Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity
10,046 Commits 274 Branches 239 Tags 397 MiB
ryan/regional-conditioning-cross-attn-mask-only
Commit Graph

10046 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ryan Dick
61cd889dc5 Remove dispatch_progress() function that was added aciidentally during conflict resolution. 2024-03-08 09:00:02 -05:00
Ryan Dick
d64df4a260 Remove AddConditioningMaskInvocaton. 2024-03-08 09:00:02 -05:00
Mary Hipp Rogers
644232f7ea Default model settings (#5850) 
* UI in MM to create trigger phrases

* add scheduler and vaePrecision to config

* UI for configuring default settings for models'

* hook MM default model settings up to API

* add button to set default settings in parameters

* pull out trigger phrases

* back-end for default settings

* lint

* remove log;
gi

* ruff

* ruff format

---------

Co-authored-by: Mary Hipp <maryhipp@Marys-MacBook-Air.local>
 2024-03-08 09:00:02 -05:00
Brandon Rising
e2448d2b4e Next: Allow in place local installs of models 2024-03-08 09:00:02 -05:00
Ryan Dick
60815f59d1 Log a stack trace for invocation errors. 2024-03-08 09:00:02 -05:00
Hosted Weblate
c481c08a64 translationBot(ui): update translation files 
Updated by "Cleanup translation files" hook in Weblate.

Co-authored-by: Hosted Weblate <hosted@weblate.org>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/
Translation: InvokeAI/Web UI
 2024-03-08 09:00:02 -05:00
Riccardo Giovanetti
7e53a8ab1e translationBot(ui): update translation (Italian) 
Currently translated at 98.0% (1442 of 1470 strings)

Co-authored-by: Riccardo Giovanetti <riccardo.giovanetti@gmail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/it/
Translation: InvokeAI/Web UI
 2024-03-08 09:00:02 -05:00
B N
3c02e55f2d translationBot(ui): update translation (German) 
Currently translated at 80.4% (1183 of 1470 strings)

Co-authored-by: B N <berndnieschalk@gmail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/de/
Translation: InvokeAI/Web UI
 2024-03-08 09:00:02 -05:00
Mary Hipp
107390e40b add button to navigate to model manager if tab is enabled 2024-03-08 09:00:02 -05:00
Mary Hipp
01d86f3a78 consolidate tabs for main model and concepts in generation panel 2024-03-08 09:00:02 -05:00
Wubbbi
7aa6534960 Update Transformers 4.37.2 -> 4.38.2 2024-03-08 09:00:02 -05:00
dunkeroni
ec456bc58c docs: added both create mask nodes to defaultNodes 2024-03-08 09:00:02 -05:00
dunkeroni
589cd3d654 fix(canvas): use corrected mask for pasteback 2024-03-08 09:00:02 -05:00
psychedelicious
f1d8865bb5 tests(mm): update tests to reflect using UUID for key 2024-03-08 09:00:02 -05:00
psychedelicious
af24013bb8 feat(mm): improved model hash class 
- Use memory view for hashlib algorithms (closer to python 3.11's filehash API in hashlib)
- Remove `sha1_fast` (realized it doesn't even hash the whole file, it just does the first block)
- Add support for custom file filters
- Update docstrings
- Update tests
 2024-03-08 09:00:02 -05:00
psychedelicious
93aed57e81 fix(mm): use UUIDv4 for key 
This changes the functionality of this PR to only use the updated hashing for model hashes with a UUID for the key.
 2024-03-08 09:00:02 -05:00
psychedelicious
9f690e0a7f tests(mm): add tests for ModelHash 2024-03-08 09:00:02 -05:00
psychedelicious
33967cfc6d feat(mm): make ModelHash instantiatable, taking an algorithm as arg 2024-03-08 09:00:02 -05:00
psychedelicious
3cf3ed55a2 feat(mm): modularize ModelHash to facilitate testing 2024-03-08 09:00:02 -05:00
psychedelicious
6b41246b2d feat(mm): add hashing algos to ModelHash 
- Some algos are slow, so it is now just called ModelHash
- Added all hashlib algos, plus BLAKE3 and the fast (but incorrect) SHA1 algo
 2024-03-08 09:00:02 -05:00
psychedelicious
4b073157b8 feat(mm): make hash.py a script for testing 2024-03-08 09:00:02 -05:00
psychedelicious
efceee5128 feat(mm): use blake3 for hashing 2024-03-08 09:00:02 -05:00
Lincoln Stein
64f8535ef5 make model key assignment deterministic 
- When installing, model keys are now calculated from the model contents.
- .safetensors, .ckpt and other single file models are hashed with sha1
- The contents of diffusers directories are hashed using imohash (faster)

fixup yaml->sql db migration script to assign deterministic key

- this commit also detects and assigns the correct image encoder for
  ip adapter models.
 2024-03-08 09:00:02 -05:00
psychedelicious
d16b9a25bb docs: update RELEASE.md 2024-03-08 08:58:28 -05:00
psychedelicious
794e4db77f ci: add comments to workflows 2024-03-08 08:58:28 -05:00
psychedelicious
dba08376a8 ci: rename test matrix 
Now python version: platform, e.g. `py3.10: linux-cpu`

This displays better in GH actions.
 2024-03-08 08:58:28 -05:00
psychedelicious
1ab8565609 ci: add conditionals for jobs based on dispatch/call 2024-03-08 08:58:28 -05:00
psychedelicious
35cd3f6bf0 ci: rename jobs, remove extraneous needs in release 2024-03-08 08:58:28 -05:00
psychedelicious
1348bf495c ci: split build job 2024-03-08 08:58:28 -05:00
psychedelicious
1f1deb6a05 ci: workflow & job names 2024-03-08 08:58:28 -05:00
psychedelicious
0dde327bf8 ci: tidy pr labeler labels 2024-03-08 08:58:28 -05:00
psychedelicious
dbb485e430 ci: fix workflows 
Do not split up "on change" and "do the thing". Less convoluted, no catch-22 with required checks for PRs.
 2024-03-08 08:58:28 -05:00
Ryan Dick
289e759f15 Fix avoid storing extra conditioning info in two places. 2024-03-08 08:51:44 -05:00
Ryan Dick
5fad379192 Add ability to control regional prompt region weights. 2024-03-03 12:55:07 -05:00
Ryan Dick
ad18429fe3 Very experimentation with various regional prompting tuning params. 2024-03-02 17:43:21 -05:00
Ryan Dick
942efa011e Implement (very slow) self-attention regional masking. 2024-03-01 18:43:32 -05:00
Ryan Dick
ffc4ebb14c Merge branch 'ryan/remove-attention-map-saving' into ryan/regional-conditioning 2024-03-01 11:33:50 -05:00
Ryan Dick
5b3adf0740 Remove unused code for attention map saving. 2024-02-29 23:42:37 -05:00
Ryan Dick
a5c94fba43 Delete unused functions from shared_invokeai_diffusion.py. 2024-02-29 23:41:15 -05:00
Ryan Dick
3e14bd6c45 Remove unused constructor declared with typo in name: __int__. 2024-02-29 22:42:59 -05:00
Ryan Dick
8721926f14 Merge sequential conditioning and cac conditioning logic to eliminate a bunch of duplication. 2024-02-29 22:42:59 -05:00
Ryan Dick
d87ff3a206 Remove outdated comments related to T2I-Adapters and ControlNets. 2024-02-29 22:42:59 -05:00
Ryan Dick
7d9671014b Remove use of **kwargs in do_unet_step(...), where full parameter list is known and supported. 2024-02-29 22:42:59 -05:00
Ryan Dick
4a1acd4db9 Fix avoid storing extra conditioning info in two places. 2024-02-29 22:42:59 -05:00
Lincoln Stein
8fb297e5f6 add regression tests for <NOKEY> issue 2024-02-29 22:31:05 -05:00
Lincoln Stein
0832e1818e Fix problem of all installed models being assigned "<NOKEY>" 
- Also fix redundant scanning of models directory at startup.
 2024-02-29 22:31:05 -05:00
psychedelicious
26d4d93e64 ci: update mkdocs workflow 
Bit of a merge of the docs at https://github.com/squidfunk/mkdocs-material/blob/master/docs/publishing-your-site.md and the previous workflow.

Not sure how to test this without access to the main repo.
 2024-02-29 21:57:20 -05:00
psychedelicious
77f39aa935 ci: bump setup-python v4 -> v5 2024-02-29 21:57:20 -05:00
psychedelicious
6aae940834 ci: clean up unused workflow 2024-02-29 21:57:20 -05:00
psychedelicious
be8dcad1da feat(installer): do not delete dist/ 2024-02-29 21:57:20 -05:00