Flux to SDXL Style with IP Adapter
About this model
Version 1.1: Added IP Adapter Noise node which sharpens up style details significantly. I didn't change it in the workflow, but setting a weight_style to 1.8 instead of 1 can apply the style more completely across the image, more than just the foreground. Like all of these settings, the benefit is subjective, so what may work best for one style input may work better without it on another input image.
Version 1.0: This ComfyUI workflow is useful for rendering a Flux image and then applying a style over it with SDXL's IP Adapter and Controlnet ability.
Adjusting the end percent on the Apply Controlnet node from 0.5 to 0.7 can increase how closely the image adheres to the composition of the original flux image. The controlnet model that's used can be downloaded here:
IP adapter models and various other nodes that are non-standard can be downloaded inside ComfyUI's model and node manager.
I'm using Flux Dev with a niji anime lora:
SDXL model I'm using is Jibmix:
Tags
Related Models
Similar AI models you may like
ON-THE-FLY 实时生成!Wan-AI 万相/ Wan2.1 Video Model (multi-specs) - CausVid&Comfy&Kijai - workflow included
【WAN2.1】IMG to VIDEO
ComfyUI Image Workflows
UltraReal Fine-Tune
Hourglass Body Shape SD1.5/SDXL/PONY/FLUX | olaz
WAN 2.2 Workflow T2V-I2V-T2I (Kijai Wrapper)