Sean Sube
|
1d5ac7dde5
|
optimize XL LoRA node matching
|
2023-09-04 21:20:54 -05:00 |
Sean Sube
|
ea9023c2eb
|
fix(api): only run SDXL LoRA node matching on XL models
|
2023-09-04 21:20:39 -05:00 |
Sean Sube
|
ecac0d5770
|
apply lint
|
2023-09-04 21:20:33 -05:00 |
Sean Sube
|
bbacfd1ca0
|
feat(api): support for SDXL LoRAs
|
2023-09-04 21:20:30 -05:00 |
Sean Sube
|
404a314050
|
lint(api): add typed errors from cancelled job and download error
|
2023-09-04 21:20:04 -05:00 |
Sean Sube
|
8e1f188d8f
|
fix(api): pass replacement VAE to diffusers conversion
|
2023-09-04 21:19:36 -05:00 |
Sean Sube
|
6ec7777f77
|
lint(api): type fixes and hints throughout
|
2023-07-04 10:20:28 -05:00 |
Sean Sube
|
7c8dc7a6b6
|
feat(api): create hash file for models without one
|
2023-06-27 08:17:21 -05:00 |
Sean Sube
|
062b1c47aa
|
feat(api): write model hashes to image exif
|
2023-06-26 17:24:34 -05:00 |
Sean Sube
|
7db53a82df
|
fix(api): correctly handle sliced kernels
|
2023-06-17 14:51:58 -05:00 |
Sean Sube
|
1506f51ff4
|
fix(api): handle more SwinIR models
|
2023-06-16 21:53:49 -05:00 |
Sean Sube
|
5713957026
|
fix(api): keep kernel slices within bounds
|
2023-06-16 20:49:43 -05:00 |
Sean Sube
|
c1a4484b75
|
apply lint
|
2023-06-16 20:43:28 -05:00 |
Sean Sube
|
719b34967f
|
fix(api): handle blending of mismatched kernels
|
2023-06-16 20:41:25 -05:00 |
Sean Sube
|
ac2eceb0ac
|
fix(api): remove trailing space from param name
|
2023-06-10 11:54:33 -05:00 |
Sean Sube
|
e64b813ac0
|
fix(api): pass inpaint param to checkpoint extraction
|
2023-06-10 11:52:25 -05:00 |
Sean Sube
|
665cf57a86
|
fix typo
|
2023-06-10 11:30:47 -05:00 |
HoopyFreud
|
22ff0be758
|
fix inpainting conversion via torch
|
2023-06-10 12:01:02 -04:00 |
Sean Sube
|
f4d944acbe
|
apply lint
|
2023-06-08 07:20:19 -05:00 |
Sean Sube
|
3f00da9681
|
feat(api): add option for CPU-only conversion on systems with CUDA
|
2023-06-08 07:20:03 -05:00 |
Sean Sube
|
4810ca858a
|
fix(api): correct name of torch extraction var
|
2023-06-03 09:52:31 -05:00 |
Sean Sube
|
4dc192a2c7
|
apply lint
|
2023-05-28 19:44:16 -05:00 |
Sean Sube
|
00b1bec7a9
|
fix(api): skip loading custom VAE after torch extraction (#379)
|
2023-05-27 12:31:08 -05:00 |
Sean Sube
|
3adafeaa3d
|
fix(api): switch back to torch extraction for now (#379)
|
2023-05-27 12:29:17 -05:00 |
Sean Sube
|
86d458a0c6
|
fix(api): avoid passing cache path before sanitizing config name
|
2023-05-27 12:27:33 -05:00 |
Sean Sube
|
24f1ecc0eb
|
fix(api): load local custom VAE from within model path
|
2023-05-27 11:26:16 -05:00 |
Sean Sube
|
1562f4011e
|
replace pydantic polyfill
|
2023-05-20 20:19:41 -05:00 |
Sean Sube
|
eb53238fd5
|
do not override source after fetch
|
2023-05-20 20:15:19 -05:00 |
Sean Sube
|
df2e854dcc
|
fix load_yaml import
|
2023-05-20 20:09:45 -05:00 |
Sean Sube
|
9fa1f0387b
|
add env var for torch extraction
|
2023-05-20 20:06:54 -05:00 |
Sean Sube
|
9c28154dee
|
feat(api): add option to reload CNet for conversion
|
2023-05-20 15:19:38 -05:00 |
Sean Sube
|
20107f559a
|
use Torch working model for conversion
|
2023-05-20 15:12:39 -05:00 |
Sean Sube
|
339441cb16
|
fix(api): restore old checkpoint conversion code path
|
2023-05-20 13:41:23 -05:00 |
Sean Sube
|
fe80e61e79
|
fix CNet conversion condition
|
2023-05-14 20:53:12 -05:00 |
Sean Sube
|
b6a4cbaae1
|
fix(api): collate CNet after unloading UNet
|
2023-05-14 20:43:16 -05:00 |
Sean Sube
|
01ab864a55
|
collate UNet after unloading original, add option to skip pipeline loading test
|
2023-05-14 20:29:18 -05:00 |
Sean Sube
|
56fa0729b5
|
fix conversion context
|
2023-05-14 20:05:49 -05:00 |
Sean Sube
|
0d51d61728
|
feat(api): add env vars for controlnet conversion and opset
|
2023-05-14 20:04:43 -05:00 |
Sean Sube
|
a99388645a
|
correct import
|
2023-05-14 19:56:40 -05:00 |
Sean Sube
|
e2035c3fbf
|
fix(api): run GC during diffusers conversion, add flag to skip ControlNet (#369)
|
2023-05-14 19:30:30 -05:00 |
Sean Sube
|
f1856cb0d2
|
reload models and extras after conversion
|
2023-05-08 21:59:27 -05:00 |
Sean Sube
|
6f38d35c73
|
default content type, use arg parser for override
|
2023-05-08 21:56:05 -05:00 |
Sean Sube
|
c992c03584
|
write extras as string, override conversion args from endpoint
|
2023-05-08 21:49:36 -05:00 |
Sean Sube
|
da6aa15afc
|
fix(api): fully qualify HF models (#371)
|
2023-05-05 18:33:54 -05:00 |
Sean Sube
|
d66bf9e54f
|
fix(api): download pretrained models from HF correctly (#371)
|
2023-05-03 22:21:04 -05:00 |
Sean Sube
|
b6692f068e
|
fix(api): parse config files as JSON or YAML depending on extension (#370)
|
2023-05-03 22:15:17 -05:00 |
Sean Sube
|
5dfb09bd3c
|
fix(api): use existing progress counter for highres and loopback
|
2023-04-30 17:27:51 -05:00 |
Sean Sube
|
572a5159ad
|
fix(api): limit fp16 ops for v2.1 models (#364)
|
2023-04-30 08:49:34 -05:00 |
Sean Sube
|
bf2f77d7a2
|
apply lint
|
2023-04-29 23:12:15 -05:00 |
Sean Sube
|
077845e868
|
fix log levels
|
2023-04-29 23:11:46 -05:00 |
Sean Sube
|
62abc76f3f
|
convert checkpoint dtype after loading
|
2023-04-29 23:08:48 -05:00 |
Sean Sube
|
e28bbe2c18
|
set safetensor and dtype when loading
|
2023-04-29 23:05:51 -05:00 |
Sean Sube
|
1c308e0bab
|
collect and summarize errors while converting models
|
2023-04-29 22:58:58 -05:00 |
Sean Sube
|
bc71583393
|
fix(api): add model image size and version hint to extras file
|
2023-04-29 22:56:52 -05:00 |
Sean Sube
|
2690eafe09
|
fix(api): pass correct text model type when converting v2 checkpoints (#360)
|
2023-04-29 22:45:48 -05:00 |
Sean Sube
|
4eba9a6400
|
avoid joining none path
|
2023-04-29 21:16:23 -05:00 |
Sean Sube
|
5760be710a
|
fix(api): restore use of config key when converting from checkpoints
|
2023-04-29 20:26:01 -05:00 |
Sean Sube
|
f782f39cce
|
fix(api): remove size limit on inpainting stage
|
2023-04-29 14:23:00 -05:00 |
Sean Sube
|
acde899559
|
reuse config from loaded UNet
|
2023-04-29 13:27:39 -05:00 |
Sean Sube
|
0175d7edcf
|
fix(api): specify input channels when converting inpainting models (#356)
|
2023-04-29 12:18:15 -05:00 |
Sean Sube
|
4c126153f5
|
fix(api): switch to diffusers ckpt loading, add more pipelines to conversion (#337, #356)
|
2023-04-29 12:00:43 -05:00 |
Sean Sube
|
dbd9a186ae
|
feat(api): allow converting inpaint models (#356)
|
2023-04-27 23:41:04 -05:00 |
Sean Sube
|
dc6bf330c1
|
feat(api): add optimization for max attention slicing (#355)
|
2023-04-24 19:13:32 -05:00 |
Sean Sube
|
9e9fe90f80
|
chore(api): remove SD v2.1 from base models
|
2023-04-23 18:23:05 -05:00 |
Sean Sube
|
5f5b01fed0
|
apply lint
|
2023-04-22 12:28:46 -05:00 |
Sean Sube
|
5f5418132b
|
fix(api): build sum tokens for TIs using emb_params key
|
2023-04-22 12:07:52 -05:00 |
Sean Sube
|
a46f00aeb4
|
fix(api): use slice multiplication for 3x3 kernels without CP decomp
|
2023-04-20 22:10:49 -05:00 |
Sean Sube
|
49781df2fd
|
apply lint
|
2023-04-20 21:26:16 -05:00 |
Sean Sube
|
ff4c8a9404
|
handle tensors of the same rank
|
2023-04-20 20:24:37 -05:00 |
Sean Sube
|
3e8f4b3edf
|
fix(api): improve summing of mismatched weights
|
2023-04-20 20:06:43 -05:00 |
Sean Sube
|
f0109d3406
|
fix(api): blend LoHA and LoRA weights for 1x1 kernels
|
2023-04-20 19:31:40 -05:00 |
Sean Sube
|
e9e9d75f9d
|
fix(api): correct return value after fully converting checkpoints
|
2023-04-20 18:00:35 -05:00 |
Sean Sube
|
df0e7dc57e
|
feat: add admin endpoint to restart image workers (#207)
|
2023-04-20 07:36:31 -05:00 |
Sean Sube
|
161913bb7e
|
fix(api): add pre-converted ControlNets to base sources, add missing ControlNet strings
|
2023-04-15 16:55:53 -05:00 |
Sean Sube
|
e0e6b74b98
|
fix(api): correct parameter names for BSRGAN, use RRDB from BasicSR for Real ESRGAN
|
2023-04-15 16:20:46 -05:00 |
Sean Sube
|
317029356e
|
apply lint
|
2023-04-15 14:42:14 -05:00 |
Sean Sube
|
95841ffe2b
|
fix(api): check diffusers version before imports (#336)
|
2023-04-15 14:32:22 -05:00 |
Sean Sube
|
6effbea1eb
|
fix missing import
|
2023-04-15 10:57:37 -05:00 |
Sean Sube
|
7545d7c73d
|
add ControlNet UNet to existing checkpoints
|
2023-04-15 10:54:52 -05:00 |
Sean Sube
|
7f16b2f0ae
|
clean up CNet-only conversion code
|
2023-04-15 09:08:14 -05:00 |
Sean Sube
|
0dd8272285
|
feat(api): convert CNet for existing diffusion models
|
2023-04-15 09:00:17 -05:00 |
Sean Sube
|
9e017ee35d
|
feat: add parameter for ControlNet selection
|
2023-04-12 08:43:15 -05:00 |
Sean Sube
|
fbf576746c
|
attention fix for cnet export
|
2023-04-11 23:11:08 -05:00 |
Sean Sube
|
f49a4ddfdf
|
test controlnet pipe
|
2023-04-11 23:06:32 -05:00 |
Sean Sube
|
a3daaf0112
|
initial integration of controlnet pipeline
|
2023-04-11 19:29:25 -05:00 |
Sean Sube
|
de61e388a0
|
chore(api): remove some unused non-ONNX code paths
|
2023-04-11 08:26:21 -05:00 |
Sean Sube
|
0a6c99d57e
|
lint repeated factors
|
2023-04-10 21:04:48 -05:00 |
Sean Sube
|
7f6da8eeca
|
feat(api): add params for SwinIR large models
|
2023-04-10 19:13:49 -05:00 |
Sean Sube
|
6570d19fa3
|
feat(api): add SwinIR real x4 to base models
|
2023-04-10 19:04:52 -05:00 |
Sean Sube
|
2a7621c195
|
feat(api): add params for more SwinIR models
|
2023-04-10 19:02:12 -05:00 |
Sean Sube
|
62aa7e8473
|
feat(api): add initial support for BSRGAN and SwinIR upscaling (#153, #154)
|
2023-04-10 17:49:56 -05:00 |
Sean Sube
|
512f41135d
|
add logging when conv shapes do not match
|
2023-04-10 08:14:47 -05:00 |
Sean Sube
|
4db1737f98
|
apply lint
|
2023-04-10 08:09:29 -05:00 |
Sean Sube
|
7d2d865c19
|
convert LoHA T weights to same dtype, log shapes rather than data
|
2023-04-10 08:06:28 -05:00 |
Sean Sube
|
1ed51352c4
|
handle LoHA nodes with CP decomp
|
2023-04-10 08:06:22 -05:00 |
Sean Sube
|
88c7fd9f60
|
start handling Gemm nodes
|
2023-04-10 07:58:21 -05:00 |
Sean Sube
|
df02e20b34
|
only use mids once
|
2023-04-10 07:58:18 -05:00 |
Sean Sube
|
4947734add
|
flip axis
|
2023-04-10 07:58:15 -05:00 |
Sean Sube
|
87bba0e169
|
reverse factors
|
2023-04-10 07:58:12 -05:00 |
Sean Sube
|
d671cb8113
|
attempt layer by layer recomp
|
2023-04-10 07:58:08 -05:00 |
ForserX
|
7c4e729f85
|
Fix for LoHA weight and LoRA alpha read
|
2023-04-10 10:58:47 +03:00 |
Sean Sube
|
b6bb246032
|
apply lint
|
2023-04-09 20:34:10 -05:00 |
Sean Sube
|
9698e29268
|
lint(api): name context params consistently (#278)
|
2023-04-09 20:33:03 -05:00 |
Sean Sube
|
ff9ce03af5
|
fix(api): better handling for errors while converting checkpoint to torch (#165)
|
2023-04-09 18:05:44 -05:00 |
Sean Sube
|
34f1973707
|
feat(api): add support for PyTorch 2.0 (#292)
|
2023-04-09 16:07:40 -05:00 |
ForserX
|
d244ca9a9c
|
LoHA: Fixed blending error
|
2023-04-08 13:46:05 +03:00 |
Sean Sube
|
bd03edc2ad
|
fix(api): handle 3x3 kernels in LoHA networks
|
2023-04-07 20:54:42 -05:00 |
Sean Sube
|
7f7476bcbb
|
fix(api): use correct weight pairs in LoHA
|
2023-04-07 19:51:30 -05:00 |
Sean Sube
|
35432f1ab2
|
feat(api): experimental support for LoHA networks
|
2023-04-07 18:50:12 -05:00 |
Sean Sube
|
7e3ca8ab01
|
feat(api): support 3x3 kernels in LoRA and LoCONs
|
2023-04-06 23:34:55 -05:00 |
Sean Sube
|
25176fea4d
|
fix(api): correctly blend LoRAs into UNet during conversion
|
2023-04-06 23:34:06 -05:00 |
Sean Sube
|
c8382dc689
|
feat(api): implement spiral tile order for non-square images
|
2023-04-04 20:02:13 -05:00 |
Sean Sube
|
6bad599b3c
|
lint(api): move some chatty logs to trace level
|
2023-04-01 15:39:22 -05:00 |
Sean Sube
|
2bbc5d877f
|
lint(api): explicitly bind the device pool to shutdown callback
|
2023-03-27 17:13:45 -05:00 |
Sean Sube
|
c2f8fb1d31
|
fix(api): combine names for ONNX fp16 optimization
|
2023-03-27 08:55:01 -05:00 |
Sean Sube
|
73e9cf8b66
|
fix(api): disable internal fp16 for VAE encoder (#290)
|
2023-03-27 08:10:40 -05:00 |
Sean Sube
|
afa8f5e706
|
feat(api): add optimization for internal fp16 conversion
|
2023-03-26 22:41:12 -05:00 |
Sean Sube
|
e552a5560f
|
feat(api): check device worker pool and recycle on a regular interval (#284)
|
2023-03-26 11:09:22 -05:00 |
Sean Sube
|
2c47904057
|
lint(api): use constant for model filename
|
2023-03-24 08:14:19 -05:00 |
Sean Sube
|
fa71d87e2c
|
apply lint
|
2023-03-21 22:19:50 -05:00 |
Sean Sube
|
c8aad8554e
|
fix(api): convert back to model format after blending, convert samples as needed (#274)
|
2023-03-21 22:05:14 -05:00 |
Sean Sube
|
0315a8cbc6
|
fix(api): apply fp16 optimizations to LoRA and Textual Inversion blending
|
2023-03-21 21:45:27 -05:00 |
Sean Sube
|
4f6574c88e
|
sonar lint fixes
|
2023-03-21 17:11:38 -05:00 |
Sean Sube
|
f779fbd5cc
|
fix(api): remove prefix before downloading for HF hub
|
2023-03-19 23:30:31 -05:00 |
Sean Sube
|
ae3bcf3b8b
|
fix(api): add HF hub download to fetch logic for Inversion concepts
|
2023-03-19 20:32:21 -05:00 |
Sean Sube
|
0732058aa8
|
feat(api): detect Textual Inversion type from keys (#262)
|
2023-03-19 20:16:52 -05:00 |
Sean Sube
|
fe498b16f0
|
fix(api): embed Inversion concepts using their name
|
2023-03-19 19:01:22 -05:00 |
Sean Sube
|
19d4d554c3
|
fix(api): add base token for Textual Inversion as sum layer
|
2023-03-19 18:04:21 -05:00 |
Sean Sube
|
8acc15f52e
|
fix(api): better error handling around tensor loading
|
2023-03-19 15:38:43 -05:00 |
Sean Sube
|
07622690dc
|
fix(api): use Torch JIT and fallback loading
|
2023-03-19 15:31:35 -05:00 |
Sean Sube
|
b797b3d616
|
fix(api): do not assume file extension for additional networks
|
2023-03-19 15:27:51 -05:00 |
Sean Sube
|
33008531e9
|
fix(api): load blending tensors onto CPU
|
2023-03-19 15:13:54 -05:00 |
Sean Sube
|
b8f816323e
|
fix(api): correctly load server env for conversion
|
2023-03-19 10:39:09 -05:00 |
Sean Sube
|
98e488319c
|
use fp16 optimization flag during conversion, add to admin docs
|
2023-03-19 10:33:46 -05:00 |
Sean Sube
|
243a2d9df6
|
apply lint
|
2023-03-19 09:29:06 -05:00 |
Sean Sube
|
0e43acc0f7
|
fix(api): fetch sources and additional networks by default
|
2023-03-19 09:09:03 -05:00 |
Sean Sube
|
2ef00599b6
|
experimental CLIP skip
|
2023-03-19 08:17:40 -05:00 |
Sean Sube
|
84718e5928
|
feat(scripts): add env debug script (#191)
|
2023-03-18 13:16:59 -05:00 |
Sean Sube
|
5b308d5fc1
|
lint(api): improve logging for inversion tokens
|
2023-03-18 12:04:39 -05:00 |
Sean Sube
|
2cb0a6be3c
|
more lint
|
2023-03-18 11:55:06 -05:00 |
Sean Sube
|
e104c81e19
|
apply lint
|
2023-03-18 11:50:09 -05:00 |
Sean Sube
|
a1f17c0877
|
fix dest paths for blended nets
|
2023-03-18 11:37:16 -05:00 |
Sean Sube
|
f465120cad
|
use conversion dest path when applying additional nets
|
2023-03-18 11:34:05 -05:00 |
Sean Sube
|
1f6105a8fe
|
make blend functions take tuples rather than split lists
|
2023-03-18 10:50:48 -05:00 |
Sean Sube
|
40c92f054b
|
add networks as conversion arg
|
2023-03-18 10:22:24 -05:00 |
Sean Sube
|
5dd14c19ce
|
feat(api): build a single token for multi-layer Textual Inversions (#212)
|
2023-03-18 07:47:36 -05:00 |
Sean Sube
|
af62c1c3b6
|
apply lint
|
2023-03-18 07:41:29 -05:00 |
Sean Sube
|
e3bf04ab8f
|
feat(api): add section to extras file for additional networks
|
2023-03-18 07:40:57 -05:00 |
Sean Sube
|
c3979246df
|
make blending happen once after conversion
|
2023-03-18 07:14:22 -05:00 |
Sean Sube
|
32b2a76a0b
|
fix(api): download additional networks to their own subdir in models
|
2023-03-18 07:07:05 -05:00 |