8ffaea76ba
Add Diffusers model and VAE variant loading option
2023-07-31 14:39:41 +03:00
884e464693
Move base to cpu when using refiner with offload
2023-07-30 18:39:27 +03:00
2300329893
fix lint
2023-07-30 17:17:56 +02:00
6e428ff0a2
update diffusers
2023-07-30 17:14:34 +02:00
13ba9531a5
Merge pull request #1875 from AI-Casanova/diffusers-LoRA
...
Enable SDXL LoRA (Must install the newest Diffusers!)
2023-07-30 11:13:36 -04:00
350be09282
w/a for model cpu offload refiner
2023-07-30 17:18:57 +03:00
0180402563
Better move and accelerate handling
2023-07-30 11:36:47 +03:00
66a6e783f0
has_accelerate = False for original backend
2023-07-30 01:22:29 +03:00
4d00224082
Fix pipeline switching
2023-07-30 00:51:35 +03:00
7e1030d499
Introduce sd_model.has_accelerate
2023-07-30 00:51:35 +03:00
f945cf14b0
Fix model offload by not focring the model to GPU
2023-07-30 00:51:35 +03:00
085d1da825
Fix force upcast VAE with Diffusers
2023-07-29 21:01:24 +03:00
3258b27523
Update sequential CPU offload check
2023-07-29 19:13:29 +03:00
38ecfb6dff
Add Move UNet to CPU option
2023-07-29 18:58:08 +03:00
3010d1823d
Fix modules
2023-07-29 15:44:55 +03:00
42c6147ac8
cleanup
2023-07-29 13:48:28 +09:00
7017a4a2a9
Fix UniPC sampler issue on DirectML.
2023-07-29 13:38:41 +09:00
813eb48bf7
Restore Python 3.9 compatibility. (DirectML)
2023-07-29 12:10:41 +09:00
47f2f50574
Restore Python 3.9 compatibility. (DirectML)
2023-07-29 12:08:22 +09:00
025df86ac0
Cleanup
2023-07-29 02:06:34 +03:00
fd7f51302e
Update processing_diffusers.py
2023-07-28 18:01:38 -05:00
942371b25a
Update lora_diffusers.py
2023-07-28 18:00:44 -05:00
1da64b9d08
Fix setting VAE Force Upcast in diffusers
2023-07-28 23:07:11 +01:00
31e1bb01ff
Fix VAE reloading
2023-07-28 23:23:36 +03:00
dbd7887632
Fix refiner unloading
2023-07-28 23:12:45 +03:00
c8af2affaf
Fix original backend reloading
2023-07-28 21:26:54 +03:00
cfcf481992
cleanup
2023-07-28 21:10:38 +03:00
9f18db474d
Merge pull request #1861 from Nuullll/master
...
[IPEX] Fix ControlNet depth leres/leres++
2023-07-28 20:15:31 +03:00
e6cf3d72cd
Fix sequential cpu offload
2023-07-28 20:01:32 +03:00
77de9cd093
Fix medvram with DirectML.
2023-07-28 23:18:28 +09:00
0f44332e5c
Make sequential CPU offload available for non-CUDA
...
Add settings override for DirectML.
Move `devices.set_cuda_params()` to correct line.
2023-07-28 23:11:57 +09:00
3aed536206
[IPEX] Fix ControlNet depth leres/leres++
2023-07-28 21:25:17 +08:00
a32bf083f1
cleanup
2023-07-28 12:15:25 +03:00
459a8bc048
ipex fix adetailer
2023-07-28 12:08:02 +03:00
f38d5a91bf
Move ipex fixes into it's own folder
2023-07-28 10:58:45 +03:00
38dcca7399
ipex cleanup
2023-07-28 01:35:02 +03:00
6acb3ef131
[IPEX] Fix batch_norm for Tiled VAE
...
Tiled VAE invokes `torch.nn.functional.batch_norm` without providing the
`weight` and `bias` parameter, so torch backend creates default empty
tensors for them but bails out with "tensor does not have a device" error.
This patch overrides the `weight` and `bias` parameters to all-ones and
all-zeros if they are `None`.
2023-07-27 22:56:19 +08:00
86a0cb5f7e
add secondary pass info to metadata
2023-07-27 10:06:21 -04:00
8f6f8413b1
fix ti training
2023-07-27 09:30:41 -04:00
83208591e5
improve inpaint layout
2023-07-26 22:22:35 -04:00
90f6cc8ebb
add refiner enabled check
2023-07-26 20:54:51 -04:00
3437132817
update refiner start/end
2023-07-26 20:49:24 -04:00
0bc389594c
Merge pull request #1840 from Kubuxu/fix/refiner-start-end
...
Fix base and refiner when using diffusers
2023-07-26 20:07:23 -04:00
fc1a7ad0b1
Fix base and refiner when using diffusers
...
With diffusers 0.19 densoise_start and _end started applying.
2023-07-27 00:51:56 +01:00
d778876010
minor css fixes
2023-07-26 19:48:36 -04:00
58bfb9246f
update lora enum
2023-07-26 19:27:38 -04:00
dc1c682a46
Fixes params pasting for denoise start and end
2023-07-27 00:29:10 +02:00
4a64eef568
Merge pull request #1831 from vladmandic/improve_diffusers_kandinsky_2
...
[Diffusers] Make all Kandinsky work
2023-07-26 16:04:08 -04:00
ff9b8bc062
api endpoint refresh vaes
2023-07-26 15:51:19 -04:00
15d5873f22
improve params pasting
2023-07-26 15:32:26 -04:00
Disty0
Vladimir Mandic
Kubuxu
Seunghoon Lee
AI-Casanova
Disty0
Nuullll
Dookie