8b7925edf3
fix crash in textual inversion with "num_samples=0" error
...
-At some point pathlib was added to the list of imported modules and this
broken the os.path code that assembled the sample data set.
-Now fixed by replacing os.path calls with Path methods
2023-02-22 11:29:30 -05:00
d41dcdfc46
move trigger_str registration into try block
2023-02-21 21:38:42 -05:00
5e41811fb5
move trigger text munging to upper level per review
2023-02-21 17:04:42 -05:00
1d0ba4a1a7
Merge branch 'main' into bugfix/filename-embedding-fallback
2023-02-21 13:12:34 -06:00
71bbd78574
Fix crashing when using 2.1 model
...
We now require more free memory to avoid attention slicing. 17.5% free was not sufficient headroom, so now we require 25%.
2023-02-21 12:35:03 -06:00
d5f524a156
Merge branch 'main' into bugfix/filename-embedding-fallback
2023-02-22 06:13:41 +13:00
3ab9d02883
Fixed embiggening crash due to clear_cuda_cache not being passed on and bad cuda stats initialization. ( #2756 )
2023-02-22 06:12:24 +13:00
da04b11a31
Merge branch 'main' into bugfix/filename-embedding-fallback
2023-02-21 10:52:13 -06:00
9436f2e3d1
alphabetize trigger strings
2023-02-21 06:23:34 -05:00
4c2a588e1f
Merge branch 'main' into perf/lowmem_sequential_guidance
2023-02-20 22:40:31 -05:00
91f7abb398
replace repeated triggers with <filename>
2023-02-20 22:33:13 -05:00
833079140b
Merge branch 'main' into enhance/update-menu
2023-02-20 17:16:20 -05:00
fd27948c36
Merge branch 'main' into perf/lowmem_sequential_guidance
2023-02-20 17:15:33 -05:00
a30c91f398
Merge branch 'main' into bugfix/textual-inversion-training
2023-02-21 09:58:19 +13:00
3fa1771cc9
Merge branch 'main' into perf/lowmem_sequential_guidance
2023-02-20 15:20:15 -05:00
1d9845557f
reduced verbosity of embed loading messages
2023-02-20 15:18:55 -05:00
47ddc00c6a
in textual inversion training, skip over non-image files
...
- Closes #2715
2023-02-20 14:44:10 -05:00
0d22fd59ed
restore ability of textual inversion manager to read .pt files
...
- Fixes longstanding bug in the token vector size code which caused
.pt files to be assigned the wrong token vector length. These
were then tossed out during directory scanning.
2023-02-20 14:34:14 -05:00
cf53bba99e
Merge branch 'main' into bugfix/save-intermediates
2023-02-20 12:51:53 -05:00
ed4c8f6a8a
fix crash in CLI when --save_intermediates called
...
Fixes #2733
2023-02-20 12:50:32 -05:00
b21bd6f428
Fix crash on calling diffusers' prepare_attention_mask
...
Diffusers' `prepare_attention_mask` was crashing when we didn't pass in a batch size.
2023-02-20 11:12:47 -06:00
cb6903dfd0
Merge branch 'main' into perf/lowmem_sequential_guidance
2023-02-20 08:03:11 -08:00
58e5bf5a58
Merge branch 'main' into bugfix/embedding-compatibility-test
2023-02-21 04:09:18 +13:00
cc7733af1c
Merge branch 'main' into enhance/update-menu
2023-02-21 03:54:40 +13:00
cfd897874b
Merge branch 'main' into perf/lowmem_sequential_guidance
2023-02-20 07:42:35 -05:00
1249147c57
Merge branch 'main' into enhance/update-menu
2023-02-20 07:38:56 -05:00
eec5c3bbb1
Merge branch 'main' into main
2023-02-20 07:38:08 -05:00
ca8d9fb885
Add symmetry to generation ( #2675 )
...
Added symmetry to Invoke based on discussions with @damian0815. This can currently only be activated via the CLI with the `--h_symmetry_time_pct` and `--v_symmetry_time_pct` options. Those take values from 0.0-1.0, exclusive, indicating the percentage through generation at which symmetry is applied as a one-time operation. To have symmetry in either axis applied after the first step, use a very low value like 0.001.
2023-02-20 07:33:19 -05:00
2dded68267
add --sequential_guidance option for low-RAM tradeoff
2023-02-19 21:21:14 -08:00
172ce3dc25
correctly detect when an embedding is incompatible with the current model
...
- Fixed the test for token length; tested on several .pt and .bin files
- Also added a __main__ entrypoint for CLI.py, to make pdb debugging a bit
more convenient.
2023-02-19 22:30:57 -05:00
6c8d4b091e
dev(InvokeAIDiffuserComponent): mollify type checker's concern about the optional argument
2023-02-19 16:58:54 -08:00
d0abe13b60
performance(InvokeAIDiffuserComponent): add low-memory path for calculating conditioned and unconditioned predictions sequentially
...
Proof of concept. Still needs to be wired up to options or heuristics.
2023-02-19 16:04:54 -08:00
aca9d74489
refactor(InvokeAIDiffuserComponent): rename internal methods
...
Prefix with `_` as is tradition.
2023-02-19 15:33:16 -08:00
d3c1b747ee
Fix behavior when encountering a bad embedding ( #2721 )
...
When encountering a bad embedding, InvokeAI was asking about reconfiguring models. This is because the embedding load error was never handled - it now is.
2023-02-19 14:04:59 +00:00
671c5943e4
Merge remote-tracking branch 'origin/main' into api/add-trigger-string-retrieval
...
# Conflicts:
# ldm/generate.py
2023-02-18 17:44:59 -08:00
d01b7ea2d2
remove debug statement & actually do merge
2023-02-18 11:19:06 -05:00
4fa91724d9
fix conversion of checkpoints into incompatible diffusers models
...
- The checkpoint conversion script was generating diffusers models
with the safety checker set to null. This resulted in models
that could not be merged with ones that have the safety checker
activated.
- This PR fixes the issue by incorporating the safety checker into
all 1.x-derived checkpoints, regardless of user's nsfw_checker setting.
2023-02-18 11:07:38 -05:00
d5d2e1d7a3
Merge branch 'main' into fix/expected-torch-device
2023-02-18 15:23:08 +01:00
2bf2f627e4
Fix for issue #2707
2023-02-18 11:40:12 +01:00
11a70e9764
Merge branch 'main' into patch-14
2023-02-18 18:45:05 +13:00
6b702c32ca
fix(xformers): shush about not having Triton available.
...
It's not readily available on Windows and xformers only uses it on some very specific hardware anyway.
2023-02-17 17:41:27 -08:00
b8212e4dea
fix(diffusers_pipeline): ensure cuda.get_mem_info always gets a specific device index.
...
Also tighten up the typing of `device` attributes in general.
2023-02-17 16:56:15 -08:00
1ae8986451
add log_tokenization to globals
2023-02-17 16:47:32 -05:00
b305c240de
fix syntax errors introduced by github web-ui edits
2023-02-17 16:44:20 -05:00
7a518218e5
AttributeError: 'Namespace' object has no attribute 'log_tokenization'
...
Could be fixed here or alternatively declared in file globals.py
2023-02-17 22:11:49 +01:00
fc14ac7faa
Merge branch 'main' into api/add-trigger-string-retrieval
2023-02-17 15:53:57 -05:00
95e2739c47
Merge branch 'main' into bugfix/merge-gui
2023-02-17 15:42:53 -05:00
f129393a2e
document add_difference on-screen
2023-02-17 15:42:06 -05:00
4888d0d832
fix slider and interpolations
...
- fix alpha slider to show values from 0.01 to 0.99
- fix interpolation list to show 'difference' method for 3 models,
- and weighted_sum, sigmoid and inverse_sigmoid methods for 2
2023-02-17 14:46:26 -05:00
47de3fb007
correct display of 'add_difference' method when three models defined
...
- due to typo, the add_difference method was being displayed as "['add_difference']"
2023-02-17 14:41:02 -05:00
