【Workflow Introduction】
First, open this workflow. You need to upload two images on the left side: one base image and one style image. Use "Runninghub Captioner" to reverse-engineer the prompt for the base image, extract the main color palette tones through the "LayerUtility: Get Main Colors" node, then finely control the image and depth, and finally use Flux redux for style transfer. Combine it with the sampler to generate the final image.
【Usage Scenario】
This workflow requires only two images to achieve any style transformation. It is convenient, fast, and efficient. All built-in parameters are preset. Let your imagination run wild!

【Key Nodes】
Flux redux

【Model Version】
Flux
Model Name: flux1 redux dev.safetensors

【LoRA Model】
Model Name: flux1 depth dev lora.safetensors

【Controlnet Application】
None

【K Sampler】
Sampling Method: euler
Scheduler: simple
Denoising: 1
【Custom Sampler】
Sampling Method: euler
Scheduler: simple
Denoising: 0.38