Comfyui workflow directory github example
Comfyui workflow directory github example. Example GIF [2024/07/23] 🌩️ BizyAir ChatGLM3 Text Encode node is released. Image-to-image workflow. The SDXL base checkpoint can be used like any regular checkpoint in ComfyUI. Install the ComfyUI dependencies. Contribute to sharosoo/comfyui development by creating an account on GitHub. Always refresh your browser and click refresh in the ComfyUI window after adding models or custom_nodes. "knight on horseback, sharp teeth, ancient tree, ethereal, fantasy, knva, looking at viewer from below, japanese fantasy, fantasy art, gauntlets, male in armor standing in a battlefield, epic detailed, forest, realistic gigantic dragon, river, solo focus, no humans, medieval, swirling clouds, armor, swirling waves, retro artstyle cloudy sky, stormy environment, glowing red eyes, blush Examples of ComfyUI workflows. Rename Create your comfyui workflow app，and share with your friends ComfyUI\models\checkpoints. CosXL Sample Workflow. Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything. json workflow file to your ComfyUI/ComfyUI-to-Python-Extension folder. You can load this image in ComfyUI to get the full workflow. 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. py file name. version of your ComfyUI workflow. txt Download aura_flow_0. . A CosXL Edit model takes a source image as input Sep 2, 2024 · 示例的VH node ComfyUI-VideoHelperSuite node: ComfyUI-VideoHelperSuite mormal Audio-Drived Algo Inference new workflow 音频驱动视频常规示例 最新版本示例 motion_sync Extract facial features directly from the video (with the option of voice synchronization), while generating a PKL model for the reference video ，The old version For your ComfyUI workflow, you probably used one or more models. It covers the following topics: The RequestSchema is a zod schema that describes the input to the workflow, and the generateWorkflow function takes the input and returns a ComfyUI API-format prompt. safetensors (10. trying it with your favorite workflow and make sure it works writing code to customise the JSON you pass to the model, for example changing seeds or prompts using the Replicate API to run the workflow You signed in with another tab or window. The vase, with a slightly curved silhouette, stands on a dark wood table with a noticeable grain pattern. Fully supports SD1. You can find the InstantX Canny model file here (rename to instantx_flux_canny. This should update and may ask you the click restart. 1. js file in that directory will be loaded by the frontend as a frontend extension # WEB_DIRECTORY = ". (I got Chun-Li image from civitai); Support different sampler & scheduler: You signed in with another tab or window. /somejs" # Add custom API routes, using router 👏 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. This repo is divided into macro categories, in the root of each directory you'll find the basic json files and an experiments directory. Check my ComfyUI Advanced Understanding videos on YouTube for example, part 1 and part 2. yaml and edit it with your favorite text editor. Reload to refresh your session. \. There is now a install. safetensors and put it in your ComfyUI/checkpoints directory. A sample workflow for running CosXL Edit models, such as my RobMix CosXL Edit checkpoint. 1GB) can be used like any regular checkpoint in ComfyUI. These are examples demonstrating how to do img2img. safetensors already in your ComfyUI/models/clip/ directory you can find them on: this link. CosXL models have better dynamic range and finer control than SDXL models. Install ComfyUI Manager on Windows. Rename extra_model_paths. ComfyUI Examples. The pre-trained models are available on huggingface, download and place them in the ComfyUI/models/ipadapter directory (create it if not Follow the ComfyUI manual installation instructions for Windows and Linux. Jupyter Notebook Dec 28, 2023 · Download or git clone this repository inside ComfyUI/custom_nodes/ directory or use the Manager. ReActorBuildFaceModel Node got "face_model" output to provide a blended face model directly to the main Node: Basic workflow 💾. example in the ComfyUI directory to extra_model_paths. InstantID requires insightface, you need to add it to your libraries together with onnxruntime and onnxruntime-gpu. 1. As a reminder you can save these image files and drag or load them into ComfyUI to get the workflow. Text-to-image. You can Load these images in ComfyUI to get the full workflow. Contribute to fofr/cog-comfyui-supir development by creating an account on GitHub. 2. Share, discover, & run thousands of ComfyUI workflows. Items other than base_path can be added or removed freely to map newly added subdirectories; the program will try load all of them. KSampler. CLIP Text Encode. Move the downloaded . # Set the web directory, any . You can then load up the following image in ComfyUI to get the workflow: AuraFlow 0. For some workflow examples and see what ComfyUI can do you can check out: In the standalone windows build you can find this file in the ComfyUI directory. json which you can both drop into ComfyUI to import the workflow. md file with a description of the workflow and a workflow. Download hunyuan_dit_1. json if it exists Jul 2, 2024 · Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything. The only important thing is that for optimal performance the resolution should be set to 1024x1024 or other resolutions with the same amount of pixels but a different aspect ratio. py --force-fp16. Selecting a model. Inpainting a cat with the v2 inpainting model: Inpainting a woman with the v2 inpainting model: It also works with non inpainting models. CosXL Edit Sample Workflow. This repo contains examples of what is achievable with ComfyUI. Linux. x, SDXL, Stable Video Diffusion, Stable Cascade, SD3 and Stable Audio You signed in with another tab or window. 1 ComfyUI install guidance, workflow and example. 3. You signed out in another tab or window. By default, the script will look for a file called workflow_api. safetensors from this page and save it as t5_base. png / workflow. 1 ComfyUI also has a mask editor that can be accessed by right clicking an image in the LoadImage node and “Open in MaskEditor”. Edit extra_model_paths. AnimateDiff workflows will often make use of these helpful ReActorBuildFaceModel Node got "face_model" output to provide a blended face model directly to the main Node: Basic workflow 💾. You signed in with another tab or window. json workflow file from the C:\Downloads\ComfyUI\workflows folder. bat file to run the script; Wait while the script downloads the latest version of ComfyUI Windows Portable, along with all the latest required custom nodes and extensions ComfyUI: The Ultimate Guide to Stable Diffusion's Powerful and Modular GUI. Loras are patches applied on top of the main MODEL and the CLIP model so to use them put them in the models/loras directory and use the LoraLoader node like this: Extract the workflow zip file; Copy the install-comfyui. safetensors instead for lower memory usage but the fp16 one is recommended if you have more than 32GB ram. The only way to keep the code open and free is by sponsoring its development. Launch ComfyUI by running python main. Here is the input image I used for this workflow: Jul 6, 2024 · Where to start? Basic controls. Please read the AnimateDiff repo README and Wiki for more information about how it works at its core. All the models will be downloaded automatically when running the workflow if they are not found in the ComfyUI\models\prompt_generator\ directory. If you have another Stable Diffusion UI you might be able to reuse the dependencies. Download the repository and unpack it into the custom_nodes folder in the ComfyUI installation directory. 5GB) and sd3_medium_incl_clips_t5xxlfp8. Rename Aug 1, 2024 · For use cases please check out Example Workflows. ComfyUI Examples. om。 说明：这个工作流使用了 LCM Open the cmd window in the ComfyUI_CatVTON_Wrapper plugin directory like ComfyUI\custom_ Nodes\ComfyUI_CatVTON_Wrapper and enter the following command, For ComfyUI official portable package, type: . The workflow endpoints will follow whatever directory structure you provide. Face Masking feature is available now, just add the "ReActorMaskHelper" Node to the workflow and connect it as shown below: These are examples demonstrating how to use Loras. Git clone this repo For some workflow examples and see what None of the aforementioned files are required to exist in the defaults/ directory, but the first token must exist as a workflow in the workflows/ directory. Welcome to the comprehensive, community-maintained documentation for ComfyUI open in new window, the cutting-edge, modular Stable Diffusion GUI and backend. Note that --force-fp16 will only work if you installed the latest pytorch nightly. You can also animate the subject while the composite node is being schedules as well! Load the . Rename Hunyuan DiT Examples. SD3 performs very well with the negative conditioning zeroed out like in the following example: SD3 Controlnet Flux. Those models need to be defined inside truss. This guide is about how to setup ComfyUI on your Windows computer to run Flux. Img2Img works by loading an image like this example image, converting it to latent space with the VAE and then sampling on it with a denoise lower than 1. Beware that the automatic update of the manager sometimes doesn't work and you may need to upgrade manually. You can use Test Inputs to generate the exactly same results that I showed here. For example, a directory structure like this: You signed in with another tab or window. Generate an image. Hunyuan DiT 1. exe -s -m pip install -r requirements. SDXL Examples. [Last update: 01/August/2024]Note: you need to put Example Inputs Files & Folders under ComfyUI Root Directory\ComfyUI\input folder before you can run the example workflow ComfyUI IPAdapter Plus; ComfyUI InstantID (Native) ComfyUI Essentials; ComfyUI FaceAnalysis; Not to mention the documentation and videos tutorials. bat file to the directory where you want to set up ComfyUI; Double click the install-comfyui. py to update the default input_file and output_file to match your . In the workflows directory you will find a separate directory containing a README. If you don’t have t5xxl_fp16. txt In the standalone windows build you can find this file in the ComfyUI directory. safetensors or clip_l. "A vivid red book with a smooth, matte cover lies next to a glossy yellow vase. This is different to the commonly shared JSON This example showcases the Noisy Laten Composition workflow. \python_embeded\python. About The implementation of MiniCPM-V-2_6-int4 has been seamlessly integrated into the ComfyUI platform, enabling the support for text-based queries, video queries, single-image queries, and multi Upgrade ComfyUI to the latest version! Download or git clone this repository into the ComfyUI/custom_nodes/ directory or use the Manager. This means many users will be sending workflows to it that might be quite different to yours. yaml. The pre-trained models are available on huggingface, download and place them in the ComfyUI/models/ipadapter directory (create it if not You signed in with another tab or window. Here’s a simple example of how to use controlnets, this example uses the scribble controlnet and the AnythingV3 model. Please check example workflows for usage. safetensors and put it in your ComfyUI/models/loras directory. The value schedule node schedules the latent composite node's x position. You can use t5xxl_fp8_e4m3fn. The experiments are more advanced examples and tips and tricks that might be useful in day-to-day tasks. Audio Examples Stable Audio Open 1. Or clone via GIT, starting from ComfyUI installation Aug 1, 2024 · [2024/07/25] 🌩️ Users can load BizyAir workflow examples directly by clicking the "☁️BizyAir Workflow Examples" button. You switched accounts on another tab or window. 0. Merge 2 images together with this ComfyUI workflow: View Now: ControlNet Depth Comfyui workflow: Use ControlNet Depth to enhance your SDXL images: View Now: Animation workflow: A great starting point for using AnimateDiff: View Now: ControlNet workflow: A great starting point for using ControlNet: View Now: Inpainting workflow: A great starting Examples of ComfyUI workflows. bat you can run to install to portable if detected. Download it, rename it to: lcm_lora_sdxl. ComfyUI Manager. 2. Face Masking feature is available now, just add the "ReActorMaskHelper" Node to the workflow and connect it as shown below: If you're running on Linux, or non-admin account on windows you'll want to ensure /ComfyUI/custom_nodes and comfyui_controlnet_aux has write permissions. json. yaml according to the directory structure, removing corresponding comments. You can then load up the following image in ComfyUI to get the workflow: Examples of ComfyUI workflows. Run any ComfyUI workflow w/ ZERO setup (free & open source) Try now Jul 25, 2024 · For some workflow examples and see what ComfyUI can do you can check out: In the standalone windows build you can find this file in the ComfyUI directory. From the root of the truss project, open the file called config. Hunyuan DiT is a diffusion model that understands both english and chinese. Rename this file to extra_model_paths. Load and merge the contents of categories/Some Category. All LoRA flavours: Lycoris, loha, lokr, locon, etc… are used this way. The effect of this will be that the internal ComfyUI server may need to swap models in and out of memory, this can slow down your prediction time. A sample workflow for running CosXL models, such as my RobMix CosXL checkpoint. What has just happened? Load Checkpoint node. Once loaded go into the ComfyUI Manager and click Install Missing Custom Nodes. The any-comfyui-workflow model on Replicate is a shared public model. Open the cmd window in the ComfyUI_CatVTON_Wrapper plugin directory like ComfyUI\custom_ Nodes\ComfyUI_CatVTON_Wrapper and enter the following command, For ComfyUI official portable package, type: . Download the model. Nov 29, 2023 · Download or git clone this repository inside ComfyUI/custom_nodes/ directory or use the Manager. The SD3 checkpoints that contain text encoders: sd3_medium_incl_clips. Then you can load this image in ComfyUI to get the workflow that shows how to use the LCM SDXL lora with the SDXL base model: Improved AnimateDiff integration for ComfyUI, as well as advanced sampling options dubbed Evolved Sampling usable outside of AnimateDiff. Enter a prompt and a negative prompt. Empty latent image. safetensors for the example below), the Depth controlnet here and the Union Controlnet here. Rename XLab and InstantX + Shakker Labs have released Controlnets for Flux. x, SD2. json workflow file and desired . safetensors to your ComfyUI/models/clip/ directory. [2024/07/16] 🌩️ BizyAir Controlnet Union SDXL 1. Comfy Workflows Comfy Workflows. safetensors (5. If needed, add arguments when executing comfyui_to_python. Generating your first image on ComfyUI. SD3 Examples. 0 node is released. The following images can be loaded in ComfyUI to get the full workflow. nuxvjx evdv fqdqdiv ayfuz hch wii ltybqc pbwmgr ipo znti