Kent Keirsey
22f637b647
ruff ruff
2025-05-19 13:50:04 +10:00
Kent Keirsey
5d192ab6e5
Fix SD precise in patcher.
2025-05-19 13:50:04 +10:00
Kent Keirsey
3bfb497764
ruff fixes
2025-05-19 13:50:04 +10:00
Kent Keirsey
b02ea1a898
Expanded styles & updated UI
2025-05-19 13:50:04 +10:00
Kent Keirsey
d709040f4b
Matt3o base changes
2025-05-19 13:50:04 +10:00
Ryan Dick
bac05a7885
Add CogView4TextEncoderInvocation
2025-04-10 10:50:13 +10:00
psychedelicious
5fa2cf59e2
fix(app): add trusted classes to torch safe globals to prevent errors when loading them
...
In `ObjectSerializerDisk`, we use `torch.load` to load serialized objects from disk. With torch 2.6.0, torch defaults to `weights_only=True`. As a result, torch will raise when attempting to deserialize anything with an unrecognized class.
For example, our `ConditioningFieldData` class is untrusted. When we load conditioning from disk, we will get a runtime error.
Torch provides a method to add trusted classes to an allowlist. This change adds an arg to `ObjectSerializerDisk` to add a list of safe globals to the allowlist and uses it for both `ObjectSerializerDisk` instances.
Note: My first attempt inferred the class from the generic type arg that `ObjectSerializerDisk` accepts, and added that to the allowlist. Unfortunately, this doesn't work.
For example, `ConditioningFieldData` has a `conditionings` attribute that may be one some other untrusted classes representing model-specific conditioning data. So, even if we allowlist `ConditioningFieldData`, loading will fail when torch deserializes the `conditionings` attribute.
2025-04-04 18:42:13 +11:00
Billy
182580ff69
Imports
2025-03-26 12:55:10 +11:00
Ryan Dick
607d19f4dd
We should not trust the value of since the model could be partially-loaded.
2025-01-07 19:22:31 -05:00
Ryan Dick
6d7314ac0a
Consolidate the LayerPatching patching modes into a single implementation.
2024-12-24 15:57:54 +00:00
Ryan Dick
80db9537ff
Rename model_patcher.py -> layer_patcher.py.
2024-12-24 15:57:54 +00:00
Ryan Dick
dd09509dbd
Rename ModelPatcher -> LayerPatcher to avoid conflicts with another ModelPatcher definition.
2024-12-17 13:20:19 +00:00
Ryan Dick
7fad4c9491
Rename LoRAModelRaw to ModelPatchRaw.
2024-12-17 13:20:19 +00:00
Ryan Dick
b820862eab
Rename ModelPatcher methods to reflect that they are general model patching methods and are not LoRA-specific.
2024-12-17 13:20:19 +00:00
Ryan Dick
c604a0956e
Rename LoRAPatcher -> ModelPatcher.
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
2d86298b7f
Add first draft of Sd3TextEncoderInvocation.
2024-11-04 12:42:09 -05:00
dunkeroni
34569a2410
Make T2I Adapters compatible with x8 resolutions
2024-10-27 15:38:22 -04:00
dunkeroni
62cf0f54e0
fix preview progress bar pre-denoise
2024-10-25 23:22:06 -04:00
Ryan Dick
ac08c31fbc
Remove unnecessary hasattr checks for scaled_dot_product_attention. We pin the torch version, so there should be no concern that this function does not exist.
2024-10-10 19:23:45 -04:00
Ryan Dick
ea54a2655a
Add a workaround for broken sliced attention on MPS with torch 2.4.1.
2024-10-10 19:23:45 -04:00
Eugene Brodsky
b6c7949bb7
feat(backend): prefer xformers based on cuda compute capability
2024-10-09 22:46:18 -04:00
psychedelicious
dc10197615
fix(app): step callbacks for SD, FLUX, MultiDiffusion
...
Each of these was a bit off:
- The SD callback started at `-1` and ended at `i`. Combined w/ the weird math on the previous `calc_percentage` util, this caused the progress bar to never finish.
- The MultiDiffusion callback had the same problems as SD.
- The FLUX callback didn't emit a pre-denoising step 0 image. It also reported total_steps as 1 higher than the actual step count.
Each of these now emit the expected events to the frontend:
- The initial latents at 0%
- Progress at each step, ending at 100%
2024-09-22 21:20:32 +03:00
Ryan Dick
fef26a5f2f
Consolidate all LoRA patching logic in the LoRAPatcher.
2024-09-15 04:39:56 +03:00
Ryan Dick
2b3e4e123d
Split LoRA layer implementations into separate files.
2024-09-12 15:53:30 +00:00
Ryan Dick
4e4b6c6dbc
Tidy variable management and dtype handling in FluxTextToImageInvocation.
2024-08-29 19:08:18 +00:00
Ryan Dick
a52c899c6d
Split a FluxTextEncoderInvocation out from the FluxTextToImageInvocation. This has the advantage that we benfit from automatic caching when the prompt isn't changed.
2024-08-26 20:17:50 -04:00
Ryan Dick
5a9173f766
Merge branch 'main' into stalker-modular_lora
2024-07-31 15:13:22 -04:00
blessedcoolant
328e58be4c
Merge branch 'main' into stalker7779/new_karras_schedulers
2024-07-31 05:56:13 +05:30
Sergey Borisov
86f705bf48
Optimize weights handling
2024-07-30 03:39:01 +03:00
Sergey Borisov
1fd9631f2d
Comments fix
...
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com >
2024-07-30 00:39:50 +03:00
Sergey Borisov
2227a2357f
Suggested changes + simplify weights logic in patching
...
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com >
2024-07-30 00:34:37 +03:00
Sergey Borisov
58e7ab157d
Ruff format
2024-07-29 22:59:17 +03:00
Sergey Borisov
8d16fa6a49
Remove dpmpp_3s schedulers as it bugged now
2024-07-29 22:55:45 +03:00
Sergey Borisov
55e810efa3
Add dpmpp_3 schedulers
2024-07-29 22:52:15 +03:00
Ryan Dick
693a3eaff5
Merge branch 'main' into stalker-modular_inpaint-2
2024-07-29 10:14:45 -04:00
Sergey Borisov
86a92bb6b5
Add more karras schedulers
2024-07-29 15:14:34 +03:00
Ryan Dick
310719eb4c
Merge branch 'main' into stalker-modular_t2i_adapter
2024-07-28 15:30:00 -04:00
Sergey Borisov
84d028898c
Revert wrong comment copy
2024-07-27 13:20:58 +03:00
Sergey Borisov
ed0174fbc6
Suggested changes
...
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com >
2024-07-27 13:18:28 +03:00
Sergey Borisov
9e582563eb
Suggested changes
...
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com >
2024-07-27 04:25:15 +03:00
Sergey Borisov
faa88f72bf
Make lora as separate extensions
2024-07-27 02:39:53 +03:00
Sergey Borisov
5b84e117b2
Suggested changes
...
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com >
2024-07-26 20:51:12 +03:00
Sergey Borisov
5810cee6c9
Suggested changes
...
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com >
2024-07-26 19:47:28 +03:00
Sergey Borisov
adf1a977ea
Suggested changes
...
Co-Authored-By: Ryan Dick <14897797+RyanJDick@users.noreply.github.com >
2024-07-26 19:22:26 +03:00
Sergey Borisov
0ccb304b8b
Ruff format
2024-07-24 16:01:29 +03:00
Sergey Borisov
ab0bfa709a
Handle loras in modular denoise
2024-07-24 05:07:29 +03:00
Sergey Borisov
6af659b1da
Handle t2i adapter in modular denoise
2024-07-24 02:55:33 +03:00
Sergey Borisov
416d29fb83
Ruff format
2024-07-24 01:17:28 +03:00
Sergey Borisov
19c00241c6
Use non-inverted mask generally(except inpaint model handling)
2024-07-24 00:59:13 +03:00
