Workflow name: Dummy/Mannequin to Real Person
[Workflow Introduction]
Open the workflow, first you need to upload three images, 1 facial image, 1 clothing dummy image, and 1 background image, and reverse the three images. First, use the SDXL model combined with brushnet and controlnet to generate the first image pair. Then use the FLUX model to refine the image, and finally use the FLUX model to repair the face, enlarge the image, and generate the final image. The parameters are built-in, just click Run, come and try it!
[Usage scenario]
Upload 3 images to generate the desired real-life clothing model with background. It is convenient, fast and practical. Give full play to your creativity!
[Key nodes]
SDXL
[Model version]
SDXL
Model name: Wanxiang XL Hyperrealistic Photography V8.4 V8.4.safetensors
FLUX
Model name: flux1-dev-fp8-Kijai.safetensors
[ControlNet]
control-lora-canny-rank256.safetensors
Start time: 0.1
End time: 1.0
Intensity: 0.7
[LoRA model]
None
[Custom sampler]
Scheduler: sgm uniform
Noise reduction: 0.5
Sampler: euler ancestral
[K sampler]
Scheduler: normal
Noise reduction: 0.45
Sampler: euler ancestral
Sign In