ReActor works much better for me, when I inpaint the faces. An idea for micro-facials-models. For demanding projects that require top-notch results, this workflow is your go-to option. I'm using the comfyui reactor node, but I keep getting this error, so I can't use it. I was testing the face swap and noticed that i have no options loaded for face-Restore-model. 3 there was an option to stop the workflow if the source face does not match a specific gender. Last update slows down worflow. Install the ComfyUI dependencies. I now want to change the face in an image to a video, but there are many different faces in this video. Contribute to kijai/ComfyUI-LivePortraitKJ development by creating an account on GitHub. Just put . It was very confusing and I didn't understand it until I deleted the node and replaced it with a new one. Sign up for a free GitHub account to open an issue and contact its maintainers and the community. The upscaler in ReActor is set to 4x-UltraSharp. Restore Face -> 2. Everything about ComfyUI, including workflow sharing, resource sharing, knowledge sharing, tutorial sharing, and more. This is a custom node that lets you use TripoSR right from ComfyUI. highly experimental—expect things to break and/or change frequently or not at all. 1 will enforce this behaviour change. Then merge all 4 face models together into one. Sytan SDXL ComfyUI: Very nice workflow showing how to connect the base model with the refiner and include an upscaler. I have read the instruction carefully; I have searched the existing issues; I have updated the extension to the latest version; What happened? i am trying to run a workflow on Touchdesigner using Reactor Faceswap, the console log level causing it to not working by throwing following output: ComfyUI Manager: Plugin for CompfyUI that helps detect and install missing plugins. I have read the instruction carefully; I have searched the existing issues; I have updated the extension to the latest version; What happened? I tried installing reactor node with ComfyUI-ZLUDA, the installation process was ok, however after creating reactor node and loading img, I performed queue prompt and the comfyui manager reported the following error: First, confirm. First, confirm. Функции маски лица теперь доступна и в версии для Комфи, просто добавьте нод You signed in with another tab or window. i have done this already and replaced the file several times, but it still doesn't work :( i just can't select it in the node and it only shows me "undefined". You signed out in another tab or window. but those options: face_restore_visability Codeformer_weight. Notably, the outputs directory defaults to the --output-directory argument to comfyui itself, or the default path that comfyui wishes to use for the --output-directory . Sysinfo. Find and fix vulnerabilities Nov 9, 2023 · **Hi everyone, I just got into faceswap and have a quick question on time taken to do a video face swap. py --windows-standalone-build ** ComfyUI start up time: 2023-11-27 17:43:15. thirdparty. 0. More than 100 million people use GitHub to discover, fork, and contribute to over 420 million projects. here is the workflow what I want to use you can see the they are different ` F:\ComfyUI_windows_portable>. Sep 8, 2023 · Does anyone have an img2img workflow? Because the one in the other thread first generates the image and then changes the two faces in the flow. Upscale (-Uncheck- if you want vice versa)" option, but the aliasing remains. Automate your software development practices with workflow files embracing the Git flow by codifying it in your repository. Your workflow 5) Batch Face Swap - ReActor [Experimental]. How can I solve it? First, confirm I have read the instruction carefully I have searched the existing issues I have updated the extension to the latest version What happened? I created a simple workflow with face swap using a face model and source image. A possible replacement is to upgrade to a newer version of torchsde or contact the author to suggest that they release a version with a conforming dependency specifiers. This doesn't happen when running the same workflow via Runpod. I think it is because not needed models are loaded. In the current 0. Nov 9, 2023 · Hi, I just installed Reactor node 3. Any idea what might be the issue? Sep 27, 2023 · Your workflow. Reload to refresh your session. bat, Insightface and ReaCtor has you suggested and now its working not with cuda 12. When dealing with the character on the left in your animation, set both the Source and Input Face Index to 0. Launch ComfyUI by running python main. I am an noob to all of this and I am working on a film project for school that involves swapping cartoon faces/heads. Start by creating 4 separate reactor face models using the comfyui node, 1 from each face image. Sep 4, 2023 · I initially had a problem: After git pull updating, the node (in an existing workflow) had the new gender fields, but the two inputs kept their original legends but had their new positions which caused my wiring to fail. I have been using the Reactor fast face swap node with the inswapper_128. Where as everyone else can seem to see them. I am not exactly a python expert, but I am pretty sure that when it gets imported, comfyui-reactor-node adds itself to the front of pythons (process global) module lookup path. 8:db85d51, Feb 6 2024, 22:03:32) [MSC v. onnx (it's the only one that works for me) In some renders I only want to change the face, not the hair or hat, but the selection area is often too big or is feathered very much so the hair or hat is partly changed. . Jun 21, 2024 · [START] Security scan [DONE] Security scan # # ComfyUI-Manager: installing dependencies done. Dec 18, 2023 · Saved searches Use saved searches to filter your results more quickly Nov 4, 2023 · Feature description. Instant dev environments Oct 31, 2023 · First, confirm I have read the instruction carefully I have searched the existing issues I have updated the extension to the latest version What happened? ComfyUI is up to date, this is the portable version. This instructs the Reactor to, "Utilize the Source Image for substituting the left character in the input image. If you have another Stable Diffusion UI you might be able to reuse the dependencies. 8 (tags/v3. Input "input_image" goes first now, it gives a correct bypass and also it is right to have the main input first; You can now save face models as "safetensors" files (ComfyUI\models\reactor\faces) and load them into ReActor implementing different scenarios and keeping super lightweight face models of the faces you use: More than 100 million people use GitHub to discover, fork, and contribute to over 420 million projects. Jan 14, 2024 · Let's say you want to use 4 face images as inputs for the reactor face model. During Reactor Node phase, it is Swap / Basic workflow 💾. Contribute to cdb-boop/ComfyUI-Bringing-Old-Photos-Back-to-Life development by creating an account on GitHub. exe -s ComfyUI\main. 关于ComfyUI的一切,工作流分享、资源分享、知识分享、教程分享等 - xiaowuzicode/ComfyUI-- I am sorry but just to be clear i uninstalled the cuda 12. mesh. e. cython' (unknown location) Where [comfyui-browser] is the automatically determined path of your comfyui-browser installation, and [comfyui] is the automatically determined path of your comfyui server. 11. The main faceswap core of ReActor, Roop, FaceFusion, FaceSwapLab - is Insightface library which works only with insightface models (both analysis and faceswap) like "inswapper_128" "inswapper_128" - is the only one faceswap model available for free SimSwap models don't work with Insightface even converted to ONNX format GitHub community articles Gourieff / comfyui-reactor-node Public. ComfyUI nodes for LivePortrait. As issues are created, they’ll appear here in a searchable and filterable list. Find and fix vulnerabilities Codespaces. I have tried everything and it shows up in the Comfyui folder but when I launch Comfyui the ReActor button is no where to be found. log Prestartup times for Updating. please consider forking this repository! Nov 6, 2023 · ImportError: cannot import name 'mesh_core_cython' from 'insightface. 4 it just does not swap the face, but still continues the workflow. I upgraded to the latest Cog, however my workflow doesn't work properly using the new Reactor Nodes: It runs, but the face in the resulting image is blacked out. \python_embeded\python. {'model_path': 'D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-reactor-node\models\insightface\models\buffalo_l\1k3d68. The idea would be to create a complementary node in ReActor that takes in an image folder and runs through each image to complete a full facial model (with different camera angles, different lighting, etc. Hello, I'm not good at English, so I'm asking questions using a translator. 7 ". Go to the ComfyUI\custom_nodes directory. Relevant console log. 8, installed the old Comfyui 11. Dec 13, 2023 · You signed in with another tab or window. Your workflow Welcome to issues! Issues are used to track todos, bugs, feature requests, and more. ComfyUI ControlNet aux: Plugin with preprocessors for ControlNet, so you can generate images directly from ComfyUI. Oct 13, 2023 · i've been using ReActor for a while using auto1111, but first time cracking at it in comfyui, for whatever reason, my face always ends up blurry, if i take reactor out, then it looks clear and sharp, I have attached a copy of my workflow if anyone is gracious enough to assist. Explore its features, templates and examples on GitHub. om 。 Cheers, yeah, now the gender-identification is both improved and simplified slightly by Oceanwave;s suggestion, the only feature request would be to integrate the masking and recomposition phases into a single entry point for the Reactor node. onnx'} Sep 3, 2023 · I initially had a problem: After git pull updating, the node (in an existing workflow) had the new gender fields, but the two inputs kept their original legends but had their new positions which caused my wiring to fail. It combines advanced face swapping and generation techniques to deliver high-quality outcomes, ensuring a comprehensive solution for your needs. cython' (unknown location) Cannot import C:\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-reactor-node module for custom nodes: cannot import name 'mesh_core_cython' from 'insightface. tldr ReActor uses ComfyUI\custom_nodes\comfyui-reactor-node\models instead of using ComfyUI/models First, confirm I have read the instruction carefully I have searched the existing issues I have updated the extension to the latest version What happened? I have ComfyUI with the Manager and a bunch of other extensions/models etc all dow Sep 30, 2023 · Gourieff / comfyui-reactor-node Public. I try this and it works until I quit First, confirm. Usually the flow on a production app is that first the user uploads his image, and then later generates something else that requires face swapping. Host and manage packages Follow the ComfyUI manual installation instructions for Windows and Linux. ComfyUI is a powerful and modular GUI for diffusion models with a graph interface. I'm not sure how to do this in ComfyUI so I did it in the Checkpoint Merger tab in A1111. 4. This was the base for my Nov 27, 2023 · I am sure I have put the model in ComfyUI\models\facerestore_models. in ReActor - Fast Face Swap 0. I have read the instruction carefully; I have searched the existing issues; I have updated the extension to the latest version; What happened? Hi, I don't know if this issue is the same reported here: #176 Feb 15, 2024 · I also just encountered this issue. Below is my setup on comfyUI It is a 2 minute video. Oct 28, 2023 · Fast and Simple Face Swap Extension Node for ComfyUI - Issues · Gourieff/comfyui-reactor-node Dec 6, 2023 · You signed in with another tab or window. This allows to create ComfyUI nodes that interact directly with some parts of the webui's normal pipeline. sh script from this Repo to the ComfyUI\custom_nodes directory and run it when you need to check for updates. Jul 2, 2024 · First, confirm I have read the instruction carefully I have searched the existing issues I have updated the extension to the latest version What happened? Unable to run Steps to reproduce the problem Your workflow Sysinfo comfyui Relevan Host and manage packages Security. Instant dev environments Mar 21, 2024 · First, confirm I have read the instruction carefully I have searched the existing issues I have updated the extension to the latest version What happened? I installed Visual Studio 2022 and installed ReActor through ComfyUI Manager. Gourieff / comfyui-reactor-node Public. 2. 5 has a non-standard dependency specifier numpy > =1. 2. 1-b8 in ComfyUI. ComfyUI workflow. I have read the instruction carefully; I have searched the existing issues; I have updated the extension to the latest version; What happened? I have not figured out the very reason why reactor node would fail to load giving an "import failed" remark and an option to fix it in the custom nodes manager. Entra en ComfyUI Manager y selecciona "Import Missing Nodes" y dentro los seleccionas todos y los instalas. Notifications I think you use some workflow that requires the node "FaceRestoreWithModel Fast and Simple Face Swap Extension Node for ComfyUI - Gourieff/comfyui-reactor-node May 28, 2024 · First, confirm I have read the instruction carefully I have searched the existing issues I have updated the extension to the latest version What happened? Only when I select GFPGAN for face_restore_model, I get gray noise in the output i I have not figured out the very reason why reactor node would fail to load giving an "import failed" remark and an option to fix it in the custom nodes manager. I also tried "1. git clone comfyui-reactor-node repo to custom_nodes/ launch ComfyUI; Sysinfo. dataleveling / ComfyUI-Reactor-Workflow Public Mar 4, 2024 · You signed in with another tab or window. Hello, I'd like to know if it's possible to build a complex facial model in safetensor. And since I find these ComfyUI workflows a bit complicated, it would be interesting to have one with a simple face swap with a facerestore. I understood that they should have been included with version 3. This software is meant to be a productive contribution to the rapidly growing AI-generated media industry. Is there a way to get this "stop workflow" feature back? Gourieff / comfyui-reactor-node Public. face3d. pip 24. (early and not Nov 17, 2023 · Did you delete the existing ReActor Node (from your workflow) and add it again before run the query? FIX Nuked88/comfyui-reactor-node#1. Open ComfyUI Clear Workflow Add ReActor Node. First, confirm I have read the instruction carefully I have searched the existing issues I have updated the extension to the latest version What happened? Can't load reactor node in ComfyUI. You switched accounts on another tab or window. json. Left image is coming from the ksampler, Si te salen nodos en rojo y errores al cargar el workflow, es normal, quizá no tengas todos los nodos necesarios. 0 with seemingly no errors on ComfyUI Portable. Disclaimer. Contribute to yuyou-dev/workflow development by creating an account on GitHub. 054757 ** Platform: Windows ** Python version: 3. Steps to reproduce the problem. when i delete the node and then place a new node it shows "null" but either then i can't select anything there :( my path is: W:[-Ai-]\ComfyUI_Base\ComfyUI\models\insightface - it seems like something is blocking the node to get to the Jul 15, 2024 · You signed in with another tab or window. ** ComfyUI startup time: 2024-06-21 13:01:55. Windows 10 Nvidia 4070 ti Chrome. " For the character positioned on the right, adjust the Source Index to 0 and the All the images in this repo contain metadata which means they can be loaded into ComfyUI with the Load button (or dragged onto the window) to get the full workflow that was used to create the image. I checked the task manager and it seems that the GPU is not being utilized. exe ** Log path: D: \p\C omfyUI \c omfyui. Automate any workflow Packages. 19. 848555. 👏 欢迎来到我的 ComfyUI 工作流集合地! 为了给大家提供福利,粗糙地搭建了一个平台,有什么反馈优化的地方,或者你想让我帮忙实现一些功能,可以提交 issue 或者邮件联系我 theboylzh@163. then in my workflow, I removed and re-added the node. *; python_version > = " 3. Please do the next: Inside the folder extensions\sd-webui-reactor run Terminal or Console (cmd) and then: git reset f48bdf1 --hard; git pull; OR First, confirm. system info: GPU : A4000 16GB vram. generative audio tools for ComfyUI. A good place to start if you have no idea how any of this works is the: ComfyUI Basic Tutorial VN: All the art is made with ComfyUI. sd-webui-comfyui is an extension for A1111 webui that embeds ComfyUI workflows in different sections of the normal pipeline of the webui. Sep 15, 2023 · While I keep my face restore models under the ComfyUI's "models" directory, having a copy of these models just so ReActor node can see them doesn't seem efficient to me. py detect_gender_source - is the gender of source face image detect_gender_input - is the gender of input image (where you need to swap the face). Open the Console and run the following command: installed requirements. Nov 15, 2023 · Nice speed @Gourieff. py i was testing my workflow and was surprised to find that the faceswapping process on my AWS EC2 instance (using an A10G) runs faster than on my RTX4090 machine. ), with a kind of incrementation of the facial model at each itteration. Input "input_image" goes first now, it gives a correct bypass and also it is right to have the main input first; You can now save face models as "safetensors" files (ComfyUI\models\reactor\faces) and load them into ReActor implementing different scenarios and keeping super lightweight face models of the faces you use: Feb 5, 2024 · First, confirm I have read the instruction carefully I have searched the existing issues I have updated the extension to the latest version What happened? Hello, I am a beginner, and I encountered a problem while importing a workflow. Relevant console log You signed in with another tab or window. Face Masking feature is available now, just add the "ReActorMaskHelper" Node to the workflow and connect it as shown below: Dec 15, 2023 · Maybe, I've to wait for a ReActor update? Steps to reproduce the problem. Input "input_image" goes first now, it gives a correct bypass and also it is right to have the main input first; You can now save face models as "safetensors" files (ComfyUI\models\reactor\faces) and load them into ReActor implementing different scenarios and keeping super lightweight face models of the faces you use: Follow the ComfyUI manual installation instructions for Windows and Linux. 2k Workflow-to Bringing Old Photos Back to Life in ComfyUI. Apr 24, 2024 · Multiple Faces Swap in Separate Images. I think what would also be useful, if you have time to implement, is a node that takes an image and outputs the embeddings. Nov 14, 2023 · Installation guides (as provided on their respective GitHub pages): ReActor: 1. Multi-container testing Test your web service and its DB in your workflow by simply adding some docker-compose to your workflow file. Merged Sign up for free You signed in with another tab or window. 1, installed the cuda 11. 1937 64 bit (AMD64)] ** Python executable: D: \p\C omfyUI \p ython_embeded \p ython. "Mean (recommended) - Average value (best result 👍)\nMedian* - Mid-point value (may be funny 😅)\nMode - Most common value (may be scary 😨)\n\n*Mean and Median will be similar if you load two images" If after git pull you see the message: Merge made by the 'recursive' strategy and then when you check git status you see Your branch is ahead of 'origin/main' by. Prestartup times for custom nodes: ReActorBuildFaceModel Node got "face_model" output to provide a blended face model directly to the main Node: Basic workflow 💾. [ReActor] - STATUS - Running v0. Feb 23, 2024 · DEPRECATION: torchsde 0. i. to have Reactor use the SEGS or Mask output to focus on just that face for that replacement. Your workflow run Hi is there any chance you can help me out installing ReActor in Comfyui. 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. Where do i find them or how do i add them now? thanks all! Oct 18, 2023 · You signed in with another tab or window. 8, made update_comfyui_and_python_dependencies. Oct 21, 2023 · my workflow is the following for A1111: I render an image in text2img, with ReActor enabled. bat or . You signed in with another tab or window. Your workflow. Gourieff / comfyui-reactor-node Star 1 . Are missing. NOTE : for the foreseeable future, i will be unable to continue working on this extension. ay tz bu bu hv pg kr ns zt ii