1556 Commits (1a4bd9e9a6fc2b364ebb547dbd80736548cf9f5c)
 

Author SHA1 Message Date
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.
1 year ago
comfyanonymous 8cc75c64ff Let unet wrapper functions have .to attributes. 1 year ago
comfyanonymous 5e885bd9c8 Cleanup. 1 year ago
comfyanonymous 851bb87ca9 Merge branch 'taesd_safetensors' of https://github.com/mochiya98/ComfyUI 1 year ago
comfyanonymous be903eb2e2 Add default CheckpointSave, CLIPSave and VAESave paths to model paths. 1 year ago
comfyanonymous 877553843f Add a CLIPSave node to save CLIP model weights. 1 year ago
Yukimasa Funaoka 9eb621c95a
Supports TAESD models in safetensors format 1 year ago
comfyanonymous d1a0abd40b Merge branch 'input-directory' of https://github.com/jn-jairo/ComfyUI 1 year ago
comfyanonymous 4308862ce0 Add a note to README about pytorch 3.12 not being supported. 1 year ago
comfyanonymous 7bb9f6b7e8 Add a VAESave node. 1 year ago
comfyanonymous c16f5744e3 Fix SplitImageWithAlpha and JoinImageWithAlpha. 1 year ago
comfyanonymous 1f2f4eaa6f Fix bug when copying node with converted input. 1 year ago
comfyanonymous 69a824e9a4 Move _for_testing/custom_sampling nodes to sampling/custom_sampling. 1 year ago
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
1 year ago
comfyanonymous 1c5d6663fa Update standalone download link. 1 year ago
comfyanonymous 0986cc7c38 Fix issues with the packaging. 1 year ago
pythongosssss ae3e4e9ad8
access getConfig via a symbol so structuredClone works (#1677) 1 year ago
comfyanonymous 72188dffc3 load_checkpoint_guess_config can now optionally output the model. 1 year ago
comfyanonymous 5b828258f1 Merge branch 'widget-input-updates' of https://github.com/pythongosssss/ComfyUI 1 year ago
comfyanonymous 0134d7ab49 Generate update script with right settings. 1 year ago
pythongosssss d761eaa486 if the output type is an array, use combo 1 year ago
comfyanonymous 1497528de8 Fix workflow. 1 year ago
comfyanonymous 640d5080e5 Make xformers optional in packaging. 1 year ago
comfyanonymous 34b36e3207 More configurable workflows to package windows release. 1 year ago
comfyanonymous 6f464f801f Update nightly workflow to python 3.11.6 1 year ago
comfyanonymous 11b404766e Merge branch 'widget-input-updates' of https://github.com/pythongosssss/ComfyUI 1 year ago
pythongosssss b9b178b839 More cleanup of old type data
Fix connecting combos of same type from different types of node
1 year ago
pythongosssss 80932ddf40 updated messages 1 year ago
comfyanonymous 48242be508 Update readme for pytorch 2.1 1 year ago
Jairo Correa 63e5fd1790 Option to input directory 1 year ago
comfyanonymous 0e763e880f JoinImageWithAlpha now works with any mask shape. 1 year ago
pythongosssss 0b9246d9fa allow connecting numbers merging config 1 year ago
comfyanonymous 9212bea87c Change a few things in #1578. 1 year ago
MoonRide303 214ca7197e Corrected joining images with alpha (for RGBA input), and checking scaling conditions 1 year ago
MoonRide303 585fb0475b Adding default alpha when splitting RGB images 1 year ago
MoonRide303 ece69bf28c Change channel type to MASK (reduced redundancy, increased usability) 1 year ago
MoonRide303 d06cd2805d Added support for Porter-Duff image compositing 1 year ago
City 9bfec2bdbf Fix quality loss due to low precision 1 year ago
pythongosssss 6fc7314393 support refreshing primitive combos
no longer uses combo list as type name
1 year ago
comfyanonymous 4103f7fad5 Merge branch 'fix/robust_object_info' of https://github.com/ltdrdata/ComfyUI 1 year ago
Dr.Lt.Data 1f38de1fb3 If an error occurs while retrieving object_info, only the node that encountered the error should be handled as an exception, while the information for the other nodes should continue to be processed normally. 1 year ago
comfyanonymous fe1e2dbe90 pytorch nightly is now ROCm 5.7 1 year ago
comfyanonymous ec454c771b Refactor with code from comment of #1588 1 year ago
comfyanonymous 2ef459b1d4 Add VPScheduler node 1 year ago
comfyanonymous 8ab49dc0a4 DPMPP_SDE node. 1 year ago
comfyanonymous 213976f8c3 Add ExponentialScheduler and PolyexponentialScheduler nodes. 1 year ago
badayvedat 0f17993d05 fix: typo in extra sampler 1 year ago
Jukka Seppänen 1c8ae9dbb2
Allow GrowMask node to work with batches (for AnimateDiff) (#1623)
* Allow mask batches

This allows LatentCompositeMasked -node to work with AnimateDiff. I tried to keep old functionality too, unsure if it's correct, but both single mask and batch of masks seems to work with this change.

* Update nodes_mask.py
1 year ago
comfyanonymous 66756de100 Add SamplerDPMPP_2M_SDE node. 1 year ago
comfyanonymous 26b7372805 Fix SplitSigmas. 1 year ago