Img2Img-Controlnet-ComfyUI This repository contains the Img2Img project using Controlnet on ComfyUI. It focuses on two styles GTA and Anime. ## Workflow 1. : The process starts by passing the input image to the LineArt and OpenPose preprocessors. 2. : The preprocessed images are fed into ControlNet. 3. : ControlNet outputs are then passed to the Efficient Loader, which loads the weights. 4. : Finally, the loaded data is processed through KSampler to generate the output image. ## Also deployed on - ## Load the model in ComfyUI - ## Prompts Used: ### GTA 1. : In the style of Grand Theft Auto, loading screens, (palm trees), GTA style artwork, highly detailed, urban scene with numerous palm trees, neon lights, and graffiti, trending on ArtStation, preserving the individual's race, color and hair. 2. : (worst quality, low quality = 1.3), drastic change in facial features ### Anime 1. : In the style of classic anime, vibrant colors, large expressive eyes, highly detailed backgrounds, intricate character designs, dynamic poses, soft shading, fantasy or urban settings with cherry blossoms, traditional Japanese architecture, and bustling cityscapes, preserving the indvidual's race, color and hair. 2. : (worst quality, low quality = 1.3), drastic change in facial features ## Installation 1. : 2. : 3. : Copy the custom nodes and models listed to the respective directories in your ComfyUI installation. ## Custom Nodes ### Comfyroll Studio - CR Aspect Ratio - CR Multi-ControlNet Stack ### ComfyUI - PreviewImage - SaveImage - LoadImage ### ComfyUI Nodes for Inference.Core - CannyEdgePreprocessor - OpenposePreprocessor - LineArtPreprocessor ### Efficiency Nodes for ComfyUI Version 2.0+ - Efficient Loader - XY Input: CFG Scale - XY Plot - KSampler (Efficient) ## Models - Checkpoint and VAE - Checkpoint: & - VAE: ## KSampler Settings The following settings were used in the KSampler (Efficient) node for ComfyUI: - : 4091745839 - : 20 - : 4.0 - : dpmpp_3m_sde_gpu - : karras - : 1.00 - : auto - : true These settings help in achieving efficient sampling while maintaining quality output in the ComfyUI framework. ## Docker A Docker file is included for easy setup and deployment. ---
