aa57136dae
Some fixes to the batch masks PR.
2 years ago
c7c1f0d074
Merge branch 'multiple_inpaint_masks' of https://github.com/guill/ComfyUI
...
# Conflicts:
# nodes.py
2 years ago
c50208a703
Refactor more code to sample.py
2 years ago
a2236a0c2a
Merge branch 'master' of https://github.com/BlenderNeko/ComfyUI
2 years ago
d9b1595f85
made sample functions more explicit
2 years ago
ccad603b2e
Add a way for nodes to validate their own inputs.
2 years ago
f7a8218814
Add clipspace feature. ( #541 )
...
* Add clipspace feature.
* feat: copy content to clipspace
* feat: paste content from clipspace
Extend validation to allow for validating annotated_path in addition to other parameters.
Add support for annotated_filepath in folder_paths function.
Generalize the '/upload/image' API to allow for uploading images to the 'input', 'temp', or 'output' directories.
* rename contentClipboard -> clipspace
* Do deep copy for imgs on copy to clipspace.
* add original_imgs into clipspace
* Preserve the original image when 'imgs' are modified
* robust patch & refactoring folder_paths about annotated_filepath
* Only show the Paste menu if the ComfyApp.clipspace is not empty
* instant refresh on paste
force triggering 'changed' on paste action
* subfolder fix on paste logic
attach subfolder if subfolder isn't empty
---------
Co-authored-by: Lt.Dr.Data <lt.dr.data@gmail.com>
2 years ago
5818539743
add docstrings
2 years ago
8d2de420d3
Merge branch 'master' of https://github.com/BlenderNeko/ComfyUI
2 years ago
2a09e2aa27
refactor/split various bits of code for sampling
2 years ago
5282f56434
Implement Linear hypernetworks.
...
Add a HypernetworkLoader node to use hypernetworks.
2 years ago
ee030d281b
Add support for multiple unique inpainting masks
...
This enables workflows like "Inpaint at full resolution" when using
batch sizes greater than 1.
2 years ago
31e60adb28
Add GLIGEN example to README.
2 years ago
3696d1699a
Add support for GLIGEN textbox model.
2 years ago
f03dade5ab
Fix bug.
2 years ago
6f7852bc47
Add a LatentFromBatch node to pick a single latent from a batch.
...
Works before and after sampling.
2 years ago
74fc7b7726
custom_nodes paths can now be set in the extra_model_paths.yaml
2 years ago
73c3e11e83
Fix model_management import so it doesn't get executed twice.
2 years ago
f48f0872e2
Refactor: move nodes_mask_convertion nodes to nodes_mask.
2 years ago
e1db7a2038
Merge branch 'image-to-mask' of https://github.com/missionfloyd/ComfyUI
...
# Conflicts:
# nodes.py
2 years ago
1a7cda715b
Revert LatentComposite.
2 years ago
fed4a70b8e
Merge branch 'master' of https://github.com/mligaintart/ComfyUI
2 years ago
d2337a86fe
remove extra semi-colon
2 years ago
9371924e65
Move mask conversion to separate file
2 years ago
45b907fbf1
Merge branch 'comfyanonymous:master' into image-to-mask
2 years ago
f15b4a7ffa
Merge branch 'fix-LoadImageMask' of https://github.com/flyingshutter/ComfyUI
2 years ago
e1d289c1ec
use slice instead of torch.select()
2 years ago
e12fb88b1b
Image/mask conversion nodes
2 years ago
24d53992c6
Rename.
2 years ago
60ac983238
Merge branch 'master' of https://github.com/city96/ComfyUI
2 years ago
44fea05064
Cleanup.
2 years ago
58ed0f2da4
Fix loading SD1.5 diffusers checkpoint.
2 years ago
7734d65f22
fix loading alt folders
2 years ago
f51b7a92c7
search all diffusers paths (oops)
2 years ago
72a8973bd5
allow configurable path for diffusers models
2 years ago
022a9f271b
Adds masking to Latent Composite, and provides new masking utilities to
...
allow better compositing.
2 years ago
9d1c610b89
make LoadImagesMask work with non RGBA images
2 years ago
42fd67b5cb
use precision determined by model management
2 years ago
3d16077e38
empty list if diffusers directory doesn't exist
2 years ago
60127a8304
diffusers loader
2 years ago
f816964847
Add a way to set output directory with --output-directory
2 years ago
10ad4c1d17
Move unclip stuff out of _for_testing
2 years ago
cadef9ff61
Merge branch 'nodes-post-processing' of https://github.com/EllangoK/ComfyUI
2 years ago
f50b1fec69
Add noise augmentation setting to unCLIPConditioning.
2 years ago
4c7a9dbcb6
adds Blend, Blur, Dither, Sharpen nodes
2 years ago
6be7c64245
Merge branch 'custom_routes' of https://github.com/pythongosssss/ComfyUI
2 years ago
809bcc8ceb
Add support for unCLIP SD2.x models.
...
See _for_testing/unclip in the UI for the new nodes.
unCLIPCheckpointLoader is used to load them.
unCLIPConditioning is used to add the image cond and takes as input a
CLIPVisionEncode output which has been moved to the conditioning section.
2 years ago
38833ceb62
Merge remote-tracking branch 'origin/master' into custom_routes
2 years ago
313f1f83a6
Tweak server/custom node load order
...
- Load custom nodes after creating server
- Add routes after loading custom nodes
Custom nodes can now add routes via PromptServer.instance
2 years ago
18a6c1db33
Add a TomePatchModel node to the _for_testing section.
...
Tome increases sampling speed at the expense of quality.
2 years ago
9ac95e6ac7
Add human-readable name support for custom nodes
2 years ago
5bcbc007dd
Add human-readable names for nodes
2 years ago
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
48efadeccf
Style.
2 years ago
8a35c12e8c
compute %width% and %height% in filepath when saving
2 years ago
9287770c66
Allow negative Lora strengths.
2 years ago
e651be551c
Merge branch 'allow-symbolic-link' of https://github.com/jn-jairo/ComfyUI
2 years ago
a30526aec1
Set default value of feathering to 40.
2 years ago
3b87302958
nodes: ImagePadForOutpaint: clean imports
2 years ago
4c01386c19
nodes: ImagePadForOutpaint: fix feathering, ignore edges not expanded
2 years ago
4580f3e644
nodes: add feathering to to ImagePadForOutpaint
2 years ago
4f24e6a13b
Allow output folder to be a symbolic link
2 years ago
3ebf7452c3
nodes: add ImagePadForOutpaint
2 years ago
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
aae9fe0cf9
Increase max res to 8192x8192 since 4096x4096 wasn't enough for some.
2 years ago
aa2ddfabb9
Fix bug with CLIPLoader.
2 years ago
e85fcb822b
Small fix.
2 years ago
0abe001edd
Merge branch 'save-images' of https://github.com/m957ymj75urz/ComfyUI
2 years ago
d1138e8ba0
rework payload from server
2 years ago
50099bcd96
Support multiple paths for embeddings.
2 years ago
2e73367f45
Merge T2IAdapterLoader and ControlNetLoader.
...
Workflows will be auto updated.
2 years ago
e1a9e26968
Add folder_paths so models can be in multiple paths.
2 years ago
bf1dc1d9bc
Fix VAEEncodeForInpaint modifying source image.
2 years ago
16001e9429
fixes for specific paths
2 years ago
d834eed7d0
Fix bug when applying controlnet to negative prompt.
2 years ago
629272c0ca
resolve conflict with the new PreviewImage node
2 years ago
3d2f60b315
Merge branch 'master' into save-images
2 years ago
6d44cf74e3
Make it more clear the recommended way to update the standalone build.
2 years ago
8537ab6f45
tidy
2 years ago
6a6256a75c
Changed flag to new node
2 years ago
6daf9bb22c
switch to realpath to check path traversal
2 years ago
5b425aaa40
remove subfolder widget and use filename_prefix
2 years ago
6db777b348
Added ability to save images to temp dir
2 years ago
70f9bd1408
fix makedirs on save
2 years ago
195d7aec9f
can specify a subfolder in the SaveImage node
2 years ago
c8f1acc4eb
Put image upscaling nodes in image/upscaling category.
2 years ago
e33dc2b33b
Add a VAEEncodeTiled node.
2 years ago
905857edd8
Take some code from chainner to implement ESRGAN and other upscale models.
2 years ago
8c4ccb55d1
Small refactor of custom node loading code.
2 years ago
1f717903bc
Prevent potential int overflow in SaveImage
2 years ago
99eb777f5d
Make the LoadImage node output the alpha as a mask.
2 years ago
fa07426569
Remove random spaces
2 years ago
99abc0eb2e
Changed to upload to input dir
...
Fixed jpg
Added dupe support
Changed to use existing nodes
2 years ago
4a326a2548
Added UploadImage+Mask nodes
2 years ago
0a0c769d6d
Try to fix import issue.
2 years ago
09db31309a
Merge remote-tracking branch 'origin/master' into frontendrefactor
2 years ago
afff30fc0a
Add --cpu to use the cpu for inference.
2 years ago
8515d96328
It's more logical for the StyleModelApply to append it directly.
2 years ago
7ec1dd25a2
A tiny bit of reorganizing.
2 years ago
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
bba14245cb
Merge remote-tracking branch 'origin' into frontendrefactor
2 years ago
b9e3f52240
stop_at_clip_layer can be set in CLIPSetLastLayer so it can be removed
...
from the CLIPLoader node.
2 years ago
4ef4cf913f
Adding built in extensions + example
2 years ago
8586515886
Move the CheckpointLoaderSimple to the right section.
2 years ago
4215206281
Add a node to set CLIP skip.
...
Use a more simple way to detect if the model is -v prediction.
2 years ago
fed315a76a
To be really simple CheckpointLoaderSimple should pick the right type.
2 years ago
94bb0375b0
New CheckpointLoaderSimple to load checkpoints without a config.
2 years ago
c8ce599a8f
Add a button to interrupt processing to the ui.
2 years ago
69cc75fbf8
Add a way to interrupt current processing in the backend.
2 years ago
d826a0971c
Outpainting actually works now.
2 years ago
a9c57849b7
Merge branch 'comfyanonymous:master' into socketrework
2 years ago
4e6b83a80a
Add a T2IAdapterLoader node to load T2I-Adapter models.
...
They are loaded as CONTROL_NET objects because they are similar.
2 years ago
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
9bd7bfa648
Added workflow history
...
Moved socket output updates to all node executions
Made image rendering on nodes more generic
2 years ago
2816eb236d
Merge branch 'comfyanonymous:master' into socketrework
2 years ago
62df8dd62a
Add a node to load diff controlnets.
2 years ago
3ae61a2bca
Add a node to invert the colours of images.
...
Might be useful for controlnets.
2 years ago
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
d80af7ca30
ControlNetApply now stacks.
...
It can be used to apply multiple control nets at the same time.
2 years ago
8683ea4248
Merge branch 'master' into m957ymj75urz-dynamic-prompting
2 years ago
a3d0b56c61
Fix for relative imports in custom nodes.
2 years ago
e2e5c4c5b0
Add basic dynamic prompting with seeding on CLIPTextEncode node
2 years ago
71354c7c57
Sort images on LoadImageMask node.
2 years ago
1688f5024d
Fix a few issues with the custom_nodes PR.
...
There only needs to be one example in the folder.
2 years ago
fa66ece26b
Merge branch 'comfyanonymous:master' into master
2 years ago
1c5fe809c2
.
2 years ago
638f924546
Sort the list of input images.
2 years ago
6135a21ee8
Add a way to control controlnet strength.
2 years ago
4efa67fa12
Add ControlNet support.
2 years ago
bc69fb5245
Use inpaint models the proper way by using VAEEncodeForInpaint.
2 years ago
e87a8669b6
Add a LoadImageMask node to load one colour channel in an image as a mask.
2 years ago
d75003001a
Add a SetLatentNoiseMask node.
...
LATENT is now a dict that can contain properties.
2 years ago
e1a047971b
Edit comment
2 years ago
7da0147d8a
Done custom_node import error fixing
2 years ago
b67b6920d1
Fix bug
2 years ago
493671574e
Adding some suggests from the author
2 years ago
721f8510af
Change the words a bit
2 years ago
f3c6d7adf2
.
2 years ago
5ce4b9eca3
Add custom node feature
2 years ago
05ad64d22c
Add a feather option to the latent composite node.
2 years ago
642516a3a6
create output dir if none is present
2 years ago
1d9ec62cfb
Use absolute output directory path.
2 years ago
e58887dfa7
forgot windows does double backslashes for paths due to its use as escape char.
2 years ago
81082045c2
add recursive_search, swap relevant os.listdirs
2 years ago
3e22815a9a
Fix k_diffusion not getting imported from the folder.
2 years ago
a84cd0d1ad
Don't unload/reload model from CPU uselessly.
2 years ago
1de5aa6a59
Add a CLIPLoader node to load standalone clip weights.
...
Put them in models/clip
2 years ago
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
bff0e11941
Add a LatentCrop node.
2 years ago
149a4de3f2
Fix potential issue if exception happens when patching model.
2 years ago
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
fef41d0a72
Add LatentComposite node.
...
This can be used to "paste" one latent image on top of the other.
2 years ago
3fa009f4cc
Add a LatentFlip node.
2 years ago
69df7eba94
Add KSamplerAdvanced node.
...
This node exposes more sampling options and makes it possible for example
to sample the first few steps on the latent image, do some operations on it
and then do the rest of the sampling steps. This can be achieved using the
start_at_step and end_at_step options.
2 years ago
f8f165e2c3
Add a LatentRotate node.
2 years ago
f73e57d881
Add support for textual inversion embedding for SD1.x CLIP.
2 years ago
2706c0b7a5
Some VAEs come in .pt files.
2 years ago
21eb33f233
Right category for latent upscale node.
2 years ago
2a87f6630d
Some categories for the nodes.
2 years ago
c4b02059d0
Add ConditioningSetArea node.
...
to apply conditioning/prompts only to a specific area of the image.
Add ConditioningCombine node.
so that multiple conditioning/prompts can be applied to the image at the
same time
2 years ago
463d0d0828
Add a center crop option to latent upscale node.
2 years ago
c1eac7bab2
Add filename_prefix to SaveImage node.
2 years ago
a34cde08cb
Nodes now support single line string properties.
...
Resize nodes automatically if they are too small because of added properties.
2 years ago
9baa48cb33
Add IS_CHANGED method to nodes to check if nodes should be executed again.
...
LoadImage.IS_CHANGED returns the hash of the image so it will execute again
if the image changed on the disk.
2 years ago
15f8da2849
Add a LoadImage node to load images for img2img.
2 years ago
220afe3310
Initial commit.
2 years ago
comfyanonymous
BlenderNeko
ltdrdata
Jacob Segal
Gavroche CryptoRUSH
missionfloyd
sALTaccount
mligaintart
flyingshutter
EllangoK
pythongosssss
City
Silversith
m957ymj75urz
Guo Y.K
Jairo Correa
m957ymj75urz
Fannovel16
BazettFraga