f06ba8e60b
Significantly reduce thread abuse for faster model moving
...
This will move all major gradio calls into the main thread rather than random gradio threads.
This ensures that all torch.module.to() are performed in main thread to completely possible avoid GPU fragments.
In my test now model moving is 0.7 ~ 1.2 seconds faster, which means all 6GB/8GB VRAM users will get 0.7 ~ 1.2 seconds faster per image on SDXL.
2024-02-08 10:13:59 -08:00
291ec743b6
use better context manager to fix potential problems
2024-02-08 02:00:54 -08:00
760f727eb9
use better context manager to fix potential problems
2024-02-08 01:51:18 -08:00
a1670c536d
Allow controlnet_model_function_wrapper
...
for animatediff to manage controlnet batch slicing window
2024-02-07 20:06:23 -08:00
e62631350a
Update forge_version.py
2024-02-06 17:55:14 -08:00
402b7beb87
fix repeated model loading bug on 4090
2024-02-06 08:02:03 -08:00
a578da074b
fix repeated model loading bug on 4090
2024-02-06 07:59:19 -08:00
d76b830add
reduce prints
2024-02-06 07:56:15 -08:00
7359740f36
Revert "safer device"
...
This reverts commit 1204d490d9
2024-02-06 05:27:07 -08:00
1204d490d9
safer device
2024-02-06 05:01:58 -08:00
9c31b0ddcb
try fix #56
2024-02-06 04:51:08 -08:00
6aee7a2032
Update forge_version.py
2024-02-05 23:55:27 -08:00
74ff4a9ba9
set CUDA_VISIBLE_DEVICES with args
2024-02-05 23:53:11 -08:00
b8cd6d2e21
Update forge_version.py
2024-02-05 20:12:37 -08:00
53057f33ed
Update forge_version.py
2024-02-05 15:30:45 -08:00
88f6df4dcd
add_sampler_pre_cfg_function
2024-02-05 14:48:43 -08:00
2c95b09a73
Euler A Turbo
2024-02-05 14:23:42 -08:00
0ba407fd9c
new samplers
...
DDPM
DDPM Karras
DPM++ 2M Turbo
DPM++ 2M SDE Turbo
LCM Karras
2024-02-05 03:58:06 -08:00
af017121d2
Update forge_version.py
2024-02-05 01:31:24 -08:00
858bfc7a32
Update unet_patcher.py
2024-02-04 19:40:21 -08:00
fdbe5b7aa7
memory_peak_estimation_modifier
2024-02-04 19:36:58 -08:00
a3245e3eb1
Update unet_patcher.py
2024-02-03 23:05:06 -08:00
8be7b347aa
Update unet_patcher.py
2024-02-03 23:03:21 -08:00
dc082be7f9
Update unet_patcher.py
2024-02-03 22:54:42 -08:00
c11490d560
add_alphas_cumprod_modifier
2024-02-03 22:33:18 -08:00
8c9dc0d0dc
retutn patcher to calc model size ( #34 )
2024-02-03 21:22:20 -06:00
8d9fdb20c3
safe copy
2024-02-03 18:17:28 -08:00
a544ececfe
better diffusers handling
2024-02-03 17:16:21 -08:00
e3fca95012
add_extra_torch_module_during_sampling for animatediff
2024-02-03 01:39:12 -08:00
95c9ed52fc
add block inner modifiers
2024-02-03 00:57:49 -08:00
7c88dbb777
better naming
2024-02-02 14:10:35 -08:00
da6041dd93
elegant patcher
2024-02-02 00:34:18 -08:00
b944aa9242
better diffuser patcher
2024-02-02 00:32:15 -08:00
7d7094b6ec
marigold_ini
2024-02-02 00:14:37 -08:00
24db0e241a
elegant codes
2024-02-01 23:04:24 -08:00
4b27699e65
masked cnet
2024-02-01 21:48:58 -08:00
4f6b8ad079
i
2024-02-01 21:26:42 -08:00
9f6ee2a688
ini mask support
2024-02-01 21:21:41 -08:00
d4d794d09e
add mask api
2024-02-01 17:32:13 -08:00
988960ae37
Update unet_patcher.py
2024-02-01 11:55:08 -08:00
a203113f43
qol
2024-01-31 23:21:58 -08:00
0f7c71b400
support controlnet mask in backend
2024-01-31 23:11:12 -08:00
61891e096c
Update unet_patcher.py
2024-01-31 22:10:50 -08:00
69206ce05f
better gpu
2024-01-31 22:10:15 -08:00
a38313368f
allow preserve memory
2024-01-31 21:57:40 -08:00
edc0b2cb85
Update unet_patcher.py
2024-01-31 19:22:12 -08:00
61b014f579
add to patcher
2024-01-31 19:12:13 -08:00
297e10e4e7
Update initialization.py
2024-01-31 17:02:58 -08:00
b0ac53f260
Update forge_util.py
2024-01-31 15:51:43 -08:00
58b1f65052
Update initialization.py
2024-01-31 15:49:09 -08:00
lllyasviel