layerdiffusion
4e3c78178a
[revised] change some dtype behaviors based on community feedbacks
...
only influence old devices like 1080/70/60/50.
please remove cmd flags if you are on 1080/70/60/50 and previously used many cmd flags to tune performance
2024-08-21 10:23:38 -07:00
layerdiffusion
1419ef29aa
Revert "change some dtype behaviors based on community feedbacks"
...
This reverts commit 31bed671ac
2024-08-21 10:10:49 -07:00
layerdiffusion
31bed671ac
change some dtype behaviors based on community feedbacks
...
only influence old devices like 1080/70/60/50.
please remove cmd flags if you are on 1080/70/60/50 and previously used many cmd flags to tune performance
2024-08-21 08:46:52 -07:00
layerdiffusion
2f1d04759f
avoid some mysteries problems when using lots of python local delegations
2024-08-19 09:47:04 -07:00
layerdiffusion
d38e560e42
Implement some rethinking about LoRA system
...
1. Add an option to allow users to use UNet in fp8/gguf but lora in fp16.
2. All FP16 loras do not need patch. Others will only patch again when lora weight change.
3. FP8 unet + fp16 lora are available (somewhat only available) in Forge now. This also solves some “LoRA too subtle” problems.
4. Significantly speed up all gguf models (in Async mode) by using independent thread (CUDA stream) to compute and dequant at the same time, even when low-bit weights are already on GPU.
5. View “online lora” as a module similar to ControlLoRA so that it is moved to GPU together with model when sampling, achieving significant speedup and perfect low VRAM management simultaneously.
2024-08-19 04:31:59 -07:00
layerdiffusion
53cd00d125
revise
2024-08-17 23:03:50 -07:00
layerdiffusion
db5a876d4c
completely solve all LoRA OOMs
2024-08-17 22:43:20 -07:00
layerdiffusion
ab4b0d5b58
fix some mem leak
2024-08-17 00:19:43 -07:00
layerdiffusion
3da7de418a
fix layerdiffuse
2024-08-16 21:37:25 -07:00
layerdiffusion
9973d5dc09
better prints
2024-08-16 21:13:09 -07:00
layerdiffusion
f3e211d431
fix bnb lora
2024-08-16 21:09:14 -07:00
layerdiffusion
12369669cf
only load lora one time
2024-08-16 02:02:22 -07:00
layerdiffusion
f510f51303
speedup lora patching
2024-08-15 06:51:52 -07:00
layerdiffusion
141cf81c23
sometimes it is not diffusion model
2024-08-15 06:36:59 -07:00
layerdiffusion
021428da26
fix nf4 lora gives pure noise on some devices
2024-08-15 06:35:15 -07:00
layerdiffusion
3d751eb69f
move file
2024-08-15 05:46:35 -07:00
layerdiffusion
1bd6cf0e0c
Support LoRAs for Q8/Q5/Q4 GGUF Models
...
what a crazy night of math
2024-08-15 05:34:46 -07:00
layerdiffusion
d336597fa5
add note to lora
...
but loras for NF4 is done already!
2024-08-15 00:42:48 -07:00
layerdiffusion
d8b83a9501
gguf preview
2024-08-15 00:03:32 -07:00
layerdiffusion
59790f2cb4
simplify codes
2024-08-14 20:48:39 -07:00
layerdiffusion
4b66cf1126
fix possible OOM again
2024-08-14 20:45:58 -07:00
layerdiffusion
a29875206f
Revert "simplify codes"
...
This reverts commit e7567efd4b
2024-08-14 20:39:05 -07:00
layerdiffusion
e7567efd4b
simplify codes
2024-08-14 20:34:02 -07:00
layerdiffusion
bbd0d76b28
fix possible oom
2024-08-14 20:27:05 -07:00
layerdiffusion
cb889470ba
experimental LoRA support for NF4 Model
...
method may change later depending on result quality
2024-08-14 19:52:19 -07:00
layerdiffusion
70a5acd8ad
doc
2024-08-14 19:12:02 -07:00
layerdiffusion
aff742b597
speed up lora using cuda profile
2024-08-14 19:09:35 -07:00
layerdiffusion
c73dd119be
typo
2024-08-13 16:03:17 -07:00
layerdiffusion
88d0300883
add note
2024-08-13 16:02:40 -07:00
layerdiffusion
a0849953bd
revise
2024-08-13 15:13:39 -07:00
layerdiffusion
00f1cd36bd
multiple lora implementation sources
2024-08-13 07:13:32 -07:00
lllyasviel
61f83dd610
support all flux models
2024-08-13 05:42:17 -07:00
lllyasviel
cfa5242a75
forge 2.0.0
...
see also discussions
2024-08-10 19:24:19 -07:00
layerdiffusion
a91a81d8e6
revise structure
2024-08-07 20:44:34 -07:00
layerdiffusion
e1df7a1bae
revise kernel
2024-08-07 17:24:22 -07:00
layerdiffusion
b61bf553ea
revise inference dtype
2024-08-07 17:08:47 -07:00
lllyasviel
14a759b5ca
revise kernel
2024-08-07 13:28:12 -07:00
layerdiffusion
f743fbff83
revise kernel
2024-08-06 21:39:06 -07:00
layerdiffusion
b57573c8da
Implement many kernels from scratch
2024-08-06 20:19:03 -07:00
layerdiffusion
0863765173
rework sd1.5 and sdxl from scratch
2024-08-05 03:08:17 -07:00
layerdiffusion
be3f0a0039
remove legacy config
2024-08-03 17:04:56 -07:00
layerdiffusion
07b2d2ccac
clipvision, ipadapter, and misc
...
backend is 75% finished
2024-08-03 14:18:16 -07:00
layerdiffusion
e722991752
control rework
2024-08-02 22:17:27 -07:00
layerdiffusion
1f56acf3e7
use trange
2024-08-02 15:09:04 -07:00
layerdiffusion
6ed95d66e5
rework several component patcher
...
backend is 65% finished
2024-08-02 14:56:57 -07:00
layerdiffusion
d1b8a2676d
rework lora and patching system
...
and dora etc - backend rework is 60% finished
And I also removed the webui’s extremely annoying lora filter from model versions.
2024-08-02 13:45:26 -07:00
