fe1967a4c4
skip multihead attn for now
2023-11-03 17:52:55 -07:00
d727ddfccd
no idea what i'm doing, trying to support both type of OFT, kblueleaf diag_oft has MultiheadAttn which kohya's doesn't?, attempt create new module based off network_lora.py, errors about tensor dim mismatch
2023-11-02 00:13:11 -07:00
65ccd6305f
detect diag_oft type
2023-11-02 00:11:32 -07:00
a2fad6ee05
test implementation based on kohaku diag-oft implementation
2023-11-01 22:34:27 -07:00
6523edb8a4
style: conform style
2023-10-22 09:31:15 -07:00
3b8515d2c9
fix: multiplier applied twice in finalize_updown
2023-10-22 09:27:48 -07:00
4a50c9638c
refactor: remove used OFT functions
2023-10-22 08:54:24 -07:00
de8ee92ed8
fix: use merge_weight to cache value
2023-10-21 17:37:17 -07:00
76f5abdbdb
style: cleanup oft
2023-10-21 16:07:45 -07:00
fce86ab7d7
fix: support multiplier, no forward pass hook
2023-10-21 16:03:54 -07:00
7683547728
fix: return orig weights during updown, merge weights before forward
2023-10-21 14:42:24 -07:00
2d8c894b27
refactor: use forward hook instead of custom forward
2023-10-21 13:43:31 -07:00
0550659ce6
style: fix ambiguous variable name
2023-10-19 13:13:02 -07:00
d10c4db57e
style: formatting
2023-10-19 12:52:14 -07:00
321680ccd0
refactor: fix constraint, re-use get_weight
2023-10-19 12:41:17 -07:00
7c128bbdac
Add fp8 for sd unet
2023-10-19 13:56:17 +08:00
eb01d7f0e0
faster by calculating R in updown and using cached R in forward
2023-10-18 04:56:53 -07:00
853e21d98e
faster by using cached R in forward
2023-10-18 04:27:44 -07:00
1c6efdbba7
inference working but SLOW
2023-10-18 04:16:01 -07:00
ec718f76b5
wip incorrect OFT implementation
2023-10-17 23:35:50 -07:00
4be7b620c2
Merge pull request #13568 from AUTOMATIC1111/lora_emb_bundle
...
Add lora-embedding bundle system
2023-10-14 12:18:55 +03:00
a8cbe50c9f
remove duplicated code
2023-10-14 12:17:59 +03:00
906d1179e9
support inference with LyCORIS GLora networks
2023-10-11 21:26:58 -07:00
891ccb767c
Fix lint
2023-10-10 15:07:25 +08:00
81e94de318
Add warning when meet emb name conflicting
...
Choose standalone embedding (in /embeddings folder) first
2023-10-10 14:44:20 +08:00
2282eb8dd5
Remove dev debug print
2023-10-10 12:11:00 +08:00
3d8b1af6be
Support string_to_param nested dict
...
format:
bundle_emb.EMBNAME.string_to_param.KEYNAME
2023-10-10 12:09:33 +08:00
2aa485b5af
add lora bundle system
2023-10-09 22:52:09 +08:00
74b80e7211
add comment
2023-09-12 09:29:07 +09:00
e785402b6a
return nothing if not found
2023-09-11 19:37:55 +09:00
7d4d871d46
fix: lora-bias-backup don't reset cache
2023-09-10 17:53:42 +08:00
f5959c1c30
thread safe extra network using list
2023-09-09 17:05:50 +09:00
25de9a785c
Revert "thread safe extra network list_items"
...
This reverts commit aab385d01b
2023-09-09 16:56:19 +09:00
aab385d01b
thread safe extra network list_items
2023-09-03 11:56:02 +09:00
d83a1ba65b
feat: display file metadata ss_output_name
...
https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/12289
2023-08-29 06:33:00 +08:00
86221269f9
RAM optimization round 2
2023-08-16 09:55:35 +03:00
85fcb7b8df
lint
2023-08-15 19:25:03 +03:00
8b181c812f
Merge pull request #12584 from AUTOMATIC1111/full-module-with-bias
...
Add ex_bias into full module
2023-08-15 19:24:15 +03:00
f01682ee01
store patches for Lora in a specialized module
2023-08-15 19:23:40 +03:00
aa57a89a21
full module with ex_bias
2023-08-15 23:41:46 +08:00
f70ded8936
remove "if bias exist" check
2023-08-14 13:53:40 +08:00
e7c03ccdce
Merge branch 'dev' into extra-norm-module
2023-08-14 13:34:51 +08:00
d9cc27cb29
Fix MHA updown err and support ex-bias for no-bias layer
2023-08-14 13:32:51 +08:00
1c6ca09992
Merge pull request #12510 from catboxanon/feat/extnet/hashes
...
Support search and display of hashes for all extra network items
2023-08-13 16:46:32 +03:00
db40d26d08
linter
2023-08-13 16:38:10 +03:00
d8419762c1
Lora: output warnings in UI rather than fail for unfitting loras; switch to logging for error output in console
2023-08-13 15:07:37 +03:00
7fa5ee54b1
Support search and display of hashes for all extra network items
2023-08-13 02:32:54 -04:00
5881dcb887
remove debug print
2023-08-13 02:36:02 +08:00
a2b8305096
return None if no ex_bias
2023-08-13 02:35:04 +08:00
bd4da4474b
Add extra norm module into built-in lora ext
...
refer to LyCORIS 1.9.0.dev6
add new option and module for training norm layer
(Which is reported to be good for style)
2023-08-13 02:27:39 +08:00
4fafc34e49
Fix to make LoRA old method setting work
2023-08-10 23:42:58 -04:00
eed963e972
Lora cache in memory
2023-08-09 16:54:49 +03:00
362789a379
gradio 3.39
2023-08-04 08:04:23 +03:00
91a131aa6c
update lora extension to work with python 3.8
2023-07-27 09:00:47 +03:00
d0bf509fa1
fix for #11963
2023-07-25 16:18:10 +03:00
a68f469030
Fix to parse TE in some LoRAs
2023-07-24 17:54:59 -04:00
b010eea520
fix incorrect multiplier for Loras
2023-07-19 00:41:00 +03:00
136c8859a4
add backwards compatibility --lyco-dir-backcompat option, use that for LyCORIS directory instead of hardcoded value
...
prevent running preload.py for disabled extensions
2023-07-18 20:11:30 +03:00
4b5a63aa11
add a bit more metadata info for the lora user metadata page
2023-07-18 17:32:46 +03:00
3d31caf4a5
use "is not None" for Tensor
2023-07-18 10:45:42 +08:00
17e14ed2d9
Fix wrong key name in lokr module
2023-07-18 10:23:41 +08:00
699108bfbb
hide cards for networks of incompatible stable diffusion version in Lora extra networks interface
2023-07-17 18:56:22 +03:00
35510f7529
add alias to lyco network
...
read networks from LyCORIS dir if it exists
add credits
2023-07-17 10:06:02 +03:00
2e07a8ae6b
some backwards compatibility
...
linter
2023-07-17 09:05:18 +03:00
238adeaffb
support specifying te and unet weights separately
...
update lora code
support full module
2023-07-17 09:00:47 +03:00
46466f09d0
Lokr support
2023-07-17 00:29:07 +03:00
58c3df32f3
IA3 support
2023-07-17 00:12:18 +03:00
ef5dac7786
fix
2023-07-17 00:01:17 +03:00
c2297b89d3
linter
2023-07-16 23:14:57 +03:00
b75b004fe6
lora extension rework to include other types of networks
2023-07-16 23:13:55 +03:00
0198eaec45
Merge pull request #11757 from AUTOMATIC1111/sdxl
...
SD XL support
2023-07-16 12:04:53 +03:00
7b052eb70e
add resolution calculation from buckets for lora user metadata page
2023-07-16 10:07:02 +03:00
47d9dd0240
speedup extra networks listing
2023-07-16 09:25:32 +03:00
a1d6ada69a
allow refreshing single card after editing user metadata instead of all cards
2023-07-16 08:38:23 +03:00
11f339733d
add lora user metadata editor dialog inspired by MrKuenning's mockup from #7458
2023-07-16 00:57:45 +03:00
e5d3ae2bf4
user metadata system for custom networks
2023-07-15 20:39:10 +03:00
dc39061856
thank you linter
2023-07-13 21:19:41 +03:00
6c5f83b19b
add support for SDXL loras with te1/te2 modules
2023-07-13 21:17:50 +03:00
76ebb175ca
lora support
2023-07-13 12:59:31 +03:00
d7d6e8cfc8
use natural sort for shared.walk_files and shared.listfiles, as well as for dirs in extra networks
2023-07-08 16:45:59 +03:00
d75ed52bfc
Don't die when a LoRA is a broken symlink
...
Fixes #11098
2023-06-09 13:26:36 +03:00
7a7a201d81
Merge pull request #10956 from akx/len
...
Simplify a bunch of `len(x) > 0`/`len(x) == 0` style expressions
2023-06-05 11:06:37 +03:00
9009e25cb1
Apply suggestions from code review
...
Co-authored-by: Aarni Koskela <akx@iki.fi>
2023-06-02 16:12:24 -04:00
51864790fd
Simplify a bunch of `len(x) > 0`/`len(x) == 0` style expressions
2023-06-02 15:07:10 +03:00
7dca8e7698
Support dynamic sort of extra networks
2023-06-02 04:08:45 +00:00
39ec4f06ff
calculate hashes for Lora
...
add lora hashes to infotext
when pasting infotext, use infotext's lora hashes to find local loras for <lora:xxx:1> entries whose hashes match loras the user has
2023-05-19 22:59:29 +03:00
2725dfd8a6
Fix ruff lint
2023-05-19 12:37:34 +03:00
e38e7dbfb9
Merge pull request #10529 from ryankashi/master
...
Added /sdapi/v1/refresh-loras api checkpoint post request
2023-05-19 08:04:13 +03:00
4dd5559162
Added the refresh-loras post request
2023-05-18 14:12:01 -07:00
44c37f94e1
add messages about Loras that failed to load to UI
2023-05-18 16:36:30 +03:00
7001e1ed61
Merge branch 'master' into dev
2023-05-14 13:36:16 +03:00
b9abdb50a3
add a possible fix for 'LatentDiffusion' object has no attribute 'lora_layer_mapping'
2023-05-14 13:31:03 +03:00
e8eea1bb7a
Merge branch 'release_candidate' into dev
2023-05-13 20:26:13 +03:00
477199357f
add an option to always refer to lora by filenames
...
never refer to lora by an alias if multiple loras have same alias or the alias is called none
2023-05-13 20:15:37 +03:00
3ec7b705c7
suggestions and fixes from the PR
2023-05-10 21:21:32 +03:00
a5121e7a06
fixes for B007
2023-05-10 11:37:18 +03:00
028d3f6425
ruff auto fixes
2023-05-10 11:05:02 +03:00
f741a98bac
imports cleanup for ruff
2023-05-10 08:43:42 +03:00
eb95809501
rework loras api
2023-05-09 11:25:46 +03:00
f9abe4cddc
Add api method to get LoRA models with prompt
2023-05-08 20:38:10 +08:00
v0xie