165 Commits (c7c1f0d074ccac36a6e7b1190f2c6ceb34e20d0e)

Author SHA1 Message Date
City 5bcbc007dd Add human-readable names for nodes 2 years ago
Silversith bb1503ed63
Bugfix/include optional node inputs (#271)
* Minor changes and extra nodes

* Added Preview Image for Nodes

* Add a delete images button on main floating menu

* Add a confirmation dialog

* Remove DeleteAll, Remove Custom KSampler, Remove Image List

* Remove Image and Custom Json Load

* Remove Custom Nodes

* remove patch.diff
2 years ago
comfyanonymous 48efadeccf Style. 2 years ago
m957ymj75urz 8a35c12e8c compute %width% and %height% in filepath when saving 2 years ago
comfyanonymous 9287770c66 Allow negative Lora strengths. 2 years ago
comfyanonymous e651be551c Merge branch 'allow-symbolic-link' of https://github.com/jn-jairo/ComfyUI 2 years ago
comfyanonymous a30526aec1 Set default value of feathering to 40. 2 years ago
Guo Y.K 3b87302958
nodes: ImagePadForOutpaint: clean imports 2 years ago
Guo Y.K 4c01386c19
nodes: ImagePadForOutpaint: fix feathering, ignore edges not expanded 2 years ago
Guo Y.K 4580f3e644
nodes: add feathering to to ImagePadForOutpaint 2 years ago
Jairo Correa 4f24e6a13b Allow output folder to be a symbolic link 2 years ago
Guo Y.K 3ebf7452c3
nodes: add ImagePadForOutpaint 2 years ago
comfyanonymous cc127eeabd Lower PNG compression for more speed.
After some quick tests compress_level=4 seems to give the best compression
performance ratio for stable diffusion images.

It's 10x faster than max compression for an image size increase of only
2.5%.
2 years ago
comfyanonymous aae9fe0cf9 Increase max res to 8192x8192 since 4096x4096 wasn't enough for some. 2 years ago
comfyanonymous aa2ddfabb9 Fix bug with CLIPLoader. 2 years ago
comfyanonymous e85fcb822b Small fix. 2 years ago
comfyanonymous 0abe001edd Merge branch 'save-images' of https://github.com/m957ymj75urz/ComfyUI 2 years ago
m957ymj75urz d1138e8ba0 rework payload from server 2 years ago
comfyanonymous 50099bcd96 Support multiple paths for embeddings. 2 years ago
comfyanonymous 2e73367f45 Merge T2IAdapterLoader and ControlNetLoader.
Workflows will be auto updated.
2 years ago
comfyanonymous e1a9e26968 Add folder_paths so models can be in multiple paths. 2 years ago
comfyanonymous bf1dc1d9bc Fix VAEEncodeForInpaint modifying source image. 2 years ago
m957ymj75urz 16001e9429 fixes for specific paths 2 years ago
comfyanonymous d834eed7d0 Fix bug when applying controlnet to negative prompt. 2 years ago
m957ymj75urz 629272c0ca resolve conflict with the new PreviewImage node 2 years ago
m957ymj75urz 3d2f60b315
Merge branch 'master' into save-images 2 years ago
comfyanonymous 6d44cf74e3 Make it more clear the recommended way to update the standalone build. 2 years ago
pythongosssss 8537ab6f45 tidy 2 years ago
pythongosssss 6a6256a75c Changed flag to new node 2 years ago
m957ymj75urz 6daf9bb22c switch to realpath to check path traversal 2 years ago
m957ymj75urz 5b425aaa40 remove subfolder widget and use filename_prefix 2 years ago
pythongosssss 6db777b348 Added ability to save images to temp dir 2 years ago
m957ymj75urz 70f9bd1408 fix makedirs on save 2 years ago
m957ymj75urz 195d7aec9f can specify a subfolder in the SaveImage node 2 years ago
comfyanonymous c8f1acc4eb Put image upscaling nodes in image/upscaling category. 2 years ago
comfyanonymous e33dc2b33b Add a VAEEncodeTiled node. 2 years ago
comfyanonymous 905857edd8 Take some code from chainner to implement ESRGAN and other upscale models. 2 years ago
comfyanonymous 8c4ccb55d1 Small refactor of custom node loading code. 2 years ago
comfyanonymous 1f717903bc Prevent potential int overflow in SaveImage 2 years ago
comfyanonymous 99eb777f5d Make the LoadImage node output the alpha as a mask. 2 years ago
pythongosssss fa07426569 Remove random spaces 2 years ago
pythongosssss 99abc0eb2e Changed to upload to input dir
Fixed jpg
Added dupe support
Changed to use existing nodes
2 years ago
pythongosssss 4a326a2548 Added UploadImage+Mask nodes 2 years ago
comfyanonymous 0a0c769d6d Try to fix import issue. 2 years ago
pythongosssss 09db31309a Merge remote-tracking branch 'origin/master' into frontendrefactor 2 years ago
comfyanonymous afff30fc0a Add --cpu to use the cpu for inference. 2 years ago
comfyanonymous 8515d96328 It's more logical for the StyleModelApply to append it directly. 2 years ago
comfyanonymous 7ec1dd25a2 A tiny bit of reorganizing. 2 years ago
comfyanonymous 47acb3d73e Implement support for t2i style model.
It needs the CLIPVision model so I added CLIPVisionLoader and CLIPVisionEncode.

Put the clip vision model in models/clip_vision
Put the t2i style model in models/style_models

StyleModelLoader to load it, StyleModelApply to apply it
ConditioningAppend to append the conditioning it outputs to a positive one.
2 years ago
pythongosssss bba14245cb Merge remote-tracking branch 'origin' into frontendrefactor 2 years ago
comfyanonymous b9e3f52240 stop_at_clip_layer can be set in CLIPSetLastLayer so it can be removed
from the CLIPLoader node.
2 years ago
pythongosssss 4ef4cf913f Adding built in extensions + example 2 years ago
comfyanonymous 8586515886 Move the CheckpointLoaderSimple to the right section. 2 years ago
comfyanonymous 4215206281 Add a node to set CLIP skip.
Use a more simple way to detect if the model is -v prediction.
2 years ago
comfyanonymous fed315a76a To be really simple CheckpointLoaderSimple should pick the right type. 2 years ago
comfyanonymous 94bb0375b0 New CheckpointLoaderSimple to load checkpoints without a config. 2 years ago
comfyanonymous c8ce599a8f Add a button to interrupt processing to the ui. 2 years ago
comfyanonymous 69cc75fbf8 Add a way to interrupt current processing in the backend. 2 years ago
comfyanonymous d826a0971c Outpainting actually works now. 2 years ago
pythongosssss a9c57849b7
Merge branch 'comfyanonymous:master' into socketrework 2 years ago
comfyanonymous 4e6b83a80a Add a T2IAdapterLoader node to load T2I-Adapter models.
They are loaded as CONTROL_NET objects because they are similar.
2 years ago
comfyanonymous 87b00b37f6 Added an experimental VAEDecodeTiled.
This decodes the image with the VAE in tiles which should be faster and
use less vram.

It's in the _for_testing section so I might change/remove it or even
add the functionality to the regular VAEDecode node depending on how
well it performs which means don't depend too much on it.
2 years ago
pythongosssss 9bd7bfa648
Added workflow history
Moved socket output updates to all node executions
Made image rendering on nodes more generic
2 years ago
pythongosssss 2816eb236d
Merge branch 'comfyanonymous:master' into socketrework 2 years ago
comfyanonymous 62df8dd62a Add a node to load diff controlnets. 2 years ago
comfyanonymous 3ae61a2bca Add a node to invert the colours of images.
Might be useful for controlnets.
2 years ago
pythongosssss a52aa9f4b5
Moved api out to server
Reworked sockets to use socketio
Added progress to nodes
Added highlight to active node
Added preview to saveimage node
2 years ago
comfyanonymous d80af7ca30 ControlNetApply now stacks.
It can be used to apply multiple control nets at the same time.
2 years ago
comfyanonymous 8683ea4248 Merge branch 'master' into m957ymj75urz-dynamic-prompting 2 years ago
comfyanonymous a3d0b56c61 Fix for relative imports in custom nodes. 2 years ago
m957ymj75urz e2e5c4c5b0 Add basic dynamic prompting with seeding on CLIPTextEncode node 2 years ago
comfyanonymous 71354c7c57 Sort images on LoadImageMask node. 2 years ago
comfyanonymous 1688f5024d Fix a few issues with the custom_nodes PR.
There only needs to be one example in the folder.
2 years ago
Fannovel16 fa66ece26b
Merge branch 'comfyanonymous:master' into master 2 years ago
Hacker 17082006 1c5fe809c2 . 2 years ago
comfyanonymous 638f924546 Sort the list of input images. 2 years ago
comfyanonymous 6135a21ee8 Add a way to control controlnet strength. 2 years ago
comfyanonymous 4efa67fa12 Add ControlNet support. 2 years ago
comfyanonymous bc69fb5245 Use inpaint models the proper way by using VAEEncodeForInpaint. 2 years ago
comfyanonymous e87a8669b6 Add a LoadImageMask node to load one colour channel in an image as a mask. 2 years ago
comfyanonymous d75003001a Add a SetLatentNoiseMask node.
LATENT is now a dict that can contain properties.
2 years ago
Hacker 17082006 e1a047971b Edit comment 2 years ago
Hacker 17082006 7da0147d8a Done custom_node import error fixing 2 years ago
Hacker 17082006 b67b6920d1 Fix bug 2 years ago
Hacker 17082006 493671574e Adding some suggests from the author 2 years ago
Hacker 17082006 721f8510af Change the words a bit 2 years ago
Hacker 17082006 f3c6d7adf2 . 2 years ago
Hacker 17082006 5ce4b9eca3 Add custom node feature 2 years ago
comfyanonymous 05ad64d22c Add a feather option to the latent composite node. 2 years ago
BazettFraga 642516a3a6 create output dir if none is present 2 years ago
comfyanonymous 1d9ec62cfb Use absolute output directory path. 2 years ago
BazettFraga e58887dfa7 forgot windows does double backslashes for paths due to its use as escape char. 2 years ago
BazettFraga 81082045c2 add recursive_search, swap relevant os.listdirs 2 years ago
comfyanonymous 3e22815a9a Fix k_diffusion not getting imported from the folder. 2 years ago
comfyanonymous a84cd0d1ad Don't unload/reload model from CPU uselessly. 2 years ago
comfyanonymous 1de5aa6a59 Add a CLIPLoader node to load standalone clip weights.
Put them in models/clip
2 years ago
comfyanonymous 4225d1cb9f Add a basic ImageScale node.
It's pretty much the same as the LatentUpscale node for now but for images
in pixel space.
2 years ago
comfyanonymous bff0e11941 Add a LatentCrop node. 2 years ago
comfyanonymous 149a4de3f2 Fix potential issue if exception happens when patching model. 2 years ago
comfyanonymous ef90e9c376 Add a LoraLoader node to apply loras to models and clip.
The models are modified in place before being used and unpatched after.
I think this is better than monkeypatching since it might make it easier
to use faster non pytorch unet inference in the future.
2 years ago