qnloft
/
ComfyUI
mirror of https://github.com/comfyanonymous/ComfyUI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
1,568 Commits 6 Branches 26 Tags 115 MiB
Commit Graph

1568 Commits

Author SHA1 Message Date
comfyanonymous 3fcab0c642 Merge branch 'fix-mask-nodes' of https://github.com/jn-jairo/ComfyUI 2023-10-14 02:42:06 -04:00
comfyanonymous fd4c5f07e7 Add a --bf16-unet to test running the unet in bf16. 2023-10-13 14:51:10 -04:00
comfyanonymous 9a55dadb4c Refactor code so model can be a dtype other than fp32 or fp16. 2023-10-13 14:41:17 -04:00
Jairo Correa b5fa3d28d7 Fix MaskComposite 2023-10-13 13:40:53 -03:00
Jairo Correa 87097a11c3 Fix FeatherMask 2023-10-13 12:26:54 -03:00
comfyanonymous fee3b0c070 Move and comment out. 2023-10-12 20:54:43 -04:00
Nick Teeple 851a4bdb80
Update extra_model_paths.yaml.example with comfy specific example 2023-10-12 21:26:27 +08:00
comfyanonymous 536799d172 Merge branch 'fix-1723' of https://github.com/chrisgoringe/ComfyUI 2023-10-11 23:35:24 -04:00
Chris 41d2c5660d add query 2023-10-12 14:26:53 +11:00
comfyanonymous 88733c997f pytorch_attention_enabled can now return True when xformers is enabled. 2023-10-11 21:30:57 -04:00
comfyanonymous 20d3852aa1 Pull some small changes from the other repo. 2023-10-11 20:38:48 -04:00
comfyanonymous ac7d8cfa87 Allow attn_mask in attention_pytorch. 2023-10-11 20:38:48 -04:00
comfyanonymous 1a4bd9e9a6 Refactor the attention functions. 
There's no reason for the whole CrossAttention object to be repeated when
only the operation in the middle changes.
 2023-10-11 20:38:48 -04:00
comfyanonymous 8cc75c64ff Let unet wrapper functions have .to attributes. 2023-10-11 01:34:38 -04:00
comfyanonymous 5e885bd9c8 Cleanup. 2023-10-10 21:46:53 -04:00
comfyanonymous 851bb87ca9 Merge branch 'taesd_safetensors' of https://github.com/mochiya98/ComfyUI 2023-10-10 21:42:35 -04:00
comfyanonymous be903eb2e2 Add default CheckpointSave, CLIPSave and VAESave paths to model paths. 2023-10-10 01:25:47 -04:00
comfyanonymous 877553843f Add a CLIPSave node to save CLIP model weights. 2023-10-10 01:24:49 -04:00
Yukimasa Funaoka 9eb621c95a
Supports TAESD models in safetensors format 2023-10-10 13:21:44 +09:00
comfyanonymous d1a0abd40b Merge branch 'input-directory' of https://github.com/jn-jairo/ComfyUI 2023-10-09 01:53:29 -04:00
comfyanonymous 4308862ce0 Add a note to README about pytorch 3.12 not being supported. 2023-10-09 01:51:01 -04:00
comfyanonymous 7bb9f6b7e8 Add a VAESave node. 2023-10-09 01:42:15 -04:00
comfyanonymous c16f5744e3 Fix SplitImageWithAlpha and JoinImageWithAlpha. 2023-10-08 15:52:10 -04:00
comfyanonymous 1f2f4eaa6f Fix bug when copying node with converted input. 2023-10-08 04:04:25 -04:00
comfyanonymous 69a824e9a4 Move _for_testing/custom_sampling nodes to sampling/custom_sampling. 2023-10-08 03:20:35 -04:00
Dr.Lt.Data a0b1d4f21d
improve: image preview (#1683) 
* improve image preview
- grid mode: align in rectangle instead of first image, show cell border
- individual mode: proper ratio handling

* improve: fix preview button position instead of relative

* improve: image preview - compact mode for same aspect ratio
 2023-10-08 03:00:33 -04:00
comfyanonymous 1c5d6663fa Update standalone download link. 2023-10-07 16:13:35 -04:00
comfyanonymous 0986cc7c38 Fix issues with the packaging. 2023-10-07 11:57:32 -04:00
pythongosssss ae3e4e9ad8
access getConfig via a symbol so structuredClone works (#1677) 2023-10-06 16:48:30 -04:00
comfyanonymous 72188dffc3 load_checkpoint_guess_config can now optionally output the model. 2023-10-06 13:48:18 -04:00
comfyanonymous 5b828258f1 Merge branch 'widget-input-updates' of https://github.com/pythongosssss/ComfyUI 2023-10-06 12:51:08 -04:00
comfyanonymous 0134d7ab49 Generate update script with right settings. 2023-10-06 12:49:40 -04:00
pythongosssss d761eaa486 if the output type is an array, use combo 2023-10-06 17:47:46 +01:00
comfyanonymous 1497528de8 Fix workflow. 2023-10-06 10:43:12 -04:00
comfyanonymous 640d5080e5 Make xformers optional in packaging. 2023-10-06 10:29:52 -04:00
comfyanonymous 34b36e3207 More configurable workflows to package windows release. 2023-10-06 10:26:51 -04:00
comfyanonymous 6f464f801f Update nightly workflow to python 3.11.6 2023-10-06 03:32:00 -04:00
comfyanonymous 11b404766e Merge branch 'widget-input-updates' of https://github.com/pythongosssss/ComfyUI 2023-10-05 14:20:47 -04:00
pythongosssss b9b178b839 More cleanup of old type data 
Fix connecting combos of same type from different types of node
 2023-10-05 19:16:39 +01:00
pythongosssss 80932ddf40 updated messages 2023-10-05 17:13:13 +01:00
comfyanonymous 48242be508 Update readme for pytorch 2.1 2023-10-05 08:25:15 -04:00
Jairo Correa 63e5fd1790 Option to input directory 2023-10-04 19:45:15 -03:00
comfyanonymous 0e763e880f JoinImageWithAlpha now works with any mask shape. 2023-10-04 15:54:34 -04:00
pythongosssss 0b9246d9fa allow connecting numbers merging config 2023-10-04 20:48:55 +01:00
comfyanonymous 9212bea87c Change a few things in #1578. 2023-10-04 15:43:41 -04:00
MoonRide303 214ca7197e Corrected joining images with alpha (for RGBA input), and checking scaling conditions 2023-10-04 19:04:52 +02:00
MoonRide303 585fb0475b Adding default alpha when splitting RGB images 2023-10-04 19:04:52 +02:00
MoonRide303 ece69bf28c Change channel type to MASK (reduced redundancy, increased usability) 2023-10-04 19:04:52 +02:00
MoonRide303 d06cd2805d Added support for Porter-Duff image compositing 2023-10-04 19:04:48 +02:00
City 9bfec2bdbf Fix quality loss due to low precision 2023-10-04 15:40:59 +02:00