Workflow Name: AI E-commerce Product Model Replacement

【Workflow Introduction】
This workflow is divided into three parts. The first part uses Portrait Master and WD14 Tagger to reverse-engineer prompts. In Portrait Master, you can choose nationality and modify the model's skin tone. The second part uses ControlNet to control the image, then generates images using the SDXL model. The third part optimizes the generated images using the Flux model. Finally, images are composited and processed. Currently, the sampler's internal parameters have been preset, so you can run it directly. Come and give it a try!

【Usage Scenarios】
This workflow allows anyone to take product photos as a model, achieving the regeneration of a model while ensuring the product remains unchanged. It eliminates the need for e-commerce product model shoots and post-production image editing.

【Key Nodes】
instantID

【Model Version】
SDXL
Model Name: dreamshaperXl lightningDPMSDE.safetensors
FLUX
Model Name: flux1 dev fp8 Kjai.safetensors

【LoRA Model】
None

【ControlNet Application】
control lora depth rank256
Start Time: 0
End Time: 1
Strength: 0.6

control lora canny rank256
Start Time: 0
End Time: 1
Strength: 0.5

【K Sampler】
CFG: 2
Sampling Method: dpmpp sde
Scheduler: karras
Denoising: 1