Sean Sube
|
421ed632b1
|
only use name from first inversion
|
2023-03-15 08:53:15 -05:00 |
Sean Sube
|
b2eb406197
|
fix(api): handle CUDA memory errors in workers
|
2023-03-15 08:51:29 -05:00 |
Sean Sube
|
a2e21f427f
|
feat(api): load Textual Inversions from prompt
|
2023-03-15 08:51:12 -05:00 |
Sean Sube
|
829cedc934
|
fix error when prompt has no LoRA tokens
|
2023-03-15 08:35:44 -05:00 |
Sean Sube
|
a7f77a033d
|
feat(api): parse LoRA weights from prompt
|
2023-03-15 08:30:31 -05:00 |
Sean Sube
|
45166f281e
|
apply lint
|
2023-03-14 23:32:47 -05:00 |
Sean Sube
|
91210ee236
|
remove extra param, correct output path
|
2023-03-14 23:32:18 -05:00 |
Sean Sube
|
143904fc51
|
feat(api): parse LoRA names from prompt
|
2023-03-14 22:28:18 -05:00 |
Sean Sube
|
03f4e1b922
|
start wiring LoRAs into prompt
|
2023-03-14 22:10:33 -05:00 |
Sean Sube
|
ce05e76947
|
load base models from model dir, use correct ORT provider
|
2023-03-14 21:57:37 -05:00 |
Sean Sube
|
56a4519818
|
test loading UNet and encoder with LoRAs
|
2023-03-14 21:27:23 -05:00 |
Sean Sube
|
2a8c85cb3e
|
feat(api): blend ONNX models in memory
|
2023-03-14 19:38:27 -05:00 |
Sean Sube
|
4c17edb267
|
feat(api): add conversion script for LoRAs from sd-scripts (#213)
|
2023-03-14 18:17:00 -05:00 |
Sean Sube
|
0b1aa26be5
|
blend LoRAs into a valid ONNX UNet (#213)
|
2023-03-12 13:38:51 -05:00 |
Sean Sube
|
919f88c7d0
|
fix(tests): clear cache between tests
|
2023-03-11 13:59:09 -06:00 |
Sean Sube
|
9555a7a3ea
|
lint(api): only log new worker message if some workers need to be restarted
|
2023-03-11 13:30:54 -06:00 |
Sean Sube
|
9c65922526
|
lint(api): remove unnecessary delete calls
|
2023-03-11 13:30:33 -06:00 |
Sean Sube
|
575cb8831b
|
fix(api): make cache global within each worker process (#227)
|
2023-03-11 13:30:11 -06:00 |
Sean Sube
|
01d3519aa3
|
fix(api): remove unused num_workers logic from server
|
2023-03-11 08:17:27 -06:00 |
Sean Sube
|
8e5d0871c8
|
log which cache items have been pruned
|
2023-03-11 08:06:22 -06:00 |
Sean Sube
|
cb2b054fde
|
fix(api): only run GC when a diffusion model has been replaced
|
2023-03-11 08:06:03 -06:00 |
Sean Sube
|
cd11e8f3ab
|
use a proper fake config class
|
2023-03-10 18:57:01 -06:00 |
Sean Sube
|
df1504d9b0
|
use fake VAE config
|
2023-03-10 18:50:01 -06:00 |
Sean Sube
|
555de5e07d
|
fix(api): correct VAE config check
|
2023-03-10 18:46:07 -06:00 |
Sean Sube
|
e960ee1d85
|
fix(api): patch VAE for SD upscaling on older versions of diffusers (#234)
|
2023-03-10 18:42:11 -06:00 |
Sean Sube
|
6bdaa4a4ed
|
fix(api): make stage-specific source image optional in GFPGAN stage (#233)
|
2023-03-10 18:15:31 -06:00 |
Sean Sube
|
da3d95ff49
|
fix(api): include bottom margin when calculating output size
|
2023-03-10 17:59:16 -06:00 |
Sean Sube
|
fe437e8cd4
|
feat: add support for UniPC multistep scheduler (#226)
|
2023-03-09 08:00:59 -06:00 |
Sean Sube
|
21c60709bc
|
fix(api): move prompt splitting logging to debug level
|
2023-03-08 22:55:58 -06:00 |
Sean Sube
|
25c41c8d66
|
feat(api): add an option to remove temporary Torch files after converting to ONNX (#122)
|
2023-03-08 21:38:17 -06:00 |
Sean Sube
|
6e71775782
|
fix(api): load LPW pipeline from local source (#224)
|
2023-03-08 19:47:22 -06:00 |
Sean Sube
|
7bd98d4a46
|
apply lint
|
2023-03-07 23:57:39 -06:00 |
Sean Sube
|
bc21165fd9
|
fix path ref
|
2023-03-07 23:54:32 -06:00 |
Sean Sube
|
c0b88733b8
|
fix(api): check for cache rather than converted model before fetch
|
2023-03-07 23:51:27 -06:00 |
Sean Sube
|
843e2f1ff3
|
feat(api): look for an index file when checking for converted models (#222)
|
2023-03-07 23:40:04 -06:00 |
Sean Sube
|
30b08c6d6d
|
fix(api): log correct token when converting Textual Inversions
|
2023-03-07 23:05:53 -06:00 |
Sean Sube
|
6542646005
|
fix(api): match format in schema for sd-concepts
|
2023-03-07 22:53:05 -06:00 |
Sean Sube
|
85ff700525
|
apply lint
|
2023-03-07 22:40:17 -06:00 |
Sean Sube
|
0a4f83ac0f
|
feat(api): add range syntax to expand numbered tokens (#179)
|
2023-03-07 20:48:26 -06:00 |
Sean Sube
|
66c42485cb
|
feat(api): add support for extremely long prompts
|
2023-03-07 19:00:25 -06:00 |
Sean Sube
|
c45915e558
|
fix(api): use server model path while converting SD checkpoints (#221)
|
2023-03-07 18:55:14 -06:00 |
Sean Sube
|
9d9bd1a639
|
apply lint
|
2023-03-07 08:02:53 -06:00 |
Sean Sube
|
af1c3c7839
|
fix(api): track items removed from cache
|
2023-03-06 07:34:09 -06:00 |
Sean Sube
|
339868de4d
|
fix(api): use pipeline class name in cache key
|
2023-03-05 21:54:09 -06:00 |
Sean Sube
|
55576ae87c
|
fix(api): include cache keys in logs
|
2023-03-05 21:50:01 -06:00 |
Sean Sube
|
35dc8a0bc4
|
improve exit logging
|
2023-03-05 21:37:39 -06:00 |
Sean Sube
|
c0a01efef4
|
fix(api): track currently active worker for each device
|
2023-03-05 21:28:21 -06:00 |
Sean Sube
|
57fed94337
|
fix(api): exit worker on memory allocation errors
|
2023-03-05 21:11:33 -06:00 |
Sean Sube
|
cb460a0c59
|
fix(api): add worker PID to log messages
|
2023-03-05 20:25:02 -06:00 |
Sean Sube
|
4ae4ce176c
|
fix(api): attempt to recycle leaking workers when a job finishes
|
2023-03-05 20:13:28 -06:00 |
Sean Sube
|
3a4928e59b
|
fix(api): prevent workers from blocking on their progress queues
|
2023-03-05 20:07:06 -06:00 |
Sean Sube
|
edc55ae8b4
|
fix(api): finished job notification should not block worker
|
2023-03-05 19:53:44 -06:00 |
Sean Sube
|
cfc20d3133
|
fix(api): improve cache logging
|
2023-03-05 19:30:52 -06:00 |
Sean Sube
|
39b9741b24
|
fix(api): show VRAM percent in logs
|
2023-03-05 19:23:23 -06:00 |
Sean Sube
|
7a3a81a4ef
|
fix(api): track and repeatedly attempt to recycle leaking workers (#219)
|
2023-03-05 18:58:13 -06:00 |
Sean Sube
|
468870e2e7
|
apply lint
|
2023-03-05 08:14:47 -06:00 |
Sean Sube
|
00fa9c5807
|
feat(api): collect labels from textual inversions (#144)
|
2023-03-05 08:00:25 -06:00 |
Sean Sube
|
6d2dd0a043
|
apply lint
|
2023-03-05 07:20:43 -06:00 |
Sean Sube
|
539d0febce
|
load extras during server init
|
2023-03-05 07:20:37 -06:00 |
Sean Sube
|
537c67619e
|
fix strings endpoint
|
2023-03-05 07:20:34 -06:00 |
Sean Sube
|
5d459ab17c
|
feat: allow users to add their own labels for models (#144)
|
2023-03-05 07:20:31 -06:00 |
Sean Sube
|
628812fb0b
|
fix(api): correct conversion imports
|
2023-03-04 23:03:15 -06:00 |
Sean Sube
|
43d4d4b86d
|
chore(api): dedupe model listing logic
|
2023-03-04 22:26:27 -06:00 |
Sean Sube
|
10fbafaff0
|
fix(api): correct imports
|
2023-03-04 22:25:49 -06:00 |
Sean Sube
|
7b88371832
|
lint(api): use load pattern in server submodule
|
2023-03-04 22:13:09 -06:00 |
Sean Sube
|
bb1d945761
|
lint(api): submodules for major libs
|
2023-03-04 22:12:35 -06:00 |
Sean Sube
|
39d36618e6
|
feat(api): add support for custom tokens for textual inversions (#179)
|
2023-03-02 23:32:20 -06:00 |
Sean Sube
|
22e9d54408
|
apply lint
|
2023-03-02 22:32:37 -06:00 |
Sean Sube
|
be1c8cd79f
|
feat(api): support ckpt inversions by splitting multivector embeddings into multiple tokens
|
2023-03-02 22:11:27 -06:00 |
Sean Sube
|
9a0d2051fb
|
fix(api): better logging when converting textual inversions
|
2023-03-02 07:57:59 -06:00 |
Sean Sube
|
46aac263d5
|
feat(api): initial support for textual inversion embeddings from civitai and others (#179)
|
2023-03-01 19:09:51 -06:00 |
Sean Sube
|
1f3a5f6f3c
|
fix(api): track completed jobs for each device worker (#170)
|
2023-03-01 19:09:18 -06:00 |
Sean Sube
|
4b77a00ca7
|
fix(api): load tokenizer with textual inversions
|
2023-03-01 19:08:31 -06:00 |
Sean Sube
|
21fc7c5968
|
fix(api): mark all convert methods as no_grad
|
2023-03-01 08:26:40 -06:00 |
Sean Sube
|
3f9f94fcb5
|
apply lint, remove unused
|
2023-02-28 23:05:17 -06:00 |
Sean Sube
|
2f4ab20f61
|
use filename for tensors
|
2023-02-28 22:49:53 -06:00 |
Sean Sube
|
74aae1b027
|
fix(api): write external weights into same directory as optimized model
|
2023-02-28 22:47:02 -06:00 |
Sean Sube
|
dbf9eaf1a4
|
fix(api): run shape inference before converting models to fp16
per discussion in https://github.com/microsoft/onnxruntime/issues/14827
|
2023-02-28 22:36:45 -06:00 |
Sean Sube
|
86984be5d4
|
better error logging during conversion
|
2023-02-28 22:36:36 -06:00 |
Sean Sube
|
9ef89db8b0
|
extract tensors after conversion
|
2023-02-28 22:36:33 -06:00 |
Sean Sube
|
7e65e21410
|
reload model from proto file before converting
|
2023-02-28 22:36:26 -06:00 |
Sean Sube
|
2210ee849b
|
only convert inner nodes with ORT conversion helpers
|
2023-02-28 22:26:04 -06:00 |
Sean Sube
|
b532570f54
|
fix(api): reuse ORT session params for each device
|
2023-02-28 22:24:38 -06:00 |
Sean Sube
|
565873b3ae
|
test half precision on all diffusion models
|
2023-02-28 22:23:55 -06:00 |
Sean Sube
|
1f9efb433a
|
apply lint
|
2023-02-28 22:04:55 -06:00 |
Sean Sube
|
12fb7f52bb
|
fix(api): sanitize filenames in user input
|
2023-02-28 21:56:12 -06:00 |
Sean Sube
|
c99aa67220
|
name threads, max queues, type/lint fixes
|
2023-02-28 21:44:52 -06:00 |
Sean Sube
|
c95ac1fbdd
|
avoid terminating workers because it breaks their queues
|
2023-02-28 08:53:17 -06:00 |
Sean Sube
|
0011f079d4
|
daemonize queue collectors
|
2023-02-28 06:55:15 -06:00 |
Sean Sube
|
cad0d37604
|
some pending queue logging
|
2023-02-27 23:43:38 -06:00 |
Sean Sube
|
4ae3d9caa2
|
remove task done
|
2023-02-27 23:18:37 -06:00 |
Sean Sube
|
7e0ccdb1af
|
remove pending queues after joining
|
2023-02-27 23:14:20 -06:00 |
Sean Sube
|
1ce98ace33
|
add value error handling
|
2023-02-27 23:12:53 -06:00 |
Sean Sube
|
f7f438e767
|
directly rejoin pool
|
2023-02-27 23:03:42 -06:00 |
Sean Sube
|
da6ae5d62f
|
more logging around shutdown, close queues
|
2023-02-27 23:01:26 -06:00 |
Sean Sube
|
988088d64e
|
quit workers on keyboard signal
|
2023-02-27 22:52:43 -06:00 |
Sean Sube
|
953e5abd36
|
handle empty errors
|
2023-02-27 22:45:29 -06:00 |
Sean Sube
|
136759285d
|
set queue timeouts
|
2023-02-27 22:37:43 -06:00 |
Sean Sube
|
0793b61c3a
|
consistently pass job key to workers
|
2023-02-27 22:25:53 -06:00 |
Sean Sube
|
06f06f5a11
|
error handling in all threads
|
2023-02-27 19:48:51 -06:00 |