See GitHub page for more details.

Overview

I've created 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. This workflow can use LoRAs, ControlNets, enabling negative prompting with Ksampler, dynamic thresholding, inpainting, and more. Please note that this is not the "correct" way of using these techniques, but rather my personal interpretation based on the available information.

Main Features

• Switch between image-to-image and text-to-image generation

• For text-to-image generation, choose from predefined SDXL resolution or use the Pixel Resolution Calculator node to create a resolution based on aspect ratio and megapixel via the switch

• Load ControlNet models and LoRAs

• Sampling with model sampling Flux and Sampler Custom Advance node, based on the original official demo workflow

• sampling with dynamic thresholding and Ksampler Advance node, enabling positive and negative conditioning with FluxGuidance

• Simple inpainting

• High-res fix like iterative upscaling with Tiled Diffusion