Wan 2.1 Video is a series of open foundational video models. It supports a wide range of video-generation tasks. It can turn images or text descriptions into videos at 480p or 720p resolutions. In this post: Table of ContentsSoftwareRunning on Google ColabWan 2.1 sample videos720p videos480p videosWhat are the Wan 2.1 models?Model architectureHighlightsWan 2.1 Image-to-video…
Blog
How to create text effect in ComfyUI
This workflow uses an SDXL model with the CPDS ControlNet to blend text seamlessly with images. You can directly enter the text in the workflow. You must be a member of this site to download the following ComfyUI workflow. Table of ContentsSoftwareHow does this workflow work?Step-by-step guideStep 1: Load workflowStep 2: Install missing nodesStep 3:…
CodeFormer: Enhancing facial detail in ComfyUI
CodeFormer is a robust face restoration tool that enhances facial features, making them more realistic and detailed. Integrating CodeFormer into ComfyUI allows you to improve facial quality seamlessly within their workflows. This tutorial will guide you through installing and using CodeFormer in ComfyUI. Table of ContentsSoftwareCodeFormerDemonstrationStandalone Face restorationStep 1: Download the CodeFormer ModelStep 2: Load…
Face-to-many styles (ComfyUI)
You can use this face-to-many workflow to stylize a face or a person in an art style. This ComfyUI workflow casts a photo into 3 different styles. You can adjust the styles by changing the prompt and the checkpoint model, or adding a LoRA model. You must be a member of this site to download…
3 ways to fix Queue button missing in ComfyUI
Sometimes, the “Queue” button disappears in my ComfyUI for no reason. It may be due to glitches in the updated interface. In this post, I will share a few ways to fix it. Table of ContentsSoftwareFix #1: Zoom in and outFix #2: Reset the new style menuFix #3: Clear browser cache Software Fix #1: Zoom…
How to create an AI QR Code in ComfyUI
Transform a boring black-and-white QR code into a creative, colorful artwork with this workflow. Whether you want to innovate or captivate your audience, you will find it fun to explore the possibilities of this workflow. You must be a member of this site to download the following ComfyUI workflow. Table of ContentsSoftwareHow does this workflow…
How to run Lumina Image 2.0 on ComfyUI
Lumina Image 2.0 is an open-source AI model that generates images from text descriptions. It excels in artistic styles and adhering to the prompt. In this tutorial, I will cover: Table of ContentsSoftwareWhat is Lumina Image 2.0?Run Lumina Image 2.0 on ComfyUIStep 1: Download the Lumina modelStep 2: Update ComfyUIStep 3: Load the Lumina 2.0…
How to generate AI background in ComfyUI
You can quickly generate new AI backgrounds for an existing image in ComfyUI. This workflow keeps the image’s foreground unchanged and generates new backgrounds consistent with the original foreground. You can specify the background in the prompt. Here’s the original image. Here are the product images with new AI backgrounds. You must be a member…
TeaCache: 2x speed up in ComfyUI
Do you wish AI to run faster on your PC? TeaCache can speed up diffusion models with negligible changes in quality. It is simple to implement and is available for image generation with Flux and video generation with Hunyuan Video on ComfyUI. In this tutorial, I will cover: Table of ContentsSoftwareWhat is TeaCache?How does TeaCache…
How to resize images in ComfyUI
Resizing images is a common step in ComfyUI. An image model only works with a limited range of input image sizes. In this tutorial, I will show you how to use the Image Resize node to resize images. Table of ContentsSoftwareResize an image to a specific sizeStep 1: Load JSON workflowStep 2: Install missing nodesStep…