Commit Graph

245 Commits

Author SHA1 Message Date
pythongosssss
44b7acc884 Only poll if it has never opened 2023-03-03 21:13:11 +00:00
pythongosssss
4e8c425e3f Restored accidently removed code 2023-03-03 20:17:03 +00:00
pythongosssss
a31483f566 Restored missing input edit fix 2023-03-03 20:10:18 +00:00
pythongosssss
c2ee650ce4 Merge remote-tracking branch 'origin' into frontendrefactor 2023-03-03 19:30:24 +00:00
comfyanonymous
1500dd58c4 stop_at_clip_layer can be set in CLIPSetLastLayer so it can be removed
from the CLIPLoader node.
2023-03-03 14:27:55 -05:00
pythongosssss
f61df5faf2 Added dynamic loading of extensions 2023-03-03 19:05:39 +00:00
pythongosssss
087d931d9e Redraw node on opt change 2023-03-03 18:48:22 +00:00
pythongosssss
f6bab67bd2 Changed to store resolved prompt in workflow info 2023-03-03 18:40:50 +00:00
pythongosssss
dfe25a9eaa Adding built in extensions + example 2023-03-03 18:28:34 +00:00
comfyanonymous
8141cd7f42 Fix issue. 2023-03-03 13:18:01 -05:00
comfyanonymous
f21b0255a0 Move the CheckpointLoaderSimple to the right section. 2023-03-03 13:09:44 -05:00
comfyanonymous
c195dab61c Add a node to set CLIP skip.
Use a more simple way to detect if the model is -v prediction.
2023-03-03 13:04:36 -05:00
comfyanonymous
5608730809 To be really simple CheckpointLoaderSimple should pick the right type. 2023-03-03 11:07:10 -05:00
pythongosssss
f1a17ccae5 Documenting methods 2023-03-03 15:47:33 +00:00
pythongosssss
31e72ecdae Readded loading file 2023-03-03 15:27:08 +00:00
pythongosssss
4a48e65f1e More work on UI 2023-03-03 15:20:49 +00:00
pythongosssss
77da821554 add loras to ignore 2023-03-03 15:19:56 +00:00
pythongosssss
490c67d8ca Merge remote-tracking branch 'origin' into frontendrefactor 2023-03-03 15:06:49 +00:00
comfyanonymous
8a2699b47d New CheckpointLoaderSimple to load checkpoints without a config. 2023-03-03 03:37:35 -05:00
comfyanonymous
b2a7f1b32a Make some cross attention functions work on the CPU. 2023-03-03 03:27:33 -05:00
comfyanonymous
666a9e8604 Add some pytorch scaled_dot_product_attention code for testing.
--use-pytorch-cross-attention to use it.
2023-03-02 17:01:20 -05:00
pythongosssss
739fb214e0 Added handling of sockets
Started rework of UI elements
Added pnginfo handling
2023-03-02 21:34:29 +00:00
pythongosssss
58fa3ecd55 Refactored sockets 2023-03-02 21:33:50 +00:00
comfyanonymous
40fe09c7b8 Add a button to interrupt processing to the ui. 2023-03-02 15:24:51 -05:00
pythongosssss
f51b02e59f Initial refactoring changes
- Moved to web folder
 - Splitting into individual files
2023-03-02 20:00:06 +00:00
pythongosssss
10bdb6bcda Add mime type for js files 2023-03-02 19:58:59 +00:00
comfyanonymous
b59b82a73b Add a way to interrupt current processing in the backend. 2023-03-02 14:42:03 -05:00
comfyanonymous
9bb6edccd7 Add a print to colab. 2023-03-01 10:53:18 -05:00
comfyanonymous
e758e974e7 Add some more stuff to colab notebook. 2023-03-01 10:40:26 -05:00
comfyanonymous
3cdf64d74e Quick fix modal overflowing at the bottom if error too large. 2023-02-28 19:07:23 -05:00
comfyanonymous
151fed3dfb Hopefully fix a strange issue with xformers + lowvram. 2023-02-28 13:48:52 -05:00
comfyanonymous
392364779f Only clear cuda cache on CUDA since it causes slowdowns on ROCm. 2023-02-28 13:39:30 -05:00
comfyanonymous
a59bb36cb8 Try to improve memory issues with del. 2023-02-28 12:27:43 -05:00
comfyanonymous
fc9323caf2 Try to clear more memory at the end of each prompt execution. 2023-02-28 11:56:33 -05:00
comfyanonymous
e1a6dc0325 I confirmed the notebook works on paperspace. 2023-02-28 02:49:53 -05:00
comfyanonymous
e56477e575 Install xformers at the same time as requirements in notebook to fix issues. 2023-02-27 20:22:46 -05:00
comfyanonymous
54a4caa7f3 --highvram should be autodetected in colab/etc.. now. 2023-02-27 20:06:44 -05:00
comfyanonymous
1304a8f8ad Small adjustment. 2023-02-27 20:04:18 -05:00
comfyanonymous
bddbd4bdb0 Enable highvram automatically when vram >> ram 2023-02-27 19:57:39 -05:00
comfyanonymous
f05d2bab79 Move some stuff from main.py to execution.py 2023-02-27 19:44:58 -05:00
comfyanonymous
a5c57cdfd7 Switch the CLIPTextEncode div to a textarea. 2023-02-27 16:13:09 -05:00
comfyanonymous
573b8c18fe Outpainting actually works now. 2023-02-27 12:02:23 -05:00
comfyanonymous
14c390c0c2 Remove sample_ from some sampler names.
Old workflows will still work.
2023-02-27 01:43:06 -05:00
comfyanonymous
7205653251 Merge branch 'batchimagepreview' of https://github.com/pythongosssss/ComfyUI into pythongosssss-batchimagepreview 2023-02-26 17:29:51 -05:00
comfyanonymous
7add9fe7b3 Preparing to add another function to load checkpoints. 2023-02-26 17:29:01 -05:00
pythongosssss
c6643e0814 removed log 2023-02-26 19:05:28 +00:00
pythongosssss
a6a930644d Add thumbnails for multi batch image previews 2023-02-26 18:56:04 +00:00
comfyanonymous
84a4b1f283 Fix uni_pc sampler not working with 1 or 2 steps. 2023-02-26 04:01:01 -05:00
comfyanonymous
d79dc06cc5 Small Readme change. 2023-02-26 03:37:57 -05:00
comfyanonymous
011c60239f Add some commented out wget commands to the colab notebook. 2023-02-26 01:54:17 -05:00