8e500283b6
Fix broken import in checkpoint_convert ( #5635 )
...
* Fix broken import in checkpoint_convert
* simplify the fix
---------
Co-authored-by: Lincoln Stein <lstein@gmail.com >
2024-02-04 12:56:51 +00:00
a04981b418
This seems to work now
2024-01-30 21:32:08 -05:00
bd31b5606c
Retain suffix (.safetensors, .bin) when renaming a checkpoint file or LoRA
...
- closes #5518
2024-01-16 17:27:50 -05:00
7269c9f02e
Enable correct probing of LoRA latent-consistency/lcm-lora-sdxl ( #5449 )
...
- Closes #5435
Co-authored-by: Lincoln Stein <lstein@gmail.com >
2024-01-08 17:18:26 -05:00
ffa05a0bb3
Only replace vae when it is the broken SDXL 1.0 version
2024-01-06 14:06:47 -05:00
a20e17330b
blackify
2024-01-06 14:06:47 -05:00
4e83644433
if sdxl-vae-fp16-fix model is available then bake it in when converting ckpts
2024-01-06 14:06:47 -05:00
f7f697849c
Skip weight initialization when resizing text encoder token embeddings to accomodate new TI embeddings. This saves time.
2024-01-05 15:16:00 -05:00
53b835945f
Updated with ruff formatting
2023-12-28 11:05:19 +11:00
e38d0e39b7
fix bug when there are two multi vector TI in a prompt
2023-12-27 22:14:14 +01:00
cb698ff1fb
Update model_probe to work with diffuser-format SD TI embeddings.
2023-12-18 09:51:16 -05:00
212dbaf9a2
fix comment
2023-12-15 00:25:27 -05:00
ac3cf48d7f
make probe recognize lora format at https://civitai.com/models/224641
2023-12-15 00:25:27 -05:00
75089b7a9d
merge in changes from main
2023-12-01 09:18:07 -05:00
5a3f1f2b22
fix ruff github format errors
2023-12-01 01:59:26 -05:00
f95ce1870c
fix ruff format check
2023-12-01 01:46:12 -05:00
0719a46372
add support for SDXL textual inversion/embeddings
2023-12-01 01:28:28 -05:00
ecd3dcd5df
Merge branch 'main' into refactor/model-manager-3
2023-11-27 22:15:51 -05:00
e509d719ee
Fix attempt to deserialize on CUDA on Mac
...
Without specifying "cpu", attempts to use non-existent CUDA to deserialize embeddings on macOS, resulting in a warning / failure to load.
2023-11-28 09:24:57 +11:00
8ef596eac7
further changes for ruff
2023-11-26 17:13:31 -05:00
8c7a7bc897
Merge branch 'main' into refactor/model-manager-3
2023-11-22 22:29:23 -05:00
4aab728590
move name/description logic into model_probe.py
2023-11-22 22:29:02 -05:00
98a4930a52
add probe support for LCM main models
2023-11-22 14:58:27 -05:00
1a596a5684
fix(backend): fix unintentional change to import orders
...
- Ignore I001 (isort rules) for this file
- Ignore F401 (unused imports) for this file
2023-11-21 20:22:27 +11:00
da443973cb
chore: ruff
2023-11-21 20:22:27 +11:00
6494e8e551
chore: ruff format
2023-11-11 10:55:40 +11:00
99a8ebe3a0
chore: ruff check - fix flake8-bugbear
2023-11-11 10:55:28 +11:00
3a136420d5
chore: ruff check - fix flake8-comprensions
2023-11-11 10:55:23 +11:00
6001d3d71d
Change pad_to_multiple_of to be 8 for all cases. Add comment about it's temporary status
2023-11-10 17:51:59 -05:00
8831d1ee41
Update Documentation
2023-11-10 17:51:59 -05:00
a0be83e370
Update Transformers to 4.34 and fix pad_to_multiple_of
2023-11-10 17:51:59 -05:00
8702a63197
add support for downloading and installing LCM lora diffusers models
2023-11-10 17:51:30 -05:00
6aa87f973e
fix(nodes): create app/shared/ module to prevent circular imports
...
We have a number of shared classes, objects, and functions that are used in multiple places. This causes circular import issues.
This commit creates a new `app/shared/` module to hold these shared classes, objects, and functions.
Initially, only `FreeUConfig` and `FieldDescriptions` are moved here. This resolves a circular import issue with custom nodes.
Other shared classes, objects, and functions will be moved here in future commits.
2023-11-09 16:41:55 +11:00
e66d0f7372
Merge branch 'main' into feat/nodes/freeu
2023-11-06 05:39:58 -08:00
aa02ebf8f5
Fix model cache gc.collect() condition.
2023-11-04 08:52:10 -04:00
fb3d0c4b12
Fix bug in model cache reference count checking.
2023-11-03 13:50:40 -07:00
8488ab0134
Reduce frequency that we call gc.collect() in the model cache.
2023-11-03 13:50:40 -07:00
875231ed3d
Add reminder to clean up our model cache clearing logic.
2023-11-03 13:50:40 -07:00
43b300498f
Remove explicit gc.collect() after transferring models from device to CPU. I'm not sure why this was there in the first place, but it was taking a significant amount of time (up to ~1sec in my tests).
2023-11-03 13:50:40 -07:00
e391f3c9a8
Skip torch.nn.Embedding.reset_parameters(...) when loading a text encoder model.
2023-11-02 19:41:33 -07:00
6e7a3f0546
(minor) Fix static checks and typo.
2023-11-02 19:20:37 -07:00
4a683cc669
Add a app config parameter to control the ModelCache logging behavior.
2023-11-02 19:20:37 -07:00
3781e56e57
Add log_memory_usage param to ModelCache.
2023-11-02 19:20:37 -07:00
8ff49109a8
Update get_pretty_snapshot_diff(...) to handle None-snapshots.
2023-11-02 19:20:37 -07:00
bac2a757e8
Replace deepcopy with a pickle roundtrip in apply_ti(...) to improve speed.
2023-11-02 19:05:24 -07:00
fa7f6a6a10
Further tidying of LoRA patching. Revert some changes that didn't end up being important under the constraint that calculations are done on the same device as the model.
2023-11-02 10:03:17 -07:00
61b17c475a
Add TODO note about improving _resolve_lora_key(...).
2023-11-02 10:03:17 -07:00
379d68f595
Patch LoRA on device when model is already on device.
2023-11-02 10:03:17 -07:00
545c811bf1
Remove device and dtype members from LoRAModelRaw, they can too easily get out-of-sync with the underlying layer states.
2023-11-02 10:03:17 -07:00
2ba5b44ec4
Remove unused _lora_forward_hook(...).
2023-11-02 10:03:17 -07:00
