github/InvokeAI
1
1
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI.git synced 2026-02-02 13:05:18 -05:00
Code Issues Packages Projects Releases Wiki Activity
15,087 Commits 395 Branches 371 Tags
e2451ef5ca24f075378e1981e84d16716310a604
Commit Graph

2133 Commits

Author SHA1 Message Date
Ryan Dick
e2451ef5ca A unit tests for LinearSidecarWrapper (and fix a bug). 2024-12-17 13:20:19 +00:00
Ryan Dick
443d838fd0 Add initial basic implementation of sidecar wrappers. 2024-12-17 13:20:19 +00:00
Ryan Dick
808e3770d3 Remove AnyLoRALayer type definition in favor of using BaseLayerPatch base class. 2024-12-17 13:20:19 +00:00
Ryan Dick
2b441d6a2d Add BaseLayerPatch ABC to clarify the intended patch interface. 2024-12-17 13:20:19 +00:00
Ryan Dick
58de93a89e Delete empty file. 2024-12-17 13:20:19 +00:00
Ryan Dick
1eede4315e Delete ONNXModelPatcher. It is outdated and hasn't been used for a long time. 2024-12-17 13:20:19 +00:00
Ryan Dick
8ea697d733 Mark LoRALayerBase.rank(...) as a private method. 2024-12-17 13:20:19 +00:00
Ryan Dick
693d42661c Add basic unit tests for LoRALayer. 2024-12-17 13:20:19 +00:00
Ryan Dick
41664f88db Rename backend/patches/conversions/ to backend/patches/lora_conversions/ 2024-12-17 13:20:19 +00:00
Ryan Dick
42f8d6aa11 Rename backend/lora/ to backend/patches 2024-12-17 13:20:19 +00:00
Ryan Dick
7da90a9b6b Ensure that model probe does not crash with integer state dict keys. 2024-12-17 07:28:45 -05:00
Ryan Dick
440185cc40 Simplify FLUX control LoRA probing. 2024-12-17 07:28:45 -05:00
Ryan Dick
26edc71268 ruff format 2024-12-17 07:28:45 -05:00
Ryan Dick
a4bed7aee3 Minor tidy of FLUX control LoRA implementation. (mostly documentation) 2024-12-17 07:28:45 -05:00
Ryan Dick
d84adfd39f Clean up FLUX control LoRA pre-processing logic. 2024-12-17 07:28:45 -05:00
Brandon Rising
70811d0bd0 Remove unexpected artifacts in output images 2024-12-17 07:28:45 -05:00
Mary Hipp
da213e4638 feat(ui): add control loras to control adapter model options, add default settings for preprocessor in probe 2024-12-17 07:28:45 -05:00
Brandon Rising
046d19446c Rename Structural Lora to Control Lora 2024-12-17 07:28:45 -05:00
Ryan Dick
040551d4fb Fixes to get FLUX Control LoRA working. 2024-12-17 07:28:45 -05:00
Brandon Rising
f53da60b84 Lots of updates centered around using the lora patcher rather than changing the modules in the transformer model 2024-12-17 07:28:45 -05:00
Brandon Rising
5a035dd19f Support bnb quantized nf4 flux models, Use controlnet vae, only support 1 structural lora per transformer. various other refractors and bugfixes 2024-12-17 07:28:45 -05:00
Brandon Rising
f3b253987f Initial setup for flux tools control loras 2024-12-17 07:28:45 -05:00
Ryan Dick
0bff4ace1b Revert performance improvement, because it caused flux inference to fail on Mac: https://github.com/invoke-ai/InvokeAI/issues/7422 2024-12-03 15:18:58 +00:00
Jonathan
c094838c6a Update model_util.py 2024-12-02 14:35:02 -08:00
Ryan Dick
021552fd81 Avoid unnecessary dtype conversions with rope encodings. 2024-11-29 12:32:50 -05:00
Ryan Dick
be73dbba92 Use view() instead of rearrange() for better performance. 2024-11-29 12:32:50 -05:00
Ryan Dick
db9c0cad7c Replace custom RMSNorm implementation with torch.nn.functional.rms_norm(...) for improved speed. 2024-11-29 12:32:50 -05:00
psychedelicious
5910892c33 Merge remote-tracking branch 'origin/main' into ryan/flux-regional-prompting 2024-11-29 15:19:39 +10:00
Ryan Dick
5d8dd6e26e Fix FLUX regional negative prompts. 2024-11-28 18:49:29 +00:00
Ryan Dick
64364e7911 Short-circuit if there are no region masks in FLUX and don't apply attention masking. 2024-11-27 22:40:10 +00:00
Ryan Dick
6565cea039 Comment unused _prepare_unrestricted_attn_mask(...) for future reference. 2024-11-27 22:16:44 +00:00
Ryan Dick
3ebd8d6c07 Delete outdated TODO comment. 2024-11-27 22:13:25 +00:00
Ryan Dick
e970185161 Tweak flux regional prompting attention scheme based on latest experimentation. 2024-11-27 22:13:07 +00:00
Brandon Rising
ed46acee79 fix: Fail scan on InvalidMagicError in picklescan, update default for read_checkpoint_meta to scan unless explicitly told not to 2024-11-26 16:17:12 -05:00
Ryan Dick
b54463d294 Allow regional prompting background regions to attend to themselves and to the entire txt embedding. 2024-11-26 17:57:31 +00:00
Ryan Dick
faee79dc95 Distinguish between restricted and unrestricted attn masks in FLUX regional prompting. 2024-11-26 16:55:52 +00:00
Ryan Dick
e01f66b026 Apply regional attention masks in the single stream blocks in addition to the double stream blocks. 2024-11-25 22:40:08 +00:00
Ryan Dick
53abdde242 Update Flux RegionalPromptingExtension to prepare both a mask with restricted image self-attention and a mask with unrestricted image self attention. 2024-11-25 22:04:23 +00:00
Ryan Dick
94c088300f Be smarter about selecting the global CLIP embedding for FLUX regional prompting. 2024-11-25 20:15:04 +00:00
Ryan Dick
3741a6f5e0 Fix device handling for regional masks and apply the attention mask in the FLUX double stream block. 2024-11-25 16:02:03 +00:00
Ryan Dick
2c23b8414c Use a single global CLIP embedding for FLUX regional guidance. 2024-11-22 23:01:43 +00:00
Ryan Dick
20356c0746 Fixup the logic for preparing FLUX regional prompt attention masks. 2024-11-21 22:46:25 +00:00
Ryan Dick
bad1149504 WIP - add rough logic for preparing the FLUX regional prompting attention mask. 2024-11-20 22:29:36 +00:00
Ryan Dick
fda7aaa7ca Pass RegionalPromptingExtension down to the CustomDoubleStreamBlockProcessor in FLUX. 2024-11-20 19:48:04 +00:00
Ryan Dick
85c616fa34 WIP - Pass prompt masks to FLUX model during denoising. 2024-11-20 18:51:43 +00:00
Mary Hipp
1948ffe106 make sure Soft Edge Detection has preprocessor applied 2024-11-20 08:46:02 -05:00
Brandon Rising
a69c5ff9ef Add copyright notice for CIELab_to_UPLab.icc 2024-11-19 07:02:37 -08:00
Brandon Rising
1fd80d54a4 Run Ruff 2024-11-19 07:02:37 -08:00
Brandon Rising
991f63e455 Store CIELab_to_UPLab.icc within the repo 2024-11-19 07:02:37 -08:00
Brandon Rising
0eadc0dd9e feat: Support a subset of composition nodes within base invokeai 2024-11-19 07:02:37 -08:00