Commit Graph

1361 Commits

Author SHA1 Message Date
comfyanonymous
30de083dd0 Disable cuda malloc on all the 9xx series. 2023-07-23 13:29:14 -04:00
Dr.Lt.Data
261b0e0674
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-23 12:08:05 +09:00
comfyanonymous
22f29d66ca Try to fix memory issue with lora. 2023-07-22 21:38:56 -04:00
comfyanonymous
67be7eb81d Nodes can now patch the unet function. 2023-07-22 17:01:12 -04:00
comfyanonymous
12a6e93171 Del the right object when applying lora. 2023-07-22 11:25:49 -04:00
comfyanonymous
85a8900a14 Disable cuda malloc on regular GTX 960. 2023-07-22 11:05:33 -04:00
Dr.Lt.Data
6b9a4e2973
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-22 13:00:48 +09:00
comfyanonymous
78e7958d17 Support controlnet in diffusers format. 2023-07-21 22:58:16 -04:00
comfyanonymous
09386a3697 Fix issue with lora in some cases when combined with model merging. 2023-07-21 21:27:27 -04:00
Dr.Lt.Data
c39f6fd96f
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-22 09:06:09 +09:00
comfyanonymous
58b2364f58 Properly support SDXL diffusers unet with UNETLoader node. 2023-07-21 14:38:56 -04:00
melMass
5190aa284d fix: ️ small type fix
getCustomWidgets expects a plain record and not an array of records
2023-07-21 13:19:05 +02:00
Dr.Lt.Data
791c68f787
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-21 14:58:08 +09:00
comfyanonymous
0115018695 Print errors and continue when lora weights are not compatible. 2023-07-20 19:56:22 -04:00
Dr.Lt.Data
a1c3fa8497
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-20 14:02:11 +09:00
comfyanonymous
4760c29380 Merge branch 'fix-AttributeError-module-'torch'-has-no-attribute-'mps'' of https://github.com/KarryCharon/ComfyUI 2023-07-20 00:34:54 -04:00
Dr.Lt.Data
2887ffa35a
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-20 12:49:54 +09:00
comfyanonymous
ccb6b70de1 Move image encoding outside of sampling loop for better preview perf. 2023-07-19 18:06:58 -04:00
comfyanonymous
39c58b227f Disable cuda malloc on GTX 750 Ti. 2023-07-19 15:14:10 -04:00
comfyanonymous
d5c0765f4e Update how to get the prompt in api format in the example. 2023-07-19 15:07:12 -04:00
comfyanonymous
799c08a4ce Auto disable cuda malloc on some GPUs on windows. 2023-07-19 14:43:55 -04:00
Dr.Lt.Data
5e06acaf0a
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-20 01:21:41 +09:00
comfyanonymous
0b284f650b Fix typo. 2023-07-19 10:20:32 -04:00
comfyanonymous
e032ca6138 Fix ddim issue with older torch versions. 2023-07-19 10:16:00 -04:00
Dr.Lt.Data
705e5dc5b2
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-19 18:59:55 +09:00
comfyanonymous
18885f803a Add MX450 and MX550 to list of cards with broken fp16. 2023-07-19 03:08:30 -04:00
Dr.Lt.Data
30bd45e90f
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-19 10:51:13 +09:00
comfyanonymous
9ba440995a It's actually possible to torch.compile the unet now. 2023-07-18 21:36:35 -04:00
comfyanonymous
51d5477579 Add key to indicate checkpoint is v_prediction when saving. 2023-07-18 00:25:53 -04:00
Dr.Lt.Data
eb8ca34c1d
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-18 11:33:08 +09:00
comfyanonymous
ff6b047a74 Fix device print on old torch version. 2023-07-17 15:18:58 -04:00
comfyanonymous
9871a15cf9 Enable --cuda-malloc by default on torch 2.0 and up.
Add --disable-cuda-malloc to disable it.
2023-07-17 15:12:10 -04:00
comfyanonymous
55d0fca9fa --windows-standalone-build now enables --cuda-malloc 2023-07-17 14:10:36 -04:00
comfyanonymous
1679abd86d Add a command line argument to enable backend:cudaMallocAsync 2023-07-17 11:00:14 -04:00
comfyanonymous
3a150bad15 Only calculate randn in some samplers when it's actually being used. 2023-07-17 10:11:08 -04:00
comfyanonymous
ee8f8ee07f Fix regression with ddim and uni_pc when batch size > 1. 2023-07-17 09:35:19 -04:00
Dr.Lt.Data
b1dc9633e8
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-17 16:13:40 +09:00
comfyanonymous
3ded1a3a04 Refactor of sampler code to deal more easily with different model types. 2023-07-17 01:22:12 -04:00
Dr.Lt.Data
f1b2fba736
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-16 22:58:34 +09:00
comfyanonymous
ac9c038ac2 Merge branch 'master' of https://github.com/ComfyUI-Community/ComfyUI 2023-07-16 03:04:45 -04:00
comfyanonymous
5f57362613 Lower lora ram usage when in normal vram mode. 2023-07-16 02:59:04 -04:00
ComfyUI-Community
a8f3bbc35d
Patch del self.loaded_lora to prevent error with persistent lora_name swapping 2023-07-15 17:11:12 -07:00
comfyanonymous
490771b7f4 Speed up lora loading a bit. 2023-07-15 13:25:22 -04:00
Dr.Lt.Data
9ea247313d
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-15 17:19:09 +09:00
comfyanonymous
50b1180dde Fix CLIPSetLastLayer not reverting when removed. 2023-07-15 01:41:21 -04:00
comfyanonymous
6fb084f39d Reduce floating point rounding errors in loras. 2023-07-15 00:53:00 -04:00
Dr.Lt.Data
7e171b3d98
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-15 03:40:56 +09:00
comfyanonymous
91ed2815d5 Add a node to merge CLIP models. 2023-07-14 02:41:18 -04:00
comfyanonymous
907c9fbf0d Refactor to make it easier to set the api path. 2023-07-14 00:50:49 -04:00
Dr.Lt.Data
26d1cf5daa
Merge branch 'comfyanonymous:master' into refactor/onprompt 2023-07-14 13:32:01 +09:00