sebastiankamph

Flux ControlNet - Ultimate Workflow

Video guide https://youtu.be/B3HBAiGuySkIn this guide we’ll go over a workflow for using FluxControlNetwithin Comfy. You will be able to easily use one or more ControlNets just by flipping a switch. ControlNet will control your output image by the input image you load.If you don't have Comfy or the Comfy Manager installed, you can find a guide on it here: https://www.youtube.com/watch?v=KTPLOqAMR0sDrag and drop the .json file (download at bottom) into your Comfy. If you get red nodes, make sure to go into your Managerand Install all missi...

AI Glossary

4x-Ultrasharp- A popular upscaling model that upscales your image 4x times, but can also be used for other sizes.AI Upscaler- Software that uses AI models to increase image resolution. Unlike traditional methods, AI upscalers can add detail.AnimateDiff- A tool that creates AI animations. It generates a sequence of coherent frames, allowing for motion in generated scenes. AnimateDiff can create anything from small movements to detailed character animations.Automatic1111- One of the first and most popular user interfaces for Stable Diffusion. It&...

Local Image2Video in ComfyUI - CogVideoX-5b

This is a very good image2video model that works within ComfyUI. It's limited to 720x480 but the quality in that resolution is very good and it understands prompts.Video guide here https://youtu.be/--sbejiJ858This should work on GPU 6gb minimum, but will be slow. My 4090 renders in about 5 minutes without optimizations. If you want speed, go for the 48gb vram machine from my sponsor partners at https://thinkdiffusion.comDownload workflow from bottom of this post,drag & dropinto ComfyGo into your Managerand Install Missing Custom Nodes.After...

Improve text and prompt understanding further in ComfyUI

Video here: https://youtu.be/xcR-tzLi_7YThere's a small little node called CLIPAttentionMultiplywhich changes how the text of your prompt is understood. It changes the multiplication factor (default 1) of different values.Think of it like this, you can increase how important your prompt is. So with these values here we're increasing prompt understanding by a small margin, but large enough to make a difference without breaking the images. QKV? Query - Key - Valueq (query): Weight of tokens as they influence each other in a sentencek (key...

Even better text in Flux with new Text Encoder.

Now you can improve text results with just swapping one file.Video guide here: https://youtu.be/gCzJI4sKr1IDownload text encoder: https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14/resolve/main/ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors?download=trueComfy: Place in /models/clip/Forge: Place in /models/text-encoder/Load text encoder by replacing clip_l in DualClip LoaderOr select it in VAE/Text-encoder for ForgeThat's it! Generate away and get better text results (mostly).

LLM in Comfy. Automatic prompts!

DOWNLOAD example workflow in bottom of post!Video guide here: https://youtu.beMYSjvwD_sWith these nodes you will connect a LLM to Comfy and get great prompts for your images. Especially great for Flux, which is trained for natural language.How to installGo into your managerSelect "Custom Nodes Manager"Search for Searge LLM and press InstallDownload https://huggingface.co/MaziyarPanahi/Mistral-7B-Instruct-v0.3-GGUF/resolve/main/Mistral-7B-Instruct-v0.3.Q4_K_M.ggufCreate the directory and place model in /ComfyUI/models/llm_gguf/Restart yo...

Flux NF4 - Upscaler Workflow in Comfy

DOWNLOAD BELOW!Video: https://youtu.be/L5BjuPgF1DsWith this workflow you'll be able to upscale your newly Flux generated images, and if you follow the video guide, I will show you how you can upscale infinitely (if you have time to wait for the generations).Download the latest Flux NF4 model: https://huggingface.co/lllyasviel/flux1-dev-bnb-nf4/tree/mainPlace in /models/checkpoints/For troubleshooting, see my getting started with Flux NF4 guide.SettingsFor this upscaling process we'll use the Ultimate SD Upscale node. As we're using ...

Flux in Forge - How To Install

Video guide here: https://youtu.be/uTFdl5s6Vb0If you don't have Forge already installed, here's a guide to get it installed: https://www.youtube.com/watch?v=mHvnHA04sbcDownload the Flux models----> Step 1 Download Latest version of Flux NF4 12gb (recommended):https://huggingface.co/lllyasviel/flux1-dev-bnb-nf4/tree/main----> Step 2 Put inside /Forge/webui/models/Stable-diffusion/----> Step 3 Run Update.bat----> Step 4 Start your Forge - Select FLUX and FLUX model.Generate!NF4 or FP8?NF4 is significantly faster than other versions of Flu...

Flux - How to for ComfyUI

Installation steps for ComfyMinimum Hardware RequirementsVRAM: 8-12GB+ (16-24gb recommended)Steps to FollowUpdate your Comfy UIIf you don't have Comfy, here's how to install it: https://youtu.be/KTPLOqAMR0sDownload Necessary ModelsDownload t5xxl_fp8_e4m3fn.safetensors and clip_l.safetensors from Hugging Face.Place these files in the ComfyUI/models/clip/directory.If you have high vram and ram, you can download the FP16 version (t5xxl_fp16.safetensors) for better results. For lower memory usage, stick with t5xxl_fp8_e4m3fn.safetensors.Dow...

Patreon Exclusive SD3/SDXL/SD1.5 Upscaling Comparisons

Uncut Patreon exclusive where I compare upscaling with the various SD models (not upscaling models, but the Stable Diffusion models).

Multiple ControlNet workflow for ComfyUI

In this guide we’ll go over a workflow for using ControlNet within Comfy. You will be able to easily use one or more ControlNets just by flipping a switch. ControlNet will control your output image by the input image you load.If you don't have Comfy or the Comfy Manager installed, you can find a guide on it here: https://www.youtube.com/watch?v=KTPLOqAMR0sDrag and drop the .json file (download at bottom) into your Comfy. If you get red nodes, make sure to go into your Managerand Install all missing custom nodes.Install ControlNet models b...

Simple sketch to image Comfy workflow

I was playing around with sketch to image within Comfy and figured I'd share this simple workflow with you.Drag & drop the .json workflow (download in bottom) or above image into Comfy.Go into the manager and install any missing custom nodes.Load the model you prefer.Set your subject prompt in the top box and your style prompts in the bottom box.Negative prompts go in the red node.Using an LCM lora to speed up the generations, this is optional. Feel free to disable this to increase quality, but remember to change the sampler.8 Steps in the ...

How to reshape light with AI

I'll show you how to change any light with Stable Diffusion and ComfyUI. This is IC-Light. Workflows https://github.com/kijai/ComfyUI-IC-Light/tree/main/examplesHow to install Comfy https://youtu.be/KTPLOqAMR0sIC Light Github (not needed, just for curious people) https://github.com/kijai/ComfyUI-IC-Light

Supir image restoration and upscaling guide for Comfy

Supir helps you keep control and consistency in images while upscaling or restoring. It’s a simple Comfy workflow you can download (see bottom of page) and drag & drop into your local Comfy or cloud solution.Go into the manager and select “Install Missing Custom nodes”. Select any nodes that appear in the list and press Install. Then press restart and refresh page.Select an SDXL model. I used a lightning model to increase speed. Remember to adapt your CFG to your model (see further down). Try various lightning models to improve your resul...

Stable Cascade in Automatic1111 & Forge

Go into your extensions tabSelect Install from url and copy/paste https://github.com/blue-pen5805/sdweb-easy-stablecascade-diffusers.gitThis extension will probably be replaced at a later date and also be available from the installed tab eventually.Click installGo into the Installed tabClick Apply and restart UIStable Cascade should now be available as a tabOnce you start a generation, the model will be auto-downloaded. You don’t need to download it yourself.Prompt what you want to see and generate your amazing images! Make sure to run the si...

How to install Forge for Stable Diffusion. Detailed guide.

Method A: One Click Install1. Go to GitHub - lllyasviel/stable-diffusion-webui-forge and navigate to this area:2. Download the .7z installer file by clicking the link above. The file is a compressed archive that can be opened by installing 7-Zip, which is free.3. Create a new folder in your drive and extract the contents of the file into the new folder.4. Ensure that you have the latest version of Forge by double clicking on update.bat.5. Double click on run.bat to begin using Forge.Method B: Manual InstallationIf in case the one-click installa...

Turn Images2Video with SVD 1.1

SVD Image2Video. Stable Video Diffusion subscriber guide.In this guide we’ll be focusing on getting Stable Video Diffusion 1.1 to work in ComfyUI. This guide is accompanied by the Youtube video found here: https://youtu.be/ue1qHBvlurAIf you need help installing ComfyUI, I recommend this video: https://youtu.be/KTPLOqAMR0s1. DOWNLOADING AND INSTALLING STABLE VIDEO DIFFUSION 1.1For Stable Video Diffusion 1.1 locally download the model from this link.Press the download button marked above.From the root folder of your ComfyUI installation folder,...

Use Same Face - Ip Adapter FaceID Plus V2

IP-Adapter-Face-ID-Plus-V2 Automatic1111 Installation and Usage GuideINSTALLATIONEnsure that your ControlNet extension is up to date enough that it already has the Multi-Inputs feature:If not, go to the extensions tab:Click on “Check for updates” and ensure that the checkbox beside “sd-webui-controlnet” before pressing “Apply and restart UI”. Wait for the extension to install completely before continuing. For best results, start a new instance of A1111.DOWNLOADING MODELSGo to https://huggingface.co/h94/IP-Adapter-FaceID/tree/main an...

AnimateAnyone Patreon supporter workflow

Workflow from the video guide on AnimateAnyone here: https://youtu.be/MGvx37ccCOMhttps://github.com/MrForExample/ComfyUI-AnimateAnyone-EvolvedInstall (You can also use ComfyUI Manager)Clone this repo into the Your ComfyUI root directory\ComfyUI\custom_nodes\ and install dependent Python packages:cd Your_ComfyUI_root_directory\ComfyUI\custom_nodes\git clone https://github.com/MrForExample/ComfyUI-AnimateAnyone-Evolved.gitpip install -r requirements.txt# If you got error regards diffusers then run:pip install --force-reinstall diffusers>=0.26.1Do...

RuinedFooocus indepth guide & detailed usage

Detailed guide to install and use RuinedFooocus for Patreon Subscribers. This is a text & image guide for the video guide here: https://youtu.be/7ncu4f-PFGIhttps://github.com/runew0lf/RuinedFooocusScroll down on the page and find the download link to the latest version.https://github.com/runew0lf/RuinedFooocus/releases/download/Release-1.25.2/RuinedFooocus_win64_1-25-2.7zDownload the package and uncompress it, you might need to install 7zip if you can’t uncompress .7z files.https://www.7-zip.org/After you’ve uncompressed the files and folde...

SDXL Turbo - Detailed Indepth Guide for Patreon Subscribers

SummaryWith SDXL Turbo you will be able to generate images in just a few steps, in many different interfaces. This guide will show how to get it running in automatic1111 and ComfyUI.SDXL Turbo stands out as a remarkable engineering achievement. Its Turbo feature enables lightning-fast generation of vast numbers of images. Currently, Comfy leads the pack in utilizing this technology. While Comfy delivers undeniable speed and quality, A1111 comes remarkably close.Due to the limited generations per image, any error correction or modification time ...

SVD Image2Video. Stable Video Diffusion subscriber guide.

In this guide we’ll be focusing on getting Stable Video Diffusion to work in ComfyUI. Once available in automatic1111, this guide might be updated, or a separate guide created. This guide is accompanied by the Youtube video found here: https://youtu.be/HOVYu2UbgEEIf you need help installing ComfyUI, I recommend this video: https://youtu.be/KTPLOqAMR0sFor Stable Video Diffusion locally you will have to download an SVD model. You only need to download ONE of these, but you can test multiple. The current options are:Svd.safetensors (14 frames) <...

FaceFusion face swapper detailed subscriber guide. Install + How to use

FaceFusion is a next generation face swapper and enhancer. It can face swap both still images and videos through multiple different face swapping models. In this guide, we’ll go through how it works, all the settings and how to achieve a good result. This is an indepth guide from the video here: https://youtu.be/QU2inl3mobsInstallation WindowsPythonwinget install -e --id Python.Python.3.10PIPpython -m ensurepipGITwinget install -e --id Git.GitFFmpegwinget install -e --id Gyan.FFmpegReboot your system in order for FFmpeg to function properly.s...

Detailed Guide for Text to 3D to 2D Animation (Mootion + AnimateDiff)

This is a detailed text guide for the video guide on Youtube found here: https://youtu.be/LynYh_qrs8oGo to https://discord.com/and sign up for an account if you don’t have one. Login and then click the link https://discord.com/invite/ZStwxNxnDT to join Mootion’s Discord.Scroll down and click on one of the creation channels like #creation-1Type /motion to get started and select what you want to see.Prompt: This is what you want the character to do.Character: Select preferred character.Inplace: True will keep your character and camera static....

EARLY ACCESS VIDEO: NEW DALL-E 3!

EARLY ACCESS: Turn ANY LOGO into ART!

EARLY ACCESS: New Photorealism Model. "Realistic Stock Photos"

EARLY ACCESS: Make Your Own Clouds in Stable Diffusion

Early Access video of how to create your own shaped realistic clouds in Stable Diffusion.

ComfyUI SDXL Workflow - Searge 4.0

My good friend Searge has been working on his ComfyUI SDXL workflow for quite some time and I can recommend it if you&#39;re a fan of ComfyUI. It&#39;s got about almost everything you would need.

AI Upscaling Model Database

Huge database for AI upscaling models. It replaces the old wiki where upscaler models were found previously.