-15 10:37:11 -04:00
Lincoln Stein
a111539059
migrate script now initializes destination root if needed
2023-07-15 09:59:34 -04:00
Lincoln Stein
32e7e52d69
Merge branch 'main' into lstein/default-model-install
2023-07-15 08:30:22 -04:00
psychedelicious
d234bf1cb9
feat(install): display full ESRGAN model filenames during installation
2023-07-15 21:27:10 +10:00
blessedcoolant
808b2de709
Merge branch 'main' into lstein/model-manager-route-enhancements
2023-07-15 16:56:54 +12:00
Lincoln Stein
2faa7cee37
add rename_model route
2023-07-14 23:03:18 -04:00
Brandon
467414f214
Merge branch 'main' into update-textual-inversion-training
2023-07-14 22:32:09 -04:00
Brandon Rising
f88a338be0
Setup textual inversion training with new model manager
2023-07-14 21:58:51 -04:00
Lincoln Stein
b306247eb5
remove clipseg model install
2023-07-14 20:39:42 -04:00
Lincoln Stein
a45f7ce355
add --list-models command
2023-07-14 19:52:47 -04:00
Lincoln Stein
eb9d74653d
set default models for realesrgan, controlnet and text inversion
2023-07-14 19:03:41 -04:00
Sergey Borisov
7093e5d033
Pad conditionings using zeros and encoder_attention_mask
2023-07-15 00:52:54 +03:00
Brandon Rising
bd7b59910d
Testing onnx in new ui updates
2023-07-14 14:24:15 -04:00
Lincoln Stein
e71ce83e9c
Merge branch 'main' into lstein/model-manager-route-enhancements
2023-07-14 13:52:55 -04:00
Lincoln Stein
8600aad12b
multiple enhancements to model manager REACT API
...
1. add a /sync route for synchronizing the in-memory model lists to
models.yaml, the models directory, and the autoimport directories.
2. add optional destination_directories to convert_model and merge_model
operations.
3. add /ckpt_confs route for retrieving known legacy checkpoint configuration
files.
4. add /search route for finding all models in a directory located in the server
filesystem
2023-07-14 13:45:16 -04:00
Lincoln Stein
ad076b1174
add model directory search route
2023-07-14 11:14:33 -04:00
blessedcoolant
16e93c6455
Merge branch 'main' into mm-ui
2023-07-14 15:46:53 +12:00
Brandon Rising
524888bf3b
Merge branch 'main' into feat/onnx
2023-07-13 14:23:57 -04:00
blessedcoolant
9348dc8e0d
Merge branch 'main' into fix/controlnet_cfg_inj_cond
2023-07-14 01:11:04 +12:00
blessedcoolant
5a546e66f1
Merge branch 'main' into fix-inpainting
2023-07-13 20:42:13 +12:00
psychedelicious
eb0d55263b
fix(mm): make model config attribute names consistent
...
Our model fields use `model_name`, but the API response uses `name`. Some places use `model_type` but the API response used `type`.
Changed the API response to provide `model_name` and `model_type`, which simplifies how we manage models on the client substantially.
2023-07-13 15:40:05 +10:00
blessedcoolant
7e3b9f1320
fix: Inpaint not working with some schedulers
...
Co-Authored-By: StAlKeR7779 <7768370+StAlKeR7779@users.noreply.github.com>
2023-07-13 15:06:03 +12:00
blessedcoolant
71e34ac256
Merge branch 'main' into mm-ui
2023-07-13 12:48:43 +12:00
Sergey Borisov
67c8cf4bc2
Controlnet model detection
2023-07-12 08:50:19 -04:00
Sergey Borisov
a328986b43
Less naive model detection
2023-07-12 08:50:19 -04:00
blessedcoolant
5a6ad99d4e
feat: Restore Delete Model Functionality
2023-07-12 16:39:07 +12:00
StAlKeR7779
b8a9b499df
Merge branch 'main' into fix/controlnet_cfg_inj_cond
2023-07-11 23:43:47 +03:00
Lincoln Stein
25591788c1
fix conflicts
2023-07-11 15:55:10 -04:00
Lincoln Stein
dab03fb646
rename gpu_mem_reserved to max_vram_cache_size
...
To be consistent with max_cache_size, the amount of memory to hold in
VRAM for model caching is now controlled by the max_vram_cache_size
configuration parameter.
2023-07-11 15:25:39 -04:00
Lincoln Stein
d32f9f7cb0
reverse logic of gpu_mem_reserved
...
- gpu_mem_reserved now indicates the amount of VRAM that will be reserved
for model caching (similar to max_cache_size).
2023-07-11 15:16:40 -04:00
Lincoln Stein
6b93c1451f
do not crash when probing an unknown model type
2023-07-11 10:56:47 -04:00
Lincoln Stein
bf2b5b5cd4
improvements to sdxl support in model manager
...
- Move SDXL-related models to models/sdxl.py
- Create separate base type BaseModelType.StableDiffusionXLRefiner for the refiner
models.
2023-07-09 20:42:03 -04:00
Lincoln Stein
5759a390f9
introduce gpu_mem_reserved configuration parameter
2023-07-09 18:35:04 -04:00
Lincoln Stein
130249a2dd
add model loading support for SDXL
2023-07-09 15:47:06 -04:00
Lincoln Stein
8d7dba937d
fix undefined variable
2023-07-09 14:37:45 -04:00
Lincoln Stein
d6cb0e54b3
don't unload models from GPU until the space is needed
2023-07-09 14:26:30 -04:00
Lincoln Stein
5f7435955e
if models.yaml doesn't exist, rebuild it
2023-07-08 15:13:51 -04:00
Lincoln Stein
69ef1e1e56
speculative change to upgrade script
2023-07-08 11:45:26 -04:00
Lincoln Stein
10d3bccf32
Mac MPS FP16 fixes ( #3641 )
...
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 `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.
2023-07-07 17:43:23 -04:00
Eugene Brodsky
97b2ec58e2
Merge branch 'main' into release/invokeai-3-0-alpha
2023-07-07 14:18:12 -04:00
Lincoln Stein
56f4712814
fix checkpoint VAE handling in migrate script
2023-07-07 09:34:42 -04:00
Lincoln Stein
9f58ed35cf
improve user migration experience
...
- No longer fail root directory probing if invokeai.yaml is missing
(test is now whether a `models/core` directory exists).
- Migrate script does not overwrite previously-installed models.
- Can run migrate script on an existing 2.3 version directory
with --from and --to pointing to same 2.3 root.
2023-07-07 08:18:46 -04:00
blessedcoolant
7aa918677e
Merge branch 'main' into feat/clip_skip
2023-07-07 16:21:53 +12:00
Lincoln Stein
54f3686e3b
merge with main, fix conflicts
2023-07-06 15:21:45 -04:00
Lincoln Stein
e9352227f3
add merge api
2023-07-06 15:12:34 -04:00
blessedcoolant
bc5371eeee
Merge branch 'main' into feat/clip_skip
2023-07-07 06:03:39 +12:00
Lincoln Stein
e573a533ae
remove redundant import
2023-07-06 13:24:58 -04:00
Lincoln Stein
581be42c75
Merge branch 'main' into lstein/model-manager-router-api
2023-07-06 13:20:36 -04:00
Lincoln Stein
90c66aab3d
merge with upstream
2023-07-06 13:17:02 -04:00
Lincoln Stein
3e925fbf34
model merging API ready for testing
2023-07-06 13:15:15 -04:00
Lincoln Stein
ec7c2f07c6
model merge backend, CLI and TUI working
2023-07-06 12:21:42 -04:00
blessedcoolant
b229fe19aa
Merge branch 'main' into lstein/configure-max-cache-size
2023-07-07 01:52:12 +12:00
Sergey Borisov
04b57c408f
Add clip skip option to prompt node
2023-07-06 16:09:40 +03:00
blessedcoolant
6f1268e2b1
Merge branch 'main' into lstein/more-model-loading-fixes
2023-07-07 00:32:22 +12:00
Lincoln Stein
8f5fcb188c
Merge branch 'main' into lstein/model-manager-router-api
2023-07-05 23:16:43 -04:00
Lincoln Stein
f7daa6e71d
all methods now return OPENAPI_MODEL_CONFIGS; convert uses PUT
2023-07-05 23:13:01 -04:00
Lincoln Stein
3691b55565
fix autoimport crash
2023-07-05 21:53:08 -04:00
Lincoln Stein
f610045a14
Merge branch 'main' into mps-fp16-fixes
2023-07-05 21:01:48 -04:00
Lincoln Stein
a7cbcae176
expose max_cache_size to invokeai-configure interface
2023-07-05 20:59:57 -04:00
Lincoln Stein
0a6dccd607
expose max_cache_size to invokeai-configure interface
2023-07-05 20:59:14 -04:00
Lincoln Stein
43c51ff157
Merge branch 'main' into lstein/more-model-loading-fixes
2023-07-05 20:48:15 -04:00
Lincoln Stein
cfa3b2419c
partial implementation of merge
2023-07-05 20:25:47 -04:00
Lincoln Stein
d4550b3059
clean up lint errors in lora.py
2023-07-05 19:18:25 -04:00
Lincoln Stein
83d3a043da
merge latest changes from main
2023-07-05 19:15:53 -04:00
gogurtenjoyer
169ff6368b
Update mps_fixes.py - additional torch op for nodes
...
This fixes scaling in the nodes UI.
2023-07-05 17:47:23 -04:00
Lincoln Stein
71dad6d404
Merge branch 'main' into ti-ui
2023-07-05 16:57:31 -04:00
Lincoln Stein
685a47cc7d
fix crash during lora application
2023-07-05 16:40:47 -04:00
Lincoln Stein
cb947bcbf0
Merge branch 'main' into lstein/fix-migrate3-textencoder
2023-07-05 16:23:00 -04:00
Lincoln Stein
f8bbec8572
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 16:21:23 -04:00
Lincoln Stein
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
Lincoln Stein
90ae8ce26a
prevent model install crash "torch needs to be restarted with spawn"
2023-07-05 16:18:20 -04:00
Lincoln Stein
ad5d90aca8
prevent model install crash "torch needs to be restarted with spawn"
2023-07-05 15:38:07 -04:00
Lincoln Stein
5b6dd47b9f
add API for model convert
2023-07-05 15:13:21 -04:00
Lincoln Stein
5027d0a603
accept @psychedelicious suggestions above
2023-07-05 14:50:57 -04:00
Lincoln Stein
9f9ce08e44
Merge branch 'main' into lstein/remove-hardcoded-cuda-device
2023-07-05 13:38:33 -04:00
Lincoln Stein
021e1eca8e
Merge branch 'main' into mps-fp16-fixes
2023-07-05 13:19:52 -04:00
Lincoln Stein
5fe722900d
allow clip-vit-large-patch14 text encoder to coexist with tokenizer in same directory
2023-07-05 13:15:08 -04:00
Lincoln Stein
cf173b522b
allow clip-vit-large-patch14 text encoder to coexist with tokenizer in same directory
2023-07-05 13:14:41 -04:00
blessedcoolant
9e2d63ef97
Merge branch 'main' into fix/ckpt_convert_scan
2023-07-06 05:01:34 +12:00
Sergey Borisov
0ac9dca926
Fix loading diffusers ti
2023-07-05 19:46:00 +03:00
Lincoln Stein
bd82c4ace0
model installer confirms deletion of models
2023-07-05 09:57:23 -04:00
Lincoln Stein
9edf78dd2e
merge with main
2023-07-05 09:12:54 -04:00
Lincoln Stein
6112197edf
convert implemented; need router
2023-07-05 09:05:05 -04:00
gogurtenjoyer
ba7345deb4
Merge branch 'main' into mps-fp16-fixes
2023-07-05 07:38:41 -04:00
Sergey Borisov
ee042ab76d
Fix ckpt scanning on conversion
2023-07-05 14:18:30 +03:00
blessedcoolant
780e77d2ae
Merge branch 'main' into fix/clip_path
2023-07-05 22:45:52 +12:00
Sergey Borisov
e3fc1b3816
Fix clip path in migrate script
2023-07-05 13:43:09 +03:00
Lincoln Stein
307a01d604
when migrating models, changes / to _ in model names to avoid breaking model name keys
2023-07-05 20:27:03 +10:00
Sergey Borisov
2beb8f049e
Fix model detection
2023-07-05 09:43:46 +03:00
blessedcoolant
639d88afd6
revert: inference_mode to no_grad
2023-07-05 16:39:15 +12:00
blessedcoolant
c0501ed5c2
fix: Slow loading of Loras
...
Co-Authored-By: StAlKeR7779 <7768370+StAlKeR7779@users.noreply.github.com>
2023-07-05 12:47:34 +10:00
gogurtenjoyer
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
Lincoln Stein
5d099f4a49
update_model working
2023-07-04 17:26:57 -04:00
Lincoln Stein
752b4d50cf
model_delete method now working
2023-07-04 10:40:32 -04:00
Lincoln Stein
c1c49d9a76
import model returns 404 for invalid path, 409 for duplicate model
2023-07-04 10:08:10 -04:00
Lincoln Stein
96bf92ead4
add the import model router
2023-07-04 14:35:47 +10:00
Lincoln Stein
fc419546bc
Merge branch 'main' into lstein/remove-hardcoded-cuda-device
2023-07-03 14:10:47 -04:00
Lincoln Stein
cfd09214d3
Merge branch 'main' into lstein/fix-vae-conversion-crash
2023-07-03 14:03:13 -04:00
Lincoln Stein
b128ba81db
Merge branch 'main' into lstein/remove-hardcoded-cuda-device
2023-07-03 13:58:14 -04:00
Lincoln Stein
d6de11bd56
resolve merge conflict
2023-07-03 12:19:11 -04:00
Lincoln Stein
ed86d0b708
Union[foo, None]=>Optional[foo]
2023-07-03 12:17:45 -04:00
Lincoln Stein
fb2b2a371d
Merge branch 'lstein/fix-vae-conversion-crash' into release/invokeai-3-0-alpha
2023-07-03 11:21:16 -04:00
Lincoln Stein
10d513c5f7
add runtime root path to relative vaes and other submodels
2023-07-03 11:19:33 -04:00
Lincoln Stein
877b187a1b
Merge branch 'lstein/restore-3.9-compatibility' into release/invokeai-3-0-alpha
2023-07-03 11:01:34 -04:00
Lincoln Stein
ac9ec4e75a
restore 3.9 compatibility by replacing | with Union[]
2023-07-03 10:57:40 -04:00
Lincoln Stein
2465c7987b
Revert "restore 3.9 compatibility by replacing | with Union[]"
...
This reverts commit 76bafeb99e
2023-07-03 10:56:41 -04:00
Lincoln Stein
76bafeb99e
restore 3.9 compatibility by replacing | with Union[]
2023-07-03 10:55:04 -04:00
Lincoln Stein
6935858ef3
add debugging messages to aid in memory leak tracking
2023-07-02 13:34:53 -04:00
Lincoln Stein
fa1f9939cc
adjust invokeai-configure TUI vertical height to show NEXT button on Mac
2023-07-02 09:44:16 -04:00
