Comfyui workflow examples github sdxl. - liusida/top-100-comfyui Examples of ComfyUI workflows.
- Comfyui workflow examples github sdxl Nodes interface can be used to create complex workflows like one for Hires fix or much more advanced ones. ; ComfyPool: A manager for multiple ComfyUI instances, providing load balancing. LCM Lora. Updated Dec 5, 2024; Jupyter Notebook Among other options, separate use and automatic copying of the text prompt are possible if, for example, only one input has been filled in. To review, open the file in an editor that reveals hidden I feel like I must be doing something wrong since no one else is encountering this. . Plan and track A Video2Video framework for text2image models in ComfyUI. py remains unchanged. The lower the denoise the closer the composition will be to the original image. Contribute to shiimizu/ComfyUI-PhotoMaker-Plus development by creating an account on GitHub. json These workflow templates are intended as multi-purpose templates for use on a wide variety of projects. 0 Workflow . With so many abilities all in one workflow, you have to understand the principle of Stable Diffusion and ComfyUI to Examples of ComfyUI workflows. The denoise controls the amount of noise added to the image. I made AttentionCouplePPM node compatible with CLIPNegPiP node and with default PatchModelAddDownscale (Kohya Deep Shrink) node. Unofficial ComfyUI implementation of RAVE. ComfyUI_examples SDXL Turbo Examples. They can be used with any SDXL Here is an example workflow that can be dragged or loaded into ComfyUI. 5 vs 0. vv_sdxl. These are examples demonstrating how to do img2img. Plan and track work Code Review A set of custom nodes for ComfyUI that allow you to use Core ML models in your ComfyUI workflows. A port of muerrilla's sd-webui-Detail-Daemon as a node for ComfyUI, to adjust sigmas that control detail. The workflow primarily includes the following key nodes: Model Loading Node; UNETLoader: Loads the Flux Fill model; DualCLIPLoader: Loads the CLIP text encoding model; VAELoader: Loads the VAE model; Prompt Encoding Node Generate, downscale, change palletes and restore pixel art images with SDXL. ComfyUI Examples. Contribute to fabiomb/Comfy-Workflow-sdxl development by creating an account on GitHub. You signed in with another tab or window. json; To use GPT workflows, set your OpenAI API key in the environment: SDXL Pixel Art workflow for ComfyUI. - Jonseed/ComfyUI-Detail-Daemon Custom Conditioning Delta (ConDelta) nodes for ComfyUI - envy-ai/ComfyUI-ConDelta. Contribute to jakechai/ComfyUI-JakeUpgrade development by creating an account on GitHub. 9, but they did not update the model it seems, so that the baked in vae in the model file is incorrect. json at main · SytanSD/Sytan-SDXL-ComfyUI GitHub community articles Repositories. ThinkDiffusion_Hidden_Faces. - liusida/top-100-comfyui Saved searches Use saved searches to filter your results more quickly Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything. com/comfyanonymous/ComfyUI_examples/tree/master/model_merging Here is an example of how to create a CosXL model from a regular SDXL model A hub dedicated to development and upkeep of the Sytan SDXL workflow for ComfyUI he workflow is provided as a . md at main-branch · SharCodin/SDXL-Turbo-ComfyUI-Workflows ComfyUI Workflow Collection | ComfyUI 工作流合集. DreamShaper + SDXL Refiner: https://github. - 2024-09-29 - v1. A collection of ComfyUI custom nodes. Custom nodes and workflows for SDXL in ComfyUI. x and SDXL; Asynchronous Contribute to shiimizu/ComfyUI-PhotoMaker-Plus development by creating an account on GitHub. Models: PuLID pre-trained model goes in ComfyUI/models/pulid/ (thanks to Chenlei Hu for converting them into For some workflow examples and see what ComfyUI can do you can check out: ComfyUI Examples. 5 and below for Denoise to 0 denoise and anything above 0. 1/8/24 @6:00pm PST Version 1. Use the sdxl branch of this repo to load SDXL models; The loaded model only works with the Flatten KSampler and a standard ComfyUI checkpoint loader is required for other KSamplers; Node: Sample Trajectories. Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints download the taesd_decoder. Installing ComfyUI. pth (for SD1. The issue persists with both scripts. - liusida/top-100-comfyui Examples of ComfyUI workflows. Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints Hello, I'm a beginner trying to navigate through the ComfyUI API for SDXL 0. What it's great for: This SDXL workflow allows you to create images with the SDXL base model and the refiner and adds a LoRA to the image generation. 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. SDXL Config ComfyUI Fast Generation. A good place to start if you have no idea how any of this works is the: A hub dedicated to development and upkeep of the Sytan SDXL workflow for ComfyUI - Sytan-SDXL-ComfyUI/Sytan SDXL Workflow v0. 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: Workflow in Json format Some explanations for the parameters: Indeed, the classic LoRA will completely dilute the B-LoRA, supplanting it into the Unet. The LCM SDXL lora can be downloaded from here. SDXL 1. json at main · SytanSD/Sytan-SDXL-ComfyUI GitHub Copilot. 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. json. Fully supports SD1. CosXL models have better dynamic range and finer control than SDXL About: This specific comfyUI workflow uses SDXL model and Multi-area-conditioning (Compositional method) to generate art in Real-time. 5; Pixart Alpha and Sigma; AuraFlow; HunyuanDiT; Flux; Video Models Stable Video You signed in with another tab or window. Here is the workflow for the stability SDXL edit model, the checkpoint For some workflow examples and see what ComfyUI can do you can check out: ComfyUI Examples. GitHub Gist: instantly share code, notes, and snippets. All the images in this repo contain metadata which means they can be loaded into ComfyUI with the Load button (or dragged onto the basic_api_example. Topics Trending Collections Enterprise Enterprise platform. - Awesome smart way to work with nodes! - jags111/ComfyUI-Jags-workflows. Instant dev environments For SDXL wee are exploring some SDXL1. 1. Find and fix vulnerabilities Actions. json This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. ; CallWrapper: A wrapper for API calls that provides comprehensive event handling and execution control. A basic workflow is included, using the cupcake train example from the RAVE paper. txt within the cloned repo 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: The important parts are to use a low cfg, use the "lcm" sampler and the "sgm_uniform" or "simple" scheduler. - Security. x, SDXL, Stable Video Diffusion, Stable Cascade, SD3 and Stable Audio; LTX-Video; Flux; Mochi; Asynchronous Queue system; Git clone this repo. x) and taesdxl_decoder. You can Load these images in ComfyUI to get the full workflow. Topics Trending Collections Enterprise Enterprise platform Example: "beautiful scenery nature Extract the workflow zip file; Start ComfyUI by running the run_nvidia_gpu. 3. Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints Find and fix vulnerabilities Actions. x, SDXL, Stable Video Diffusion and Stable Cascade; Asynchronous Queue system; Many optimizations: Only re-executes the parts of the workflow that changes between executions. There was no generations queued (in the GUI) beforehand, so something funky is going on For some workflow examples and see what ComfyUI can do you can check out: ComfyUI Examples. The proper way to use it is with the new SDTurboScheduler SDXL Pixel Art workflow for ComfyUI. There are four nodes Kindly load all PNG files in same name in the (workflow driectory) to comfyUI to get all this workflows. This can be useful for systems with limited resources as the refiner takes another 6GB or ram. Write better code with AI Security. Download it, rename it to: lcm_lora_sdxl. Contribute to sanbuphy/ComfyUI-Workflow-Sanbu development by creating an account on GitHub. The proper way to use it is with the new SDTurboScheduler node but it might also work with the regular schedulers. Custom nodes and workflows for SDXL in ComfyUI. I tried to look for any special settings I must add/change to use SDXL, but nothing was mentioned in the readme. But you can drag and drop these images to see my workflow, which I spent some time on and am proud of. Download Workflow Files Download Flux Fill Workflow Workflow Usage Guide Workflow Node Explanation. Git clone this repo. pth (for SDXL) models and place them in the models Here is how you use it in ComfyUI (you can drag this into ComfyUI to get the workflow): noise_augmentation controls how closely the model will try to follow the image concept. See example_workflows directory for SD15 and SDXL examples with notes. Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints #If you want it for a specific workflow you can "enable dev mode options" #in the settings of the UI (gear beside the "Queue Size: ") this will enable #a button on the UI to save workflows in api format. pth (for SDXL) models and place them in the models SDXL Examples. x, SDXL, Stable Video Diffusion, Stable Cascade, SD3 and Stable Audio; Flux; Mochi; Asynchronous Queue system; Git clone this repo. Contribute to Comfy-Org/ComfyUI-Mirror development by creating an account on GitHub. com This repository automatically updates a list of the top 100 repositories related to ComfyUI based on the number of stars on GitHub. - liusida/top-100-comfyui Kindly load all PNG files in same name in the (workflow driectory) to comfyUI to get all this workflows. png in the Example_Workflows directory, it's a StylePrompt workflow that uses one KSampler, no Refiner. ComfyUI workflows for SD and SDXL Image Generation (ENG y ESP) English If you have any red nodes and some errors when you load it, just go to the ComfyUI Manager and select "Import Missing Nodes" and install them. Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints Welcome to the Awesome ComfyUI Custom Nodes list! The information in this list is fetched from ComfyUI Manager, ensuring you get the most up-to-date and relevant nodes. x, SD2. sdxl-pixel-art-workflow. 0: The A collection of SDXL workflow templates for use with Comfy UI - Suzie1/Comfyroll-SDXL-Workflow-Templates For some workflow examples and see what ComfyUI can do you can check out: ComfyUI Examples. 0 release. - sandy-5000/sdxl-ComfyUI. Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints ComfyApi: The main client for interacting with a single ComfyUI instance. Core ML: A machine learning framework developed by Apple. " Out of the box, upscales images 2x with some optimizations for added detail. x. Hey, I've been looking at the comfyui workflow, and it seems to use the EcomXL model. See example_workflows directory for examples. 9. ; PromptBuilder: A utility for constructing workflows with type-safe inputs and outputs. You switched accounts on another tab or window. I checked HuggingFace, but can not find it. Instant dev environments Issues. ControlNet and T2I-Adapter You signed in with another tab or window. GitHub community articles Repositories. The SDXL base checkpoint can be used like any regular checkpoint in ComfyUI. mp4. This is a basic workflow for With a regular KSampler, it seems like SDXL turbo is rounding everything 0. How to use this workflow If your model is based on SD 1. Also, when I tried to change my prompt, restarted Comfy and tried generating, it still generated an image with the old prompt. I'm having a hard time understanding how the API functions and how to effectively use it in my project. EcomID requires insightface, you need to add it to your libraries together with onnxruntime and onnxruntime-gpu. You can use the SDXL and CLIP_G functions in the prompt to set some settings like crop and target resolution values, but those are optional. Do any guys have any tips on downloading the EcomXL model? For some workflow examples and see what ComfyUI can do you can check out: ComfyUI Examples. 5 Inpaint Group Nodes upgrade, add more Image | Mask A set of ComfyUI nodes providing additional control for the LTX Video model - logtd/ComfyUI-LTXTricks The easiest of the image to image workflows is by "drawing over" an existing image using a lower than 1 denoise value in the sampler. Hand Fix module workflow added. Models: PuLID pre-trained model goes in ComfyUI/models/pulid/ (thanks to Chenlei Hu for converting them into Img2Img Examples. If you want to use SDXL Examples. json Upload your reference style image (you can find in vangogh_images folder) and target image to the respective nodes. Stable Diffusion XL (or SDXL) is the latest image generation model that is tailored towards more photorealistic outputs with more detailed imagery and composition compared to previous SD models. x, SDXL, Stable Video Diffusion, Stable Cascade, SD3 and Stable Audio; LTX-Video; Flux; Mochi; Asynchronous Queue system; "A cinematic, high-quality tracking shot in a mystical and whimsically charming swamp setting. Hidden Faces. Easy selection of resolutions recommended for SDXL (aspect ratio between square and up to 21:9 / 9:21). We will examine each aspect of this first workflow as it will give you a better understanding on how Stable Diffusion works but it's not something we will do for every workflow as we are mostly learning by example. More than 100 million people use GitHub to discover, fork, and contribute to over 420 million projects. py", line 20, in informative_sample raise RuntimeError("\n\n#### It seems that models and clips are mixed and interconnected between SDXL Base, SDXL Refiner, SD1. In this following example the positive text prompt is zeroed out in order for the final output to follow the input image more closely. and taesdxl_decoder. The author may answer you better than me. . x and SDXL; Asynchronous Queue system; Many optimizations: Only re-executes the parts This is based on the original InstructPix2Pix training example. 5 workflows? where to find best implementations to skip mediocre/redundant workflows- img2img with masking, multi controlnets, inpainting etc #8 opened Aug 6, 2023 by annasophiachristianahahn No, because it's not there yet. 5, but SDXL does work, although not as well (possibly because the multi-resolution training reduces the tiling effect?) SDXL Turbo is a SDXL model that can generate consistent images in a single step. 5 checkpoint with the FLATTEN optical flow model. LCM loras are loras that can be used to convert a regular model to a LCM model. About No description, website, or topics provided. The only important thing is that for optimal performance the resolution should be set to 1024x1024 or other resolutions with the same SDXL Turbo is a SDXL model that can generate consistent images in a single step. Our API is designed to help developers focus on creating innovative AI experiences without the burden of managing GPU infrastructure. Topics Trending These classes can be integrated into ComfyUI workflows to enhance prompt generation, image analysis, and latent space manipulation for advanced AI image generation pipelines. Installation. Use BlenderNeko's Unsampler for noise inversion. best ComfyUI sd 1. It has many upscaling options, such as img2img upscaling and Ultimate SD These workflow templates are intended as multi-purpose templates for use on a wide variety of projects. Contribute to yuichkun/my-comfyui-workflows development by creating an account on GitHub. A sample workflow for running CosXL models, such as my RobMix CosXL checkpoint. 5 to 1 denoise. This repository contains a handful of SDXL workflows I use, make sure to check the usefull links as some of these models, and/or plugins are required to use these in ComfyUI. A port of muerrilla's sd-webui-Detail-Daemon as a node for ComfyUI, to adjust sigmas that generally enhance details, and possibly remove unwanted bokeh or background blurring, particularly with Flux models (but also works with SDXL, SD1. and copy it into ComfyUI/models/loras (the example lora that was released alongside SDXL 1. Prerequisites Before you can use this workflow, you need to have ComfyUI installed. 9 safetensors + LoRA workflow + refiner You signed in with another tab or window. bat file; Click "Load" in ComfyUI and select the SDXL-ULTIMATE-WORKFLOW. x, SDXL, Stable Video Diffusion, Stable Cascade, SD3 and Stable Audio; Asynchronous Queue system; Many optimizations: Only re-executes the parts of the workflow that changes between executions. Security. List of Templates. pth (for SDXL) models and place them in the Contribute to shafayet98/SDXL-MultiAreaConditioning-ComfyUI-Workflow development by creating an account on GitHub. Contribute to markemicek/ComfyUI-SDXL-Workflow development by creating an account on GitHub. Glossary. 0 base and refiner You signed in with another tab or window. The PNG files have the json embedded into them and are easy to drag and drop ! HiRes-Fixing. Edit models also called InstructPix2Pix models are models that can be used to edit images using a text prompt. mp4 vv_sd15. github/ workflows For some workflow examples and see what ComfyUI can do you can check out: ComfyUI Examples. Stacking Scripts: XY Plot + Noise Control + HiRes-Fix ComfyUI workflows for Stable Diffusion, offering a range of tools from image upscaling and merging. Loading full workflows (with seeds) from generated PNG, WebP and FLAC files. They reverted the vae to 0. They are intended for use by people that are new to SDXL and ComfyUI. AI-powered developer platform Available add-ons. Inputs for new regions are managed automatically: when you attach cond/mask of a region to the node, a new cond_ / mask_ input Attempt at cog wrapper using ComfyUI to run a SDXL txt2img workflow config - lucataco/cog-comfyui-sdxl-txt2img GitHub community articles Repositories. A new example workflow has been addded: StylePromptBaseOnly. - Awesome smart way to work with nodes! - Examples · jags111/efficiency-nodes-comfyui Wiki. If I understand correctly there was a bug in the original 1. A hub dedicated to development and upkeep of the Sytan SDXL workflow for ComfyUI - Sytan-SDXL-ComfyUI/Sytan's SDXL 1. If you can't get the API to work, try giving this extension a shot. XY Plot: LoRA model_strength vs clip_strength. Step 2: comfyui_dagthomas - Advanced Prompt Generation and Image Analysis - dagthomas/comfyui_dagthomas This repo contains examples of what is achievable with ComfyUI. This article introduces some examples of ComfyUI. Install this repo from the ComfyUI manager or git clone the repo into custom_nodes then pip install -r requirements. If the values are taken too far it results in an oversharpened and/or HDR effect. Upgrade ComfyUI to the latest version! Download or git clone this repository into the ComfyUI/custom_nodes/ directory or use the Manager. Download the example workflow: apntest. FYI Comfy's latent handling is SUPERIOR for testing this stuff! Do check it out if you haven't yet. inference-engine diffusion-models stable-diffusion diffusers sd-webui comfyui sdxl aigc-serving lcm-lora stable-video-diffusion sdxl-turbo comfyui-workflow. Stacking Scripts: XY Plot + Noise Control + HiRes-Fix Upgrade ComfyUI to the latest version! Download or git clone this repository into the ComfyUI/custom_nodes/ directory or use the Manager. This also holds true with the CustomSampler when using a latent noise mask as in this workflow (try with the noise mask set to 0. Saving/Loading workflows as Json files. Multiple images can be used like this: A set of ComfyUI nodes providing additional control for the LTX Video model - logtd/ComfyUI-LTXTricks LCM Examples. Also, B-LoRAS work only with SDXL models, so make sure you load a SDXL Pipeline and put the is_sdxl flag of the Pipeline node to "True"! To load your B-LoRA: Put it inside the "lora" folder of your ComfyUI installation You signed in with another tab or window. - liusida/top-100-comfyui You signed in with another tab or window. 51) basic-img2img. Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything. py and websockets_api_example. 5, and likely other models). google cloud云端0成本部署comfyUI体验stable diffusion的SDXL模型 - frankchieng/comfyUI-Stable-Diffusion-Chinese-Geting-Started-Guide Instructions for downloading, installing and using the pre-converted TensorRT versions of SD3 Medium with ComfyUI and ComfyUI_TensorRT #23 (comment) btw you have a lora linked in your workflow; Same as SDXL's workflow; I think it should, if this extension is implemented correctly. Sure, it's not 2. Shortcuts. The lower the value the more it will follow the concept. x and SD2. 3. Keybind Explanation; Git clone this repo. - dimtoneff/ComfyUI-PixelArt-Detector Location of the nodes: "Image/PixelArt". A repository of well documented easy to follow workflows for ComfyUI - cubiq/ComfyUI_Workflows Workflows to implement fine-tuned CLIP Text Encoders with ComfyUI / SD, SDXL, SD3 - zer0int/ComfyUI-workflows You don't really need anything; just load an SDXL model and use it as you wold an SD1. Simple SDXL Template. ControlNet (Zoe depth) Advanced SDXL Template File "C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\sample_error_enhancer. Contribute to Asterecho/ComfyUI-ZHO-Chinese development by creating an account on GitHub. strength is how strongly it will influence the image. 15, adds a new UI field: 'prompt_style' and a 'Help' output to the style_prompt node This repository automatically updates a list of the top 100 repositories related to ComfyUI based on the number of stars on GitHub. My ComfyUI Workflows. 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. Advanced Security You signed in with another tab or window. - 2024-09-28 - v1. Loads any given SD1. 5 one. Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints Created by: OpenArt: What this workflow does This basic workflow runs the base SDXL model with some optimization for SDXL. SDXL Pixel Art workflow for ComfyUI Raw. If anyone coul Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything. This repository automatically updates a list of the top 100 repositories related to ComfyUI based on the number of stars on GitHub. - liusida/top-100-comfyui Here are the three recommended SDXL workflows for ComfyUI discussed in more detail: 1. Idk On this page: https://github. 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 Contribute to markemicek/ComfyUI-SDXL-Workflow development by creating an account on GitHub. In the ComfyUI interface, load the provided workflow file above: style_transfer_workflow. LCM models are special models that are meant to be sampled in very few steps. Automate any workflow Collection of ComyUI workflow experiments and examples - diffustar/comfyui-workflow-collection ComfyUI_examples Image Edit Model Examples. ComfyUI Workflow Examples. A ComfyUI implementation of the Clarity Upscaler, a "free and open source Magnific alternative. Most of the testing was done with SD1. They can be used with any SDXL checkpoint model. For some workflow examples and see what ComfyUI can do you can check out: ComfyUI Examples. x, SDXL, Stable Video Diffusion, Stable Cascade, SD3 and Stable Audio; Flux; Asynchronous Queue system; Git clone this repo. 0, it can add more contrast through offset For some workflow examples and see what ComfyUI can do you can check out: ComfyUI Examples. x, SDXL, SDXL Turbo; Stable Cascade; SD3 and SD3. 5 and SDXL. Topics Trending Collections Enterprise Enterprise platform Example: "beautiful scenery nature glass bottle landscape, pink galaxy bottle" About. The following examples were made with SDXL Vanilla with CFG set to 15. SDXL Refining & Noise Control Script. This can be solved by simply loadin Here is how you use it in ComfyUI (you can drag this into ComfyUI to get the workflow): noise_augmentation controls how closely the model will try to follow the image concept. Reload to refresh your session. 5. Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints A collection of my own ComfyUI workflows for working with SDXL - sepro/SDXL-ComfyUI-workflows Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything. The most powerful and modular stable diffusion GUI with a graph/nodes interface. It will convert your workflow_api. These can be obtained from sites like Hugging Face or the Stability AI GitHub. Workflow for ComfyUI and SDXL 1. ComfyICU provides a robust REST API that allows you to seamlessly integrate and execute your custom ComfyUI workflows in production environments. ai/workflows GitHub is where people build software. CosXL Sample Workflow. Area Composition; Inpainting with both regular and inpainting models. A collection of ComfyUI custom nodes based workflows and experiments. json to executable python code that can run without the comfyui server. It's used to run machine learning models on Apple devices. SDXL Ultimate Workflow is the best and most complete single workflow that exists for SDXL 1. ComfyUI workflow customization by Jake. json file which is easily loadable into the ComfyUI environment. Contribute to SeargeDP/SeargeSDXL development by creating an account on GitHub. Shrek, towering in his familiar green ogre form with a rugged vest and tunic, stands with a slightly annoyed but determined expression as he surveys his surroundings. github/ workflows . You signed out in another tab or window. 0 and SD 1. 0. - aszc-dev/ComfyUI-CoreMLSuite Check Example Workflows for some example workflows. The easiest image generation workflow. You can use more steps to increase the quality. SD2. x, SDXL and Stable Video Diffusion; Asynchronous Queue system; Many optimizations: Only re-executes the parts of the workflow that changes between executions. Left image is without APG and right image is with APG on default settings. Supports SD1. It leverages a three times larger UNet backbone. x, and SD2. For example: 896x1152 or 1536x640 are good resolutions. 4 Hand Fix supports SD3 and Flux. This repo contains the workflows and Gradio UI from the "How to Use SDXL Turbo in Comfy UI for Fast Image Generation" video tutorial This repository automatically updates a list of the top 100 repositories related to ComfyUI based on the number of stars on GitHub. Contribute to zhongpei/comfyui-example development by creating an account on GitHub. Intermediate SDXL Template. This repo contains examples of what is achievable with ComfyUI. safetensors and put it in your ComfyUI/models/loras directory. Automate any workflow Codespaces. Saved searches Use saved searches to filter your results more quickly You signed in with another tab or window. This is a curated collection of custom nodes for ComfyUI, designed to extend its Attempt at cog wrapper using ComfyUI to run a SDXL txt2img workflow config - asppj/comfyui-txt2img GitHub community articles Repositories. SDXL Turbo is a SDXL model that can generate consistent images in a single step. 15 Version 1. SDXL can indeed generate a nude body, and the model itself doesn't stop you from fine-tuning it towards whatever spicy stuff there is with a dataset, at least by the looks of it. The example images For some workflow examples and see what ComfyUI can do you can check out: ComfyUI Examples. Modified implementation of AttentionCouple by laksjdjf and Haoming02. 5, use this basic workflow instead - https://openart. ControlNet Inpaint Example. The increase of model parameters is mainly due to more attention How to Use SDXL Turbo in Comfy UI for Fast Image Generation - SDXL-Turbo-ComfyUI-Workflows/README. Workflow examples can be found on the Examples page. I've added some example workflow in the workflow. json file; Launch the ComfyUI Manager using the sidebar in ComfyUI; Click "Install Missing Custom Nodes" and install/update each of the missing nodes; Click "Install Models" to install any missing models 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. Adjust parameters as needed (It may depend on your images and just play around, it is really fun!!). Specified Dual Clip switch added for sdxl workflow. Takes the input images and samples their optical flow into Take versatile-sd as an example, it contains advanced techniques like IPadapter, ControlNet, IC light, LLM prompt generating, removing bg and excels at text-to-image generating, image blending, style transfer, style exploring, inpainting, outpainting, relighting. 43 KB. In this following example the positive text prompt is zeroed out in order for the final output to follow the input Here is an example workflow that can be dragged or loaded into ComfyUI. pth (for SDXL) models and place them in the models I am doing a Kohya LoRA training atm I need a workflow for using SDXL 0. gvwfwm freg zmmhr elnat gvff ajq bzzbexz ttdxk chkmmoq jmziz