Comfyui workflow json example

Comfyui workflow json example. For some workflow examples and see what ComfyUI can do you can check out: Saving/Loading workflows as Json files. Users can drag and drop nodes to design advanced AI art pipelines, and also take advantage of libraries of existing workflows. To load a workflow, simply click the Load button on the right sidebar, and select the workflow . Dec 19, 2023 · The extracted folder will be called ComfyUI_windows_portable. Exporting your ComfyUI project to an API-compatible JSON file is a bit trickier than just saving the project. The parameters are the prompt, which is the whole workflow JSON; client_id, which we generated; and the server_address of the running ComfyUI instance A repository of well documented easy to follow workflows for ComfyUI - cubiq/ComfyUI_Workflows This repo is divided into macro categories, in the root of each directory you'll find the basic json files and an experiments directory. serve a Flux ComfyUI workflow as an API. [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 Workflow in Json format If you want the exact input image you can find it on the unCLIP example page You can also use them like in this workflow that uses SDXL to generate an initial image that is then passed to the 25 frame model: Lora Examples. ComfyUI provides a powerful yet intuitive way to harness Stable Diffusion through a flowchart interface. A sample workflow for running CosXL models, such as my RobMix CosXL checkpoint. In this example, we show you how to. 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. While ComfyUI lets you save a project as a JSON file, that file will Sep 13, 2023 · with normal ComfyUI workflow json files, they can be drag-&-dropped into the main UI and the workflow would be loaded. Workflow examples can be found on the Simple workflow for using the new Stable Video Diffusion model in ComfyUI for image to video generation. 1. 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. Simply download the . Save this image then load it or drag it on ComfyUI to get the workflow. ComfyUI breaks down a workflow into rearrangeable elements so you can easily make your own. Some commonly used blocks are Loading a Checkpoint Model, entering a prompt, specifying a sampler, etc. Thank you very much! I understand that I have to put the downloaded JSONs into the custom nodes folder and load them from there. Merge 2 images together (Merge 2 images together with this ComfyUI workflow) View Now. AnimateDiff workflows will often make use of these helpful . com This repo contains examples of what is achievable with ComfyUI. " When you load a . json workflow file from the C:\Downloads\ComfyUI\workflows folder. x, 2. That’s it! We can now deploy our ComfyUI workflow to Baseten! Step 3: Deploying your ComfyUI workflow to For these examples I have renamed the files by adding stable_cascade_ in front of the filename for example: stable_cascade_canny. 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. zip file. You switched accounts on another tab or window. Aug 1, 2024 · For use cases please check out Example Workflows. You can find the Flux Schnell diffusion model weights here this file should go in your: ComfyUI/models/unet/ folder. json, the component is automatically loaded. You can then load or drag the following image in ComfyUI to get the workflow: This is the input image that will be used in this example: Here is an example using a first pass with AnythingV3 with the controlnet and a second pass without the controlnet with AOM3A3 (abyss orange mix 3) and using their VAE. For example, errors may occur when generating hands, and serious distortions can occur when generating full-body characters. json file; Load: Load a ComfyUI . Combining the UI and the API in a single app makes it easy to iterate on your workflow even after deployment. json file. json file, which is stored in the "components" subdirectory, and then restart ComfyUI, you will be able to add the corresponding component that starts with "##. 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. This is different to the commonly shared JSON version, it does not included visual information about nodes, etc. These are examples demonstrating how to do img2img. Feb 24, 2024 · Save: Save the current workflow as a . Quickstart Dec 8, 2023 · Run ComfyUI locally (python main. All the KSampler and Detailer in this article use LCM for output. (open('workflow_api. A sample workflow for running CosXL Edit models, such as my RobMix CosXL Edit checkpoint. 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. safetensors. ControlNet Depth Comfyui workflow (Use ControlNet Depth to enhance your SDXL images) View Now. Merge 2 images together with this ComfyUI workflow. example to extra_model_paths. 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. Img2Img Examples. Jul 18, 2024 · Examples from LivePortrait’s repository. run Flux on ComfyUI interactively to develop workflows. Load the . You can Load these images in ComfyUI to get the full workflow. EZ way, kust download this one and run like another checkpoint ;) https://civitai. SD3 performs very well with the negative conditioning zeroed out like in the following example: SD3 Controlnet ComfyUI . I made this using the following workflow with two images as a starting point from the ComfyUI IPAdapter node repository. com/models/628682/flux-1-checkpoint Edit 2024-08-26: Our latest recommended solution for productionizing a ComfyUI workflow is detailed in this example. Saving/Loading workflows as Json files. Jul 6, 2024 · What is ComfyUI? ComfyUI is a node-based GUI for Stable Diffusion. component. SD3 performs very well with the negative conditioning zeroed out like in the following example: SD3 Controlnet. I was confused by the fact that I saw in several Youtube videos by Sebastain Kamph and Olivio Sarikas that they simply drop png's into the empty ComfyUI. Dec 10, 2023 · Tensorbee will then configure the comfyUI working environment and the workflow used in this article. com/models/283810 The simplicity of this wo It is a simple workflow of Flux AI on ComfyUI. components. As a result, this post has been largely re-written to focus on the specific use case of converting a ComfyUI JSON workflow to Python. Feb 13, 2024 · Sends a prompt to a ComfyUI to place it into the workflow queue via the "/prompt" endpoint given by ComfyUI. Place the models you downloaded in the previous step in the folder: ComfyUI_windows_portable\ComfyUI\models\checkpoints; If you downloaded the upscaler, place it in the folder: ComfyUI_windows_portable\ComfyUI\models\upscale_models; Step 3: Download Sytan's SDXL Workflow "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 Jan 15, 2024 · That’s the whole thing! Every text-to-image workflow ever is just an expansion or variation of these seven nodes! If you haven’t been following along on your own ComfyUI canvas, the completed workflow is attached here as a . Generating the first video Here is a workflow for using it: Save this image then load it or drag it on ComfyUI to get the workflow. Installing ComfyUI. Open the YAML file in a code or text editor Dec 4, 2023 · It might seem daunting at first, but you actually don't need to fully learn how these are connected. You can construct an image generation workflow by chaining different blocks (called nodes) together. As a reminder you can save these image files and drag or load them into ComfyUI to get the workflow. You only need to click “generate” to create your first video. 1 ComfyUI install guidance, workflow and example. This workflow has two inputs: a prompt and an image. The denoise controls the amount of noise added to the image. You’ll find a . Jul 25, 2024 · For this tutorial, the workflow file can be copied from here. ComfyUI also supports LCM Sampler, Source code here: LCM Sampler support I tried to break it down into as many modules as possible, so the workflow in ComfyUI would closely resemble the original pipeline from AnimateAnyone paper: Roadmap Implement the compoents (Residual CFG) proposed in StreamDiffusion ( Estimated speed up: 2X ) ComfyUI Manager: Plugin for CompfyUI that helps detect and install missing plugins. json file, change your input images and your prompts and you are good to go! ControlNet Depth ComfyUI workflow See full list on github. Support for SD 1. Inpainting a cat with the v2 inpainting model: Inpainting a woman with the v2 inpainting model: It also works with non inpainting models. Join the largest ComfyUI community. This guide is about how to setup ComfyUI on your Windows computer to run Flux. I then recommend enabling Extra Options -> Auto Nov 25, 2023 · LCM & ComfyUI. ControlNet and T2I-Adapter - ComfyUI workflow Examples. Note that in these examples the raw image is passed directly to the ControlNet/T2I adapter. safetensors, stable_cascade_inpainting. It might seem daunting at first, but you actually don't need to fully learn how these are connected. Since LCM is very popular these days, and ComfyUI starts to support native LCM function after this commit, so it is not too difficult to use it on ComfyUI. 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. json file workflow ; Refresh: Refresh ComfyUI workflow; Clear: Clears all the nodes on the screen ; Load Default: Load the default ComfyUI workflow ; In the above screenshot, you’ll find options that will not be present in your ComfyUI installation. mp4 Collection of ComyUI workflow experiments and examples - diffustar/comfyui-workflow-collection Discover the Ultimate Workflow with ComfyUI in this hands-on tutorial, where I guide you through integrating custom nodes, refining images with advanced tool Here is a workflow for using it: Example. Goto ComfyUI_windows_portable\ComfyUI\ Rename extra_model_paths. Reload to refresh your session. CosXL Edit Sample Workflow. py --force-fp16 on MacOS) and use the "Load" button to import this JSON file with the prepared workflow. The following images can be loaded in ComfyUI to get the full workflow. It covers the following topics: "A vivid red book with a smooth, matte cover lies next to a glossy yellow vase. CosXL models have better dynamic range and finer control than SDXL models. yaml. ComfyUI also has a mask editor that can be accessed by right clicking an image in the LoadImage node and “Open in MaskEditor”. json file or load a workflow created with . But let me know if you need help replicating some of the concepts in my process. Flux Schnell is a distilled 4 step model. Mixing ControlNets Flux. You signed out in another tab or window. Features. This was the base for my Jun 23, 2024 · Despite significant improvements in image quality, details, understanding of prompts, and text content generation, SD3 still has some shortcomings. To get your API JSON: Turn on the "Enable Dev mode Options" from the ComfyUI settings (via the settings icon) Load your workflow into ComfyUI; Export your API JSON using the "Save (API format)" button; comfyui-save-workflow. Always refresh your browser and click refresh in the ComfyUI window after adding models or custom_nodes. Sytan SDXL ComfyUI: Very nice workflow showing how to connect the base model with the refiner and include an upscaler. Export your ComfyUI project. This should update and may ask you the click restart. You signed in with another tab or window. 0. Simply download the file and drag it directly onto your own ComfyUI canvas to explore the workflow yourself! For some workflow examples and see what ComfyUI can do you can check out: ComfyUI Examples. Please read the AnimateDiff repo README and Wiki for more information about how it works at its core. I then recommend enabling Extra Options -> Auto Queue in the interface. Dec 19, 2023 · Here's a list of example workflows in the official ComfyUI repo. Then press “Queue Prompt” once and start writing your prompt. Simply head to the interactive UI, make your changes, export the JSON, and redeploy the app. . 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. 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. json file which is the ComfyUI workflow file. 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 Feb 7, 2024 · My ComfyUI workflow that was used to create all example images with my model RedOlives: https://civitai. All LoRA flavours: Lycoris, loha, lokr, locon, etc… are used this way. ComfyUI ControlNet aux: Plugin with preprocessors for ControlNet, so you can generate images directly from ComfyUI. Download this workflow and extract the . json')) Next let’s create some example prompts and You signed in with another tab or window. You can then load or drag the following image in ComfyUI to get the workflow: Flux Schnell. This workflow can use LoRAs, ControlNets, enabling negative prompting with Ksampler, dynamic thresholding, inpainting, and more. This amazing model can be run directly using Python, but to make things easier, I will show you how to download and run LivePortrait using ComfyUI, the You signed in with another tab or window. If you place the . The experiments are more advanced examples and tips and tricks that might be useful in day-to-day tasks. A Feb 7, 2024 · We’ll be using the SDXL Config ComfyUI Fast Generation workflow which is often my go-to workflow for running SDXL in ComfyUI. CosXL Sample Workflow. Nov 25, 2023 · Upscaling (How to upscale your images with ComfyUI) View Now. Aug 16, 2023 · This ComfyUI workflow sample merges the MultiAreaConditioning plugin with serveral loras, together with openpose for controlnet and regular 2x upscaling in Comf. The vase, with a slightly curved silhouette, stands on a dark wood table with a noticeable grain pattern. Animation workflow (A great starting point for using AnimateDiff) View Now Share, discover, & run thousands of ComfyUI workflows. A CosXL Edit model takes a source image as input 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. These are examples demonstrating how to use Loras. Some workflows alternatively require you to git clone the repository to your ComfyUI/custom_nodes folder, and restart ComfyUI. We can specify those variables inside our workflow JSON file using the handlebars template {{prompt}} and {{input_image}}. 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. Basic Vid2Vid 1 ControlNet - This is the basic Vid2Vid workflow updated with the new nodes. Once loaded go into the ComfyUI Manager and click Install Missing Custom Nodes. Workflow in Json format If you want the exact input image you can find it on the unCLIP example page You can also use them like in this workflow that uses SDXL to generate an initial image that is then passed to the 25 frame model: Apr 26, 2024 · Workflow. 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. x, SDXL, LoRA, and upscaling makes ComfyUI flexible. Achieves high FPS using frame interpolation (w/ RIFE). Improved AnimateDiff integration for ComfyUI, as well as advanced sampling options dubbed Evolved Sampling usable outside of AnimateDiff. You can load this image in ComfyUI to get the full workflow. nsrcvbcu oas fwgu hto xcdge pqendk csckwvd muluwl fancs myqj