RC 24.04.13.0 Nodes List

Character Face Swap

Character face swap with LoRA and embeddings.

f395496e5bf50d88579934ec2f776cd81866e8e9

ComfyMath

Provides Math Nodes for ComfyUI. Boolean Logic, Integer Arithmetic, Floating Point Arithmetic and Functions, Vec2, Vec3, and Vec4 Arithmetic and Functions

be9beab9923ccf5c5e4132dc1653bcdfa773ed70

ComfyUI-Advanced-ControlNet

Nodes: ControlNetLoaderAdvanced, DiffControlNetLoaderAdvanced, ScaledSoftControlNetWeights, SoftControlNetWeights, CustomControlNetWeights, SoftT2IAdapterWeights, CustomT2IAdapterWeights

33d9884b76e8d7a2024691c5d98308e7e61bf38d

Merge PR #97 from Kosinkadink/develop: lowvram SparseCtrl fix Fix SparseCtrl for lowvram Account for use_motion being off Fixed SparseCtrl not working with lowvram Update README.md- full ReferenceCN support Merge PR #95 from Kosinkadink/develop SD1.5 ControlLoRA fix ControlLora fix for weights error Removed extra empty line I accidentally added Fix for cases where predefined weights length doesn't match expected layer lengths (will need to generalize for for ControlLora to properly do soft weights for actual layer number) Merge PR #93 from Kosinkadink/develop: reference_adain and reference_adain+attn support Added reference_adain and reference_adain+attn support Removed unnecessary dropdown from Reference ControlNet (Finetune) node, as should always be adain+attn anyway to prevent confusion Made sure ref cns match up to expected bank indexes, made adain properly react to strengths and masks Added Reference ControlNet (Finetune) to control attn and adain values separately Started separating out attn and adain variables to prevent issues when using multiple RefCN Added initial reference_adain and reference_adain+attn support Merge PR #92 from Kosinkadink/develop - Reference support Reference ControlNet support (reference_attn) Fixed BIGMIN and BIGMAX to conform with javascript limits, pretty-fied deprecated node Update README.md - Reference support (reference_attn) Only expose reference_attn for now since it's the only one with code support (adain coming soon) Added latent_kf and masking support (masks don't work per-area currently, but do work per-latent) Don't apply normal CNs during ref cn WRITE runs Simplified RefCN injection, model_opt no longer needed and should fix some intermittent bugs Applied proper strength control to attn1_replace_patch as well Added proper strength control to ReferenceCN, replaced old strength with ref_weight Cleaned up ref cn so I can add more features Merge branch 'main' into develop Merge PR #86 from Kosinkadink/import-fix Fixed ModelPatcher import in control.py Fixed ModelPatcher import in control.py More refcn debugging and fix for refcn issue for ancestral samplers while testing Merge branch 'main' into develop Merge PR #79 from Kosinkadink/comfyui-update Match T2iAdapter ComfyUI changes Updated T2IAdapterAdvanced to match recent ComfyUI changes

Advanced CLIP Text Encode

Advanced CLIP Text Encode (if you need A1111 like prompt. you need this. But Cutoff node includes this feature, already.)

63984deefb005da1ba90a1175e21d91040da38ab

Merge pull request #21 from ltdrdata/fix/set_clip_layer fix: compatbility patch (ComfyUI update) compatbility patch clip_layer -> set_clip_options fix missing imports

AnimateDiff Evolved

A forked repository that actively maintains [a/AnimateDiff](https://github.com/ArtVentureX/comfyui-animatediff), created by ArtVentureX. Improved AnimateDiff integration for ComfyUI, adapts from sd-webui-animatediff. [w/Download one or more motion models from [a/Original Models](https://huggingface.co/guoyww/animatediff/tree/main) | [a/Finetuned Models](https://huggingface.co/manshoety/AD_Stabilized_Motion/tree/main). See README for additional model links and usage. Put the model weights under %%ComfyUI/custom_nodes/ComfyUI-AnimateDiff-Evolved/models%%. You are free to rename the models, but keeping original names will ease use when sharing your workflow.]

f9e0343f4c4606ee6365a9af4a7e16118f1c45e1

Merge PR #337 from Kosinkadink/freeinit_samplersigma_fix Make FreeInit [sampler sigma] work with new ComfyUI versions Make FreeInit [sampler sigma] work with new ComfyUI versions Merge PR #332 from Kosinkadink/new_comfy_update: will work with upcoming update Prepare compatibility for upcoming ComfyUI patch Remove unnecessary import as Prepare compatibility for upcoming ComfyUI patch Merge PR #328 from Kosinkadink/use_calc_cond_batch Use calc_cond_batch with backwards compatibility Use calc_cond_batch with backwards compatibility Merge pull request #321 from Kosinkadink/unpatch-update-fix Accounted for unpatch_model changes in new ComfyUI Accounted for unpatch_model changes in new ComfyUI Merge PR #319 from Kosinkadink/patch-model-fix - patch_weights fix Add patch_weights to ModelPatcherAndInjector to work with lowvram Made patch_model fix backwards compatible for now Add patch_weights to ModelPatcherAndInjector to work with lowvram Merge PR #315 from Kosinkadink/develop - Added Weight Adjust Nodes Added Weight Adjust Nodes Added Weight Adjust nodes add/mult AD model weights (the real replacement and advancement for the months-deprecated motion model settings) Merge PR #314 from Kosinkadink/develop - AnimateLCM2-I2V support Added AnimateLCM-I2V support Made AnimateLCM-I2V fp8-compatible Fixed missing capitalization in Scale Ref Image and VAE Encode name Update README.md Added Scacle Ref and Vae Encode node to simplify inserting good latents into ref_latent, added extras emojis on deprecated node names Fixed EncoderOnlyTemporalModule not getting ejected Fixed bug with ref in AnimateLCM-I2V continued to be used, exposed a proper way of replicating the bug or using just the img_encoder without the motion model, AnimateDiffModel changes to facilitate these features Added initial AnimateLCM-I2V support Renamed a few long vars, refactoring to support AnimateLCM-I2V model Fix 'autoselect' beta_schedule not working with Use Evolved Sampling when no motion models are used Merge PR #310 from BlakeOne/fix_admd_lora_keys fix admd lora keys

APISR IN COMFYUI

Unofficial implementation of APISR for ComfyUI, both image and video

4c8b71e9c27f0b867adc969cd5ba117df4339f4c

ComfyUI-BRIA_AI-RMBG

Unofficial implementation of BRIA RMBG Model for ComfyUI.

44a3f8f9362aab07df068dcbe5835527bf993391

ComfyUI-CCSR

ComfyUI- CCSR upscaler node

2ed9df039911306d528b58c82075f40f9a764207

Comfyroll Studio

Custom nodes for SDXL and SD1.5 including Multi-ControlNet, LoRA, Aspect Ratio, Process Switches, and many more nodes. NOTE: Maintainer is changed to Suzie1 from RockOfFire. [w/Using an outdated version has resulted in reported issues with updates not being applied. Trying to reinstall the software is advised.]

d78b780ae43fcf8c6b7c6505e6ffb4584281ceca

ComfyUI's ControlNet Auxiliary Preprocessors

This is a rework of comfyui_controlnet_preprocessors based on ControlNet auxiliary models by 🤗. I think the old repo isn't good enough to maintain. All old workflow will still be work with this repo but the version option won't do anything. Almost all v1 preprocessors are replaced by v1.1 except those doesn't appear in v1.1. [w/NOTE: Please refrain from using the controlnet preprocessor alongside this installation, as it may lead to conflicts and prevent proper recognition.]

c0b33402d9cfdc01c4e0984c26e5aadfae948e05

Merge pull request #291 from DrJKL/drjkl/convenience_selector Add Convenience node to emit preprocessor options Fix overflow for normalizing normalized keypoints in FacialPartColoringFromPoseKps Fix https://github.com/Fannovel16/comfyui_controlnet_aux/issues/292 Fix DSINE import issues Merge pull request #297 from JettHu/main Use huggingface_hub constants instead of manually reading from environment variables Use huggingface_hub package constants instead of manually reading from environment variables Use huggingface_hub package newer constants `HF_HUB_CACHE` instead of manually reading from environment variables. Compatibility with legacy `HUGGINGFACE_HUB_CACHE` and also works on `HF_HOME`. Add Convenience node to emit preprocessor options Merge pull request #272 from xingren23/main lazy load, optimize load time from 0.3s to 0.0s

Crystools

With this suit, you can see the resources monitor, progress bar & time elapsed, metadata and compare between two images, compare between two JSONs, show any value to console/display, pipes, and more! This provides better nodes to load/save images, previews, etc, and see "hidden" data without loading a new workflow.

bfbfd121a245d04ce7d06ccc36acdb9873c47d9d

Update README.md temperature is added switch mask added

pythongosssss/ComfyUI-Custom-Scripts

This extension provides: Auto Arrange Graph, Workflow SVG, Favicon Status, Image Feed, Latent Upscale By, Lock Nodes & Groups, Lora Subfolders, Preset Text, Show Text, Touch Support, Link Render Mode, Locking, Node Finder, Quick Nodes, Show Image On Menu, Show Text, Workflow Managements, Custom Widget Default Values

3f2c021e50be2fed3c9d1552ee8dcaae06ad1fe5

Support custom + multiple models per node Merge pull request #204 from choey/deduplicate-image-feed image feed deduplication Remove duplicated function remove benchmarking Merge branch 'main' of github.com:choey/ComfyUI-Custom-Scripts into deduplicate-image-feed remove benchmarking faster image feed deduplication Merge branch 'main' of github.com:choey/ComfyUI-Custom-Scripts into deduplicate-image-feed Merge pull request #223 from DrJKL/patch-2 Fix display type for image feed when toggled Fix display time for image feed when toggled fix default Remove log Support custom favicon Add max autocomplete suggestions fixes for new menu Merge pull request #203 from JaredTherriault/main Add undo support to autocomplete actually fix fix crash Update for new menu Merge branch 'main' of https://github.com/pythongosssss/ComfyUI-Custom-Scripts change spinner class Merge pull request #216 from tobbez/lightbox-update-new-images Update lightbox with images generated while it is open fix race condition loading loras Fix quantifiers Use loras from node Update lightbox with images generated while it is open This removes the need to close and re-open the lightbox to view images that were completed while it was open. Merge pull request #206 from stereosix/main Fix relative import paths in autocompleter.js Merge pull request #207 from gaowei-space/fix_extra_pnginfo Fix a bug in notify, line is "if unique_id and extra_pnginfo and… fix: Fix a bug in notify, line is "if unique_id and extra_pnginfo and workflow in extra_pnginfo[0]", Error: TypeError: argument of type NoneType is not iterable Fix relative paths add tooltip with notes on performance implications replaced crypto.subtle.digest with simple, unsafe hash to avoid browser error under insecure context formatting changes only memoize the sha-1 hash of stripped image, as opposed to the b64 img formatting changes only deduplicate image by content sans metadata refactored new image handling for image feed; created addImageToFeed added image feed deduplication based on src metadata Remove whitespace changes from undo support Revert "Add undo support to autocomplete" This reverts commit 6f5b74f6f7e7fe4476a101edf625193037717f4c. Add undo support to autocomplete Merge pull request #200 from Lawrr/fix-preview-image-uri-encoding Fix uri encoding for preview image

ComfyUI-DynamiCrafterWrapper

Wrapper nodes to use DynamiCrafter image2video and frame interpolation models in ComfyUI

19e0c9ef5d9c16395269ffe45ff01403b015a8b2

Fix loading 512 non-interolation model fp8 unet option saves about 1.5GB VRAM during sampling

Eagle PNGInfo

Nodes: EagleImageNode

72752f6d41e45f93f124dbbe6409ed40d291dd95

ComfyUI Essentials

Essential nodes that are weirdly missing from ComfyUI core. With few exceptions they are new features and not commodities. I hope this will be just a temporary repository until the nodes get included into ComfyUI.

78fa0fdc397760a1e4239d43011015d17f70291e

add padding and blur to maskboundingbox add mask bounding box fix KSamplerVariationsWithNoise after recent comfy update add pixelize fix imagelisttobatch add image list to batch add multiple_of to resize-image

FizzNodes

Scheduled prompts, scheduled float/int values and wave function nodes for animations and utility. compatable with [a/framesync](https://www.framesync.xyz/) and [a/keyframe-string-generator](https://www.chigozie.co.uk/keyframe-string-generator/) for audio synced animations in Comfyui.

ccdc15f6f829f193b9b20ee1badbce2a0aadb6b8

image select schedule added added neg output to SDXL schedule nodes SDXL schedules fixed Merge branch 'main' of https://github.com/FizzleDorf/ComfyUI_FizzNodes pulling changes for updated string schedule fixed pre and app text for string schedules Merge pull request #77 from xingren23/main fix: prompt_weight_1/2 type error fix: prompt_weight_1/2 type error added check to set max_size to largest tokenized tensor size uncommented tuple conversion of int/floats

ComfyUI-Flowty-TripoSR

This is a custom node that lets you use TripoSR right from ComfyUI. [a/TripoSR](https://github.com/VAST-AI-Research/TripoSR) is a state-of-the-art open-source model for fast feedforward 3D reconstruction from a single image, collaboratively developed by Tripo AI and Stability AI. (TL;DR it creates a 3d model from an image.)

a0c94ac60a7cc062604f61aeeea6d0d493521de3

ComfyUI Frame Interpolation

Nodes: KSampler Gradually Adding More Denoise (efficient)

5e11679995c68f33891c306a393915feefe234b5

ComfyUI Impact Pack

This extension offers various detector nodes and detailer nodes that allow you to configure a workflow that automatically enhances facial details. And provide iterative upscaler. [w/NOTE:'Segs & Mask' has been renamed to 'ImpactSegsAndMask.' Please replace the node with the new name.]

8ffc4efcd6a12649ba5f524602dd24a74ea8145b

fix: better compatibility with other nodes. https://github.com/ltdrdata/ComfyUI-Impact-Pack/issues/547 fix: show proper warning message instead of crash https://github.com/ltdrdata/ComfyUI-Impact-Pack/issues/548 (commit message fix) fix: show proper warning message instead of crash https://github.com/ltdrdata/ComfyUI-Impact-Pack/issues/470#issuecomment-2043954600 fix: detailer - inconsistency on overlapping area fix: unsampler patch again... fix: unsampler compatibility Fix Picker (SEGS) mutating underlying mask (#543) SAMLoader - ESAM supports required PR `https://github.com/ZHO-ZHO-ZHO/ComfyUI-YoloWorld-EfficientSAM/pull/32` https://github.com/ltdrdata/ComfyUI-Impact-Pack/issues/541 fix: SubtractMaskForEach - invalid logic https://github.com/ltdrdata/ComfyUI-Impact-Pack/issues/540 fix: impact_sampling - compatibility patch https://github.com/comfyanonymous/ComfyUI/commit/1a0486bb96fb1ff10f4ea3c0d62eb815e9630585 feat: support conditioning mask for other detailers Fix conditioning masks not being cropped in SEGSDetailer (#539) improve: support conditioning set mask in detailer Fix conditioning masks not being cropped in SEGSDetailer fix: detector (combined) - support 3-dim mask instead of 2-dim mask https://github.com/ltdrdata/ComfyUI-Inspire-Pack/issues/94 improve: IPAdapterWrapper - support neg_image fix: support updated ComfyUI IPAdapter Plus update README improve: IterativeLatentUpscale - use geometric progression for upscale steps (#523) * improve: IterativeLatentUpscale - use geometric progression for upscale steps This is a small change to IterativeLatentUpscale that makes the sequence of the upscale steps to use geometric progression rather than arithmetic. This has the advantage that every step scales the intermediate image by the same factor. * feat: Iterative Upscale - support `step_mode` --------- Co-authored-by: Dr.Lt.Data <dr.lt.data@gmail.com> Co-authored-by: Dr.Lt.Data <128333288+ltdrdata@users.noreply.github.com> improve: SEGSUpscaler apply DifferentialDiffusion by noise_mask_feather fix: Upscaler (SEGS) - compensate resolution fix: robust `tensor_paste` https://github.com/ltdrdata/ComfyUI-Impact-Pack/issues/512

ComfyUI Inspire Pack

This extension provides various nodes to support Lora Block Weight and the Impact Pack. Provides many easily applicable regional features and applications for Variation Seed.

f4186951fb823683f7b231104e6f9e23d7f77ab8

update credit fix: IPAdapterModelHelper - missing clip_vision for several faceid settings improve: RegionalIPAdapter - support neg_image fix: missing display name fix: support new IPAdapter Plus fix:global_seed - store last_seed properly https://github.com/ltdrdata/ComfyUI-Inspire-Pack/issues/84 fix: global_seed - cannot reproduce seed if control before mode - store updated seed to workflow - change to `fixed` mode if control before to reproduce https://github.com/ltdrdata/ComfyUI-Inspire-Pack/issues/84 fix: IPAdapterModelHelper - missing cache tag https://github.com/ltdrdata/ComfyUI-Inspire-Pack/issues/89 improve: Assign different default cache sizes to each tag. Merge pull request #87 from JettHu/main feat: add a lru cache group by tag fix: cache_clear error feat: allow edit of the settings for the LRU Cache in ui. feat: add a lru cache group by tag fix: LoadImagesFromDirBatch - missing masks return. feat: Change Latent Batch Size (Inspire)

ComfyUI InstantID (Native Support)

Native [a/InstantID](https://github.com/InstantID/InstantID) support for ComfyUI. This extension differs from the many already available as it doesn't use diffusers but instead implements InstantID natively and it fully integrates with ComfyUI. Please note this still could be considered beta stage, looking forward to your feedback.

e9cc7597b2a7cd441065418a975a2de4aa2450df

update sponsors align attention patch with ipadapter fix regression fix an oopsie align the attention with ipadapter update timestepping to the new comfyui code fix compatibility with IPAdapter add combine embeds option Create FUNDING.yml fix compatibility with new IPAdapter allow batches of kps images, fix #80

ComfyUI_IPAdapter_plus

ComfyUI reference implementation for IPAdapter models. The code is mostly taken from the original IPAdapter repository and laksjdjf's implementation, all credit goes to them. I just made the extension closer to ComfyUI philosophy.

417d806e7a2153c98613e86407c1941b2b348e88

small fixes and cleanup add compatibility with ip2p remove layer weights fix regression add style and compostion transfer to SD1.5 prevent errors with fp8 minor bug fixes update sponsors add style and composition node readme update update readme Merge pull request #377 from sanguivore-easyco/faceanalysis-link-fix Update README FaceAnalysis link Update README FaceAnalysis link add composition weight type, small performance optimization add unified loader for community models disable noise for FaceID model add simple weight types to the basic IPAdapter node add github sponsorship Create FUNDING.yml doc fixes formatting error added support for SDXL portrait in the unified loader add experimental style transfer weight type (sdxl) unified loader support for light v1.1 model fix custom mask in tiled batch fix prepimage pad take2 fix prepimage pad fix lora and insightface loading in the unified loader add link to video tutorial add embeds scaling typo fix the attn mask for the tiled ipadapter typo fallback for old torch versions fallback for old torch versions fix clipvision auto detection update weight types workflow complete code rewrite. there will be blood fix timestepping on windows?

KJNodes for ComfyUI

Various quality of life -nodes for ComfyUI, mostly just visual stuff to improve usability.

7033cf2dfc636259219bd202db9cc33c6100b2a9

Update nodes.py VRAM debug node partial rollback Update nodes.py Menu settings updates Update help_popup.js bit smaller close button Update help_popup.js More descriptions Some string nodes Update nodes.py Support latest pillow cleanup Big documentation update Added some js code (thanks melMass) to allow help popups on the nodes, and initial documentation on some nodes. Update README.md Merge branch 'main' of https://github.com/kijai/ComfyUI-KJNodes Update nodes.py Merge pull request #38 from djbielejeski/main BatchCropFromMaskAdvanced: Fixing bounding boxes being bigger than th… Merge branch 'pr/40' Add fill holes option to GrowMaskWithBlur Merge branch 'kijai:main' into widget-to-string_documentation add note on changing node id Add CameraPoseVisualizer BatchCropFromMaskAdvanced: Flipping our if statement to clean up the git-diff. BatchCropFromMaskAdvanced: Fixing CenterCrop, handling empty masks. add documentation of WidgetToString node to README Rename 2024-04-03 20_49_29-ComfyUI.png to 2024-04-03_20_49_29-ComfyUI.png add images used in docs for WidgetToString node Update nodes.py BatchCropFromMaskAdvanced: Fixing bounding boxes being bigger than the input images when using `crop_size_mult` Multiline text mask Better font selection Update nodes.py Update nodes.py Update nodes.py Add random noise option to InjectNoiseToLatent -node Update nodes.py sigma experimenting Fix a bug that causes comfy to hang Update nodes.py Merge pull request #29 from spacepxl/main improved intrinsic lora postprocessing changed intrinsic lora postprocessing: depth uses max instead of desaturate, normals use normalize instead of clamp Update nodes.py Cleanup Add Superprompt test node https://huggingface.co/roborovski/superprompt-v1 Proper resadapter patcher Add LoadResAdapterNormalization For loading the normalization unet for: https://github.com/bytedance/res-adapter Merge pull request #26 from yvann-ba/incremental_expandrate_Int-to-float Change incremental_expandrate to float in GrowMaskWithBlur for smoother animations

ComfyUI-layerdiffuse (layerdiffusion)

ComfyUI implementation of [a/LayerDiffusion](https://github.com/layerdiffusion/LayerDiffusion).

151f7460bbc9d7437d4f0010f21f80178f7a84a6

ComfyUI Layer Style

A set of nodes for ComfyUI it generate image like Adobe Photoshop's Layer Style. the Drop Shadow is first completed node, and follow-up work is in progress.

4808f006676a7ca8a5f51cb49e337c86c89ba46a

commit AutoBrightness node fix bug of CreateGradientMask CreateGradientMask node add center option commit GetColorToneV2 and ImageRewardFilter nodes, add VITMatte(local) method of Ultra nodes. update readme fix 'argument of type 'Part' is not iterable' of PromptTagger, PromptEmbellish update repair_dependency_list.txt commit HDR Effect node update readme commit CropBoxResolve node add repair_dependency_aki.bat update repair_dependency_list.txt update readme commit repair_dependency.bat remove attribute OUTPUT_NODE of all nodes fix bug of PersonMaskUltra commit BiRefNetUltra node fix bug of Ultra nodes, ExtendCanvas update readme commit ImageAutoCropV2 node adjust Ultra nodes default range to 6 fix bug of MaskGradient(white line on bottom and right side) CropByMask and V2 nodes is forced to size in multiples of 8 fix mediapipe model path could not config with extra_model_paths fix bug of LayerColor nodes lost alpha commit ImageHub node Merge branch 'main' of https://github.com/chflame163/ComfyUI_LayerStyle commit ImageHub node Merge pull request #37 from xingren23/main optimize load time, lazy import lazy load lazy load commit TextJoin node update readme fix bug of wget not being imported update readme image commit PromptEmbellish node fix bug of Ultra nodes

ComfyUI-Manager

ComfyUI-Manager itself is also a custom node.

8a330ccc0a9836ae2203fc2f8117c81925f7c363

update DB update DB update DB fix: button size update DB add new node about ComfyUI_ChatGLM_API (#550) * Update custom-node-list.json * Update custom-node-list.json update DB update DB Update custom-node-list.json (#549) update DB update DB update DB update DB update DB update DB update DB feat: add 'restart button' into Manager menu update DB ComfyUI-Open-Sora-Plan (#547) update DB update DB update DB add ComfyUI-Debug (#545) ComfyUI Workflow Encrypt custom nodes (#544) update DB Update custom-node-list.json (#543) Change of ownership of this node update DB update DB update DB Add ComfyUI Nich Utils to node list (#541) update DB update DB Fixed typo (#540) update DB update DB script patch Update custom-node-list.json (#539) feat: custom node list - sorting feature for author/title update DB update DB fix: scanner - invalid cache expiration logic fix: fallback mode for missing distutils update DB update DB update hangover3832 nodes (#531) * update hangover3832 nodes * update lists update script update DB Update custom-node-list.json (#537) fix: try install 'distutils' when distutils package is missing afaik, distutils is a basic package https://github.com/ltdrdata/ComfyUI-Manager/issues/536 fix requirements update DB update DB A quick fix to ensure that the filter, search, and sorting can work together (#534) scanner patch fix: invalid check logic of rate limit improve: cache expiration time version marker update DB Add GitHub stats for custom nodes (#533) * Add GitHub stats fetching feature - Added PyGithub package to requirements.txt for GitHub API interaction - Updated .gitignore to ignore github-stats-cache.json - Produced github-stats.json for storing GitHub stats - Modified scanner.py to include the GitHub stats fetching process * Add sorting for 'GitHub Stars' and 'Last Update' columns - Fetch 'GitHub Stars' and 'Last Update' data when getting the custom node list. - Display 'GitHub Stars' and 'Last Update' information in the UI. - Implement sorting functionality for these two columns, allowing users to sort both in descending and ascending order. * fix: scanner - prevent stuck when exceed rate limit --------- Co-authored-by: Dr.Lt.Data <dr.lt.data@gmail.com> update DB improve: black list feature - check version - support `downgrade_blacklist` in `config.ini` https://github.com/ltdrdata/ComfyUI-Manager/issues/515 update README update DB update DB update DB update DB Update custom-node-list.json (#528) adding the MokkaBoss1 repository following requested ammendments: 1) remove pycache 2) update folder structure update DB update DB update DB Update custom-node-list.json for sd-ppp (#527) update DB Update custom-node-list.json (#526) my group of nodes for manipulating text and integers update DB Update custom-node-list.json (#524) update DB update DB Add hay86/ComfyUI_Dreamtalk node (#523) https://github.com/hay86/ComfyUI_Dreamtalk update DB Share to esheep (#517) * share to esheep * enable_cors_header * Chiness to English * remove chiness * rearrange order. * version marker --------- Co-authored-by: huyunan <huyunan@bilibili.com> Co-authored-by: Dr.Lt.Data <dr.lt.data@gmail.com> Co-authored-by: Dr.Lt.Data <128333288+ltdrdata@users.noreply.github.com> update DB Merge pull request #522 from nazgut/main update custom-node-list Merge pull request #521 from kijai/main Add Geowizard -node Merge pull request #520 from chaojie/patch-17 Update custom-node-list.json update custom-node-list Add Geowizard -node https://github.com/kijai/ComfyUI-Geowizard https://github.com/fuxiao0719/GeoWizard Update custom-node-list.json update DB Merge pull request #519 from chaojie/patch-16 Update custom-node-list.json Update custom-node-list.json update DB update DB Merge pull request #516 from alisson-anjos/main Add LLaVa-Describer custom nodes Add –LLaVa-Describer custom nodes update DB update DB update DB improve: collapse deprecation message update DB update DB Merge pull request #513 from kijai/main Add Depth-FM node and models Merge branch 'main' into main Merge pull request #512 from julien-blanchon/patch-5 Add monster-labs - Controlnet QR Code Monster v1 For SDXL Merge pull request #511 from daxcay/main New Plugin ComfyUI-JDCN update DB Merge pull request #510 from Jannchie/main feat: add ComfyUI-J, Jannchie's diffusers based nodes Add Depth-FM node and models https://github.com/kijai/ComfyUI-depth-fm https://huggingface.co/Kijai/depth-fm-pruned Add monster-labs - Controlnet QR Code Monster v1 For SDXL Revert "Revert "Merge branch 'main' of https://github.com/daxcay/ComfyUI-Manager"" This reverts commit 89ed96f83f7ccde2d67dfd8833bc76de89ffebd1. Merge branch 'main' of github.com:Jannchie/ComfyUI-Manager feat: add ComfyUI-J, Jannchie's diffusers based nodes Revert "Merge branch 'main' of https://github.com/daxcay/ComfyUI-Manager" This reverts commit 16fcb3a7b1e3f37af826452e71d4cb0b7d3d4c61, reversing changes made to bb7b13c1f544fb9b4190fea0007ae0a54fbe89ef. Merge branch 'main' of https://github.com/daxcay/ComfyUI-Manager Update custom-node-list.json ComfyUI-JDCN update DB Merge pull request #509 from julien-blanchon/patch-4 Add ZHO-ZHO-ZHO/ComfyUI-BRIA_AI-RMBG node Merge pull request #507 from julien-blanchon/patch-2 Update layerdiffusion name Add ZHO-ZHO-ZHO/ComfyUI-BRIA_AI-RMBG node Update layerdiffusion name update DB Merge pull request #505 from ZHO-ZHO-ZHO/ComfyUI-Manager ADD APISR IN COMFYUI Update custom-node-list.json update DB Merge pull request #503 from chaojie/patch-15 Update custom-node-list.json Update custom-node-list.json update DB Merge pull request #502 from KarryCharon/add-comfyui-cup add comfyui-cup repo add comfyui-cup repo update DB update DB Merge pull request #501 from nazgut/main add Image Text Overlay Node to the custom-node-list update DB add Image Text Overlay Node to the custom-node-list update DB Merge pull request #496 from kijai/main Add DynamiCrafterWrapper node and models Add DynamiCrafterWrapper node and models update DB Merge pull request #483 from Shadetail/main Added Eagleshadow Custom Nodes entry to custom-node-list.json update DB Merge pull request #495 from kijai/main Add ComfyUI-SUPIR nodes Update custom-node-list.json Changed the files entry for Eagleshadow Nodes to point to repo url instead of file url. Add ComfyUI-SUPIR nodes Wrapper nodes to use SUPIR upscaling process in ComfyUI fix: ComfyUI update - robust patch https://github.com/ltdrdata/ComfyUI-Manager/issues/489 update DB update DB fix typo: https://github.com/ltdrdata/ComfyUI-Manager/issues/490 Merge pull request #491 from MarkoCa1/main text node update DB Merge pull request #494 from ForeignGods/main Added Mana-Nodes to custom-node-list.json Merge pull request #492 from madtunebk/main Added ComfyUI-ControlnetAux node entry to custom-node-list.json Update custom-node-list.json Update custom-node-list.json text node Update custom-node-list.json Changed Eagleshadow Nodes install_type to git-clone fix: invalid detection of failed import - reflect changed ComfyUI log system https://github.com/ltdrdata/ComfyUI-Manager/issues/480 update script update script update DB update DB Merge pull request #485 from chaojie/patch-14 Update custom-node-list.json Merge pull request #482 from chaojie/patch-13 Update custom-node-list.json Update custom-node-list.json Update custom-node-list.json Added Eagleshadow Custom Nodes entry to custom-node-list Update custom-node-list.json improve: pip handling - prevent downgrade `torch, torchsde, torchvision, transformers, safetensors, kornia` update DB Merge pull request #479 from cozymantis/cozy-utils Add Cozy utils update DB Merge pull request #478 from cozymantis/cozy-reference-pose-gen Add Cozy Reference Pose nodes update DB Merge pull request #477 from cozymantis/cozy-human-parser Add Cozy Human Parser nodes Merge pull request #476 from rvorias/main remove anything-v3.0 Add Cozy utils Add Cozy Reference Pose nodes Add Cozy Human Parser nodes remove anything-v3.0 upstream huggingface model does not exist anymore update DB

ComfyUI Noise

This extension contains 6 nodes for ComfyUI that allows for more control and flexibility over the noise.

afb14757216257b12268c91845eac248727a55e2

Merge pull request #28 from ltdrdata/fix/compatibility unsampler - compatibility patch unsampler - compatibility patch https://github.com/comfyanonymous/ComfyUI/commit/0542088ef895b4825df80fd3babf91513441af65 Merge pull request #13 from ltdrdata/fix/unsampler-noise-mask Fix: Unsampler crash when using a noise mask

comfyui-portrait-master

ComfyUI Portrait Master. A node designed to help AI image creators to generate prompts for human portraits.

df5c191eb70eab297a4cad823f2c2976e7ce884d

ComfyUI-RAVE

Unofficial ComfyUI implementation of [a/RAVE](https://rave-video.github.io/)

92d19be86cdcec198088757c07873919d3c8e1b1

ReActor Node for ComfyUI

The Fast and Simple 'roop-like' Face Swap Extension Node for ComfyUI, based on ReActor (ex Roop-GE) SD-WebUI Face Swap Extension

05bf228e623c8d7aa5a33d3a6f3103a990cfe09d

Merge branch 'main' into evolve UPDATE: GPEN-BFR-512 and RestoreFormer++ support FR: #69, #175 UPDATE: Image count status during restoration FIX: Typo UPDATE: Workflow url added FIX: image width UPDATE: "What's new" section VersionUP (0.4.2 beta1) UPDATE: "Build Blended Face Model" Node VersionUP (beta passed) VersionUP (0.4.1 beta12) UPDATE: URLs UPDATE: Credits section FIX: Retinaface error when device=CPU Issue #240 Merge branch 'main' into evolve FIX: Interruption issue when batch Issue #188

segment anything

Based on GroundingDino and SAM, use semantic strings to segment any element in an image. The comfyui version of sd-webui-segment-anything.

ab6395596399d5048639cdab7e44ec9fae857a93

Merge pull request #54 from frantic/patch-1 Avoid installing dependencies on every run Avoid installing dependencies on every run It looks like the `install.py` is imported from `__init__.py`, which means every time this plugin is loaded, it'll trigger a bunch of `pip install`s. feat: add IsMaskEmpty node Signed-off-by: storyicon <storyicon@foxmail.com>

ComfyUI-SUPIR

Wrapper nodes to use SUPIR upscaling process in ComfyUI

49afedaddde27ca1c2092abccb5930a10112d5f0

Description for sampler Merge branch 'main' of https://github.com/kijai/ComfyUI-SUPIR Initial DESCRIPTIONs Update README.md Update nodes_v2.py clip decode on gpu Create LICENSE Delete LICENSE Update LICENSE Tiled sampler consequential runs workaround Copy the conds so they are not permanently modified by the Tiled samplers update example Update nodes_v2.py Update nodes_v2.py Update nodes_v2.py Better xformers check Now relies in the comfy xformers check and can thus be disabled with the command line argument --disable-xformers cleanup Update nodes_v2.py Smarter model loading and support comfy latents - Less spiky memory usage when using v2 model loader node - Support latents from other comfy nodes, when using latents from SUPIR nodes the behaviour is same as before: fully random noise fix decoder dtype clip decoder output Update README.md Make model loader node without sdxl_model selection for clarity Support using comfy model loading, including loras These inputs are optional, when used the sdxl_model dropdown is ignored, I don't want to remove it as of yet as it would break old workflows. Update nodes_v2.py

UltimateSDUpscale

ComfyUI nodes for the Ultimate Stable Diffusion Upscale script by Coyote-A.

b303386bd363df16ad6706a13b3b47a1c2a1ea49

Add __init__.py to avoid conflicts Potential fix for conflicts Change default denoise to 0.2 to avoid confusion

ComfyUI-VideoHelperSuite

Nodes: VHS_VideoCombine. Nodes related to video workflows

a92db630674044770a2da2b57054a79568040c63

Use case insensitive counter checking Windows has unusual behaviour for case sensitivity in file paths. Files and folders retain the case used when initially created, but path resolution is case insensitive. Since the previous counter code did not account for this, setting a filename_prefix in Video Combine with case different from a previous execution would fail to include prior executions nad produce a counter and filename that resolve to an already existant file, throwing an error. To account for this, the counter code has been made case insensitive. See #190 Force migrate batch_manager inputs to meta_batch When loading graph data, the "name" field on inputs is overwritten to the name data saved in the workflow. As old workflows utilizing these meta batches have the old batch_manager name, the input is loaded to it's old name which would cause an error on execution. Instead, quick javascript code has been added to manually force the update of these inputs. Always display ffmepg formats, raise error instead While it made sense to quietly proceed when io nodes were rolled into animate diff, the process of hiding unusable formats has caused frequent confusion in addition to being a logic path that should not be formally supported (imageio-ffmpeg is in requirements.txt so a lack of ffmpeg is best considered an invalid install.) While an angry warning was displayed on boot, this error message is frequently missed by end users. Now, all format options are displayed and, if an unusable format is selected, an error is raised which provides a list of options for how to install ffmpeg Additionally, an extra search path was added to run an ffmpeg executable that is placed in the base ComfyUI directory. For those struggling with virtual environments or the system path, this provides a third installation option that works regardless of os, or venv and requires no need for external configuration or environment variables. See #188, among others. Swap Batch Manager name to Meta Batch Manager. The reuse of the word batch in different contexts cuases a good bit of confusion. The batching performed by the batch manager node has been renamed as "meta batch" to help alleviate this confusion. Remove try/finally block from cv_frame_generator See #185 Fix missing total_frames in Load Video Several additional information variables were added for VideoInfo that need to be saved and passed. total_frames was ommited from one of the tuples resulting in errors when using batch_manager and has been fixed Resolves #179 Use iterators internally for Video Combine Reduces the need for the converted image data to exist entirely in memory for a 20% reduction in memory used by VideoCombine Removes the allocation of a new array for pingpong. Allows for for processing of input images which are not tensors. Resolves #176 Swap frame_rate on VideoCombine to float. As video info produces a float for it's loaded frame rate, and non_integer frame_rates are reasonably obtainable by using select_every_nth, frame_rate has been changed on VideoCombine so that the loaded frame_rate of Video info may be wired. Respect select_every_nth in VideoInfoLoaded feat: return info for both source and loaded video info feat: add video info node Merge pull request #159 from kijai/main Batched vae encode fix for latest comfyui changes

ComfyUI-Video-Matting

A minimalistic implementation of [a/Robust Video Matting (RVM)](https://github.com/PeterL1n/RobustVideoMatting/) in ComfyUI

178bf956ddb817d065b1b073ec04582ad60335bb

Masquerade Nodes

This is a node pack for ComfyUI, primarily dealing with masks.

69a944969c29d1c63dfd62eb70a764bceb49473d

WAS Node Suite

A node suite for ComfyUI with many new nodes, such as image processing, text processing, and more.

6c3fed70655b737dc9b59da1cadb3c373c08d8ed

ComfyUI-3D-Pack

An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.) NOTE: Pre-built python wheels can be download from [a/https://github.com/remsky/ComfyUI3D-Assorted-Wheels](https://github.com/remsky/ComfyUI3D-Assorted-Wheels)

abb4532d1b7fe057b6153098ec11128d27ce8810

Derfuu_ComfyUI_ModdedNodes

Automate calculation depending on image sizes or something you want.

2bb8d533b5cdc7bb409a2900e5318b4f546e9c2b

moved all scale methods into scale_methods variable; fixed LatentScale_Ratio node fixed CONDITIONING field name Debug node get additional output to be able for use in-line with other nodes; Removed(commented) "Tuples" nodes; Removed "TUPLES" type from "Get size" nodes; (DON'T FORGET TO REPLACE THEM IF THEY'RE PERSISTS IN YOUR WORKFLOW) Types moved into their own class with class methods and default parameters instead of just tuples with strings and dicts; Added "Logic node" (>, <, =, AND, OR, XOR); (idk why i did this one, but got an idea that with object recognition models to count objects and correct them in next iterations would be not so bad idea as i think. Or something like this) changed README.md to current state of this repo replaced old debug nodes with single "To text (Debug)" node, which shows stringified data in node widget and also prints it's value into console. added "Shortest" option for latent upscaler removed debug print fixed wrong image output size in Image scale to side preparing for adding custom js nodes... - moved all python scripts into /pyscripts/ folder - added all /pyscripts/**__init__.py into gitignore Merge pull request #18 from daniabib/image-to-scale-shortest Add "Shortest" option to Image scale to side Add "Shortest" option to Image scale to side Added: scale by longest side to image and latent nodes, Added: Tuple multiply node Fixed: Int node max values, added .idea to gitignore

Facerestore CF (Code Former)

This is a copy of [a/facerestore custom node](https://civitai.com/models/24690/comfyui-facerestore-node) with a bit of a change to support CodeFormer Fidelity parameter. These ComfyUI nodes can be used to restore faces in images similar to the face restore option in AUTOMATIC1111 webui. NOTE: To use this node, you need to download the face restoration model and face detection model from the 'Install models' menu.

67f90bc6be976fb58169866155346b0da13bebee

Merge pull request #18 from gkiryaziev/fix-import Fix issue No module 'named model_management' Fix issue No module 'named model_management' Merge pull request #9 from clindstedt/patch-1 Prevent incompatibility with nighly build / dev versions of torch

rgthree's ComfyUI Nodes

Nodes: Seed, Reroute, Context, Lora Loader Stack, Context Switch, Fast Muter. These custom nodes helps organize the building of complex workflows.

79f5fea259cae29dd934d1eb7be378fee2777aa2

remove debug print Adds the (discouraged) ability to pass '-1' to the Seed node's server impl and use/save a new random seed. Addresses #188 Keep power prompt lora logs silent when disabled. New Node: Power Lora Loader! Change seed node from swapping actual index value with just manipulating prompt sent to server. Fixes #185 and #169 My handy update script. Fix case for super-fast debugging workflow. Rewrite seed widget using the RgthreeBaseServerNode. Also, change timing to the serialization/resetting to better handle batches. Maybe helps #169 Fix seed to accomdate previous comfyui breaking serialize signature. Remove build prompts_service Missing? Pulling in some generic updates from dev branches. Add the Group Header toggles to README. New Feature: Add quick mute and/or bypass icon toggles to group headers for one-click toggling when viewing groups. Off by default, turn on in rgthree-comfy's settings. Don't recalculate group nodes if a group is actively moving. Fixes #181 Fix relay setting wrong mode if overriding to 'nothing'. Adds auto nesting support for nested directories. Fixes #177 Merge branch 'main' of https://github.com/rgthree/rgthree-comfy

Face Analysis for ComfyUI

This extension uses [a/DLib](http://dlib.net/) to calculate the Euclidean and Cosine distance between two faces. NOTE: Install the Shape Predictor, Face Recognition model from the Install models menu.

2aae576a3b48e3d96dc82fcd74704d81793bb0dc