Comfyui load workflow example

Comfyui load workflow example. Apr 8, 2024 · Your prompts text file should be placed in your ComfyUI/input folder; Logic Boolean node: Used to restart reading lines from text file. Here is an example of how to use upscale models like ESRGAN. This image has had part of it erased to alpha with gimp, the alpha channel is what we will be using as a mask for the inpainting. Sep 7, 2024 · Is an example how to use it. Create animations with AnimateDiff. Here are the official checkpoints for the one tuned to generate 14 frame videos and the one for 25 frame videos. Standalone VAEs and CLIP models. To load the associated flow of a generated image, simply load the image via the Load button in the menu, or drag and drop it into the ComfyUI window. Here’s a simple example of how to use controlnets, this example uses the scribble controlnet and the AnythingV3 model. To load a workflow, simply click the Load button on the right sidebar, and select the workflow . Aug 16, 2023 · ComfyUI wildcards in prompt using Text Load Line From File node; ComfyUI load prompts from text file workflow; Allow mixed content on Cordova app’s WebView; ComfyUI migration guide FAQ for a1111 webui users; ComfyUI workflow sample with MultiAreaConditioning, Loras, Openpose and ControlNet; Change output file names in ComfyUI Click Load Default button to use the default workflow. Upscale Model Examples. 0. The name of the VAE. The denoise controls the amount of noise added to the image. I made this using the following workflow with two images as a starting point from the ComfyUI IPAdapter node repository. Once loaded go into the ComfyUI Manager and click Install Missing Custom Nodes. Here is an example for how to use the Canny Controlnet: Here is an example for how to use the Inpaint Controlnet, the example input image can be found here. Flux. 2. A Dec 19, 2023 · Here's a list of example workflows in the official ComfyUI repo. 1; Overview of different versions of Flux. json file. Video Examples Image to Video. You can then load up the following image in ComfyUI to get the workflow: Try an example Canny Controlnet workflow by dragging in this image into ComfyUI. Manual way is to clone this repo to the ComfyUI/custom_nodes-folder. ComfyUI breaks down a workflow into rearrangeable elements so you can easily make your own. Then I created two more sets of nodes, from Load Images to the IPAdapters, and adjusted the masks so that they would be part of a specific section in the whole image. My actual workflow file is a little messed up at the moment, I don't like sharing workflow files that people can't understand; my process is a bit particular to my needs and the whole power of ComfyUI is for you to create something that fits your needs. Restart ComfyUI; Note that this workflow use Load Lora node to load a Can load ckpt, safetensors and diffusers models/checkpoints. In ComfyUI the saved checkpoints contain the full workflow used to generate them so they can be loaded in the UI just like images to get the full workflow that was used to create them. outputs. This repo contains examples of what is achievable with ComfyUI. Upscaling ComfyUI workflow. FLUX. The default workflow is a simple text-to-image flow using Stable Diffusion 1. These are examples demonstrating how to use Loras. Hunyuan DiT is a diffusion model that understands both english and chinese. safetensors. This guide is about how to setup ComfyUI on your Windows computer to run Flux. json workflow file from the C:\Downloads\ComfyUI\workflows folder. Sep 7, 2024 · Hypernetwork Examples. Img2Img Examples. All LoRA flavours: Lycoris, loha, lokr, locon, etc… are used this way. Here is a workflow for using it: Example. You can Load these images in ComfyUI open in new window 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. For loading a LoRA, you can utilize the Load LoRA node. Put them in the models/upscale_models folder then use the UpscaleModelLoader node to load them and the ImageUpscaleWithModel node to use them. Here are the official checkpoints for the one tuned to generate 14 frame videos open in new window and the one for 25 frame videos open in new window. Always refresh your browser and click refresh in the ComfyUI window after adding models or custom_nodes. Download workflow here: Load LoRA. It will always be this frame amount, but frames can run at different speeds. Since SDXL requires you to use both a base and a refiner model, you’ll have to switch models during the image generation process. Apr 26, 2024 · Workflow. 1. Hypernetworks are patches applied on the main MODEL so to use them put them in the models/hypernetworks directory and use the Hypernetwork Loader node like this: Jul 18, 2024 · Assuming you have ComfyUI properly installed and updated, download the workflow liveportrait_example_01. Download it and place it in your input folder. To build a workflow for image generation in ComfyUI, you’ll have to ComfyUI . Discover the Ultimate Workflow with ComfyUI in this hands-on tutorial, where I guide you through integrating custom nodes, refining images with advanced tool Sep 7, 2024 · Inpaint Examples. All LoRA flavours: Lycoris, loha, lokr, locon, etc are used this way. All the images in this page 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. Feb 24, 2024 · Load Default: Load the default ComfyUI workflow ; In the above screenshot, you’ll find options that will not be present in your ComfyUI installation. If you need an example input image for the canny, use this . The only way to keep the code open and free is by sponsoring its development. The Load VAE node can be used to load a specific VAE model, VAE models are used to encoding and decoding images to and from latent space. Download this lora and put it in ComfyUI\models\loras folder as an example. This will automatically parse the details and load all the relevant nodes, including their settings. To use your LoRA with ComfyUI you need this node: Load LoRA node in ComfyUI. Dec 10, 2023 · Progressing to generate additional videos. This model is used for image generation. Table of contents. Img2Img works by loading an image like this example image open in new window, converting it to latent space with the VAE and then sampling on it with a denoise lower than 1. Let's get started! Hunyuan DiT Examples. SD3 performs very well with the negative conditioning zeroed out like in the following example: SD3 Controlnet. This should update and may ask you the click restart. The SDXL base checkpoint can be used like any regular checkpoint in ComfyUI. It’s one that shows how to use the basic features of ComfyUI. Support for SD 1. ControlNet and T2I-Adapter - ComfyUI workflow Examples Note that in these examples the raw image is passed directly to the ControlNet/T2I adapter. You signed out in another tab or window. You can load this image in ComfyUI (opens in a new tab) to get the workflow. Aug 5, 2024 · The Tex2img workflow is as same as the classic one, including one Load checkpoint, one postive prompt node with one negative prompt node and one K Sampler. For some workflow examples and see what ComfyUI can do you can check out: ComfyUI Examples. . ComfyUI IPAdapter Plus; ComfyUI InstantID (Native) ComfyUI Essentials; ComfyUI FaceAnalysis; Not to mention the documentation and videos tutorials. In this example we will be using this image. To review any workflow you can simply drop the JSON file onto your ComfyUI work area, also remember that any image generated with ComfyUI has the whole workflow embedded into itself. Img2Img ComfyUI workflow. Here is a basic example how to use it: As a reminder you can save these image files and drag or load them into ComfyUI to get the workflow. There is a “Pad Image for Outpainting” node to automatically pad the image for outpainting while creating the proper mask. Run any ComfyUI workflow w/ ZERO setup (free & open source) Try now Load the . x, SDXL, LoRA, and upscaling makes ComfyUI flexible. Image to Video. 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. Sep 7, 2024 · Lora Examples. Users have the ability to assemble a workflow for image generation by linking various blocks, referred to as nodes. Jul 6, 2024 · You can construct an image generation workflow by chaining different blocks (called nodes) together. Save this image then load it or drag it on ComfyUI to get the workflow. VAE Aug 1, 2024 · For use cases please check out Example Workflows. Open the YAML file in a code or text editor Jun 23, 2024 · Despite significant improvements in image quality, details, understanding of prompts, and text content generation, SD3 still has some shortcomings. The models are also available through the Manager, search for "IC-light". But let me know if you need help replicating some of the concepts in my process. ComfyUI Workflow Examples; Online Resources; Let's go through a simple example of a text-to-image workflow using ComfyUI: Step1: Selecting a Model Start by selecting a Stable Diffusion Checkpoint model in the Load Checkpoint node. Share, discover, & run thousands of ComfyUI workflows. 1 UNET Model. Please note that in the example workflow using the example video we are loading every other frame of a 24 frame video and then turning that into at 8 fps animation (meaning things will be slowed compared to the original video) Workflow Explanations. English. SDXL works with other Stable Diffusion interfaces such as Automatic1111 but the workflow for it isn’t as straightforward. Think Diffusion's Stable Diffusion ComfyUI Top 10 Cool Workflows. safetensors and put it in your ComfyUI/checkpoints directory. Download hunyuan_dit_1. SDXL Examples. json and load it in the UI. Comfy Workflows Comfy Workflows. vae_name. Although the Load Checkpoint node provides a VAE model alongside the diffusion model, sometimes it can be useful to use a specific VAE model. In the Load Checkpoint node, select the checkpoint file you just downloaded. There should be no extra requirements needed. The SDXL base checkpoint can be used like any regular checkpoint in ComfyUI (opens in a new tab). To load a workflow from an image: Click the Load button in the menu; Or drag and drop the image into the ComfyUI window; The associated workflow will automatically load, complete with all nodes and settings. For some workflow examples and see what ComfyUI can do you can check An All-in-One FluxDev workflow in ComfyUI that combines various techniques for generating images with the FluxDev model, including img-to-img and text-to-img. inputs. Drag the full size png file to ComfyUI’s canva. You switched accounts on another tab or window. The way ComfyUI is built up, every image or video saves the workflow in the metadata, which means that once an image has been generated with ComfyUI, you can simply drag and drop it to get that complete workflow. This example is an example of merging 3 different checkpoints using simple block merging where the input, middle and output blocks of the unet can have a Recommended way is to use the manager. For some workflow examples and see what ComfyUI can do you can check out: Workflow examples can be found on the Examples page. The easiest way to get to grips with how ComfyUI works is to start from the shared examples. Set boolean_number to 1 to restart from the first line of the prompt text file. In this example this image will be outpainted: Using the v2 inpainting model and the “Pad Image for Outpainting” node (load it in ComfyUI to see the workflow): Sep 7, 2024 · SDXL Examples. Check my ComfyUI Advanced Understanding videos on YouTube for example, part 1 and part 2. ControlNet Depth ComfyUI workflow. Save workflow: Ctrl + O: Load workflow: Ctrl + A: Select all nodes Outpainting is the same thing as inpainting. x, 2. Users can drag and drop nodes to design advanced AI art pipelines, and also take advantage of libraries of existing workflows. ComfyUI provides a powerful yet intuitive way to harness Stable Diffusion through a flowchart interface. Load workflow: Ctrl + A: Select Here is a workflow for using it: Save this image then load it or drag it on ComfyUI to get the workflow. ComfyUI dissects a workflow into adjustable components, enabling users to customize their own unique processes. Examples of ComfyUI workflows. It covers the following topics: Introduction to Flux. For example, errors may occur when generating hands, and serious distortions can occur when generating full-body characters. Then press “Queue Prompt” once and start writing your prompt. Basic Vid2Vid 1 ControlNet - This is the basic Vid2Vid workflow updated with the new nodes. Merging 2 Images together. Some workflows alternatively require you to git clone the repository to your ComfyUI/custom_nodes folder, and restart ComfyUI. Aug 16, 2024 · Workflow. That’s because I have installed additional ComfyUI extensions which we’ll get to later in this guide. 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. These nodes include common operations such as loading a model, inputting prompts, defining samplers and more. 1 with ComfyUI See full list on github. This is the default setup of ComfyUI with its default nodes already placed. SD3 Controlnets by InstantX are also supported. This example is an example of merging 3 different checkpoints using simple block merging where the input, middle and output blocks of the unet can have a Many of the workflow guides you will find related to ComfyUI will also have this metadata included. Set your number of frames. safetensors, stable_cascade_inpainting. The workflow is like this: If you see red boxes, that means you have missing custom nodes. As of writing this there are two image to video checkpoints. Thanks to the incorporation of the latest Latent Consistency Models (LCM) technology from Tsinghua University in this workflow, the sampling process Dec 4, 2023 · It might seem daunting at first, but you actually don't need to fully learn how these are connected. 1-schnell on hugging face (opens in a new tab) Load the workflow, in this example we're using Basic Text2Vid. If you have a previous installation of ComfyUI with Models, or would like to use models stored in an external location, you can use this method to reference them instead of re-downloading them. You can Load these images in ComfyUI (opens in a new tab) to get the full workflow. Hunyuan DiT 1. yaml. These are examples demonstrating how to do img2img. Depending on your frame-rate, this will affect the length of your video in seconds. You can Load these images in ComfyUI to get the full workflow. Sep 7, 2024 · Img2Img Examples. I then recommend enabling Extra Options -> Auto Queue in the interface. Click Queue Prompt and watch your image generated. SDXL Default ComfyUI workflow. 1 ComfyUI install guidance, workflow and example. Some commonly used blocks are Loading a Checkpoint Model, entering a prompt, specifying a sampler, etc. You signed in with another tab or window. Install the UNET models; Dwonload the workflow file; Import workflow in comfyUI; Chose the UNET model and run the workflow; Download FLux. This first example is a basic example of a simple merge between two different checkpoints. For example, 50 frames at 12 frames per second will run longer than 50 frames at 24 frames per For these examples I have renamed the files by adding stable_cascade_ in front of the filename for example: stable_cascade_canny. Load VAE node. Connecting Nodes. Reload to refresh your session. I then recommend enabling Extra Options -> Auto Examples of what is achievable with ComfyUI open in new window. Put it under ComfyUI/input . Load LoRA. Feb 7, 2024 · Why Use ComfyUI for SDXL. 1; Flux Hardware Requirements; How to install and use Flux. Here is the input image I used for this workflow: Lora Examples. com 6 min read. You can load this image in ComfyUI open in new window to get the workflow. Img2Img works by loading an image like this example image (opens in a new tab), converting it to latent space with the VAE and then sampling on it with a denoise lower than 1. Use ComfyUI Manager to install the missing nodes. Each ControlNet/T2I adapter needs the image that is passed to it to be in a specific format like depthmaps, canny maps and so on depending on the specific model if you want good results. Here is an example: You can load this image in ComfyUI to get the workflow. This workflow can use LoRAs, ControlNets, enabling negative prompting with Ksampler, dynamic thresholding, inpainting, and more. 5. Next, use the ComfyUI-Manager to install the missing custom node ComfyUI Examples; 2 Pass Txt2Img (Hires fix) Examples Here is an example: Example. You can load this image in ComfyUI to get the full workflow. Start with the default workflow. You can take many of the images you see in this documentation and drop it inside ComfyUI to load the full node structure. example to extra_model_paths. Goto ComfyUI_windows_portable\ComfyUI\ Rename extra_model_paths. [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 Load Diffusion Model Workflow Example | UNET Loader Guide UNET-Loader Workflow. xdqgdeaxm eesp kqaub kbjbt ptblr dkqk eizfad sucsxol swsvi ajaiztzp  »