apextoaster
/
onnx-web
1
0
Fork 0
Code Actions
2,236 Commits 135 Branches 17 Tags 132 MiB
Commit Graph

319 Commits

Author SHA1 Message Date
Sean Sube b365660adc
move more SDXL LoRA logs to trace level 2023-11-05 16:35:32 -06:00
Sean Sube 046803fc2b
lint(api): reduce log level during SDXL LoRA blending 2023-11-05 15:55:49 -06:00
Sean Sube e9b1375440
fix(api): write tests for embedding/inversion blending 2023-10-06 19:04:48 -05:00
Sean Sube ebdfa78737
fix(api): allow PTH tensor files, add helper to check extension 2023-10-06 19:03:15 -05:00
Sean Sube 1351b2f3ff
fix(api): allow SDXL VAE in any supported tensor format, ensure new SDXL models get hash file 2023-10-06 19:01:00 -05:00
Sean Sube 047e58c916
fix(api): continue adding tests, fix bugs encountered 2023-09-28 18:45:04 -05:00
Sean Sube 0ecae65f88
fix(api): set VAE attn processor during conversion 2023-09-24 15:02:21 -05:00
Sean Sube 5d3a7d77a5
fix(api): use Torch pipelines while loading models for conversion 2023-09-24 10:04:21 -05:00
Sean Sube c99481f484
fix(api): load replacement VAE from single file for SD v1/v2 2023-09-24 09:49:50 -05:00
Sean Sube 52fdf4f48a
fix(api): test LoRA blending code 2023-09-21 18:24:08 -05:00
Sean Sube a71298ff33
remove unused schema, lint 2023-09-15 08:40:56 -05:00
Sean Sube b851c234fe
more tests 2023-09-14 19:35:48 -05:00
Sean Sube 8a5e211172
lint(api): deduplicate some imports 2023-09-13 17:27:05 -05:00
Sean Sube cf2cf51b17
fix(api): resolve XL VAE within model folder 2023-09-11 20:21:43 -05:00
Sean Sube cd06f9291b
add custom VAE and fp16 support to SDXL conversion 2023-09-11 18:18:38 -05:00
Sean Sube 51b10de265
pass initial device to chain 2023-09-10 22:46:06 -05:00
Sean Sube 956a260db6
fix import 2023-09-10 12:15:39 -05:00
Sean Sube f2d0c2f765
apply lint 2023-09-10 11:53:36 -05:00
Sean Sube fe68670844
feat(api): add conversion for SDXL models 2023-09-10 11:52:46 -05:00
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