
Workflow name: Chinese ancient style portrait
[Workflow introduction]
Upload 1 headshot for ancient style portrait, select your favorite style to generate image. Now I have built-in 4 style images, you can choose one or re-upload it yourself. Generate prompt words through portrait master combined with joy_caption, combine controlnet to control the body structure, and instantID face migration to the sampler to generate the effect. Finally, use SUPIR to repair facial details. Now the built-in parameter settings are complete, click Run to generate the effect.
[Usage scenario]
Achieve freedom of portrait, select your favorite style image, and then select an image of your own, click Run to get a portrait photo, which is convenient and quick and greatly improves the fun of life.
[Key nodes]
instantID
[Model version]
SDXL
Model name: Hanfu Guofeng Taotian PLUS-V3 new V3-Dream Wonderland.safetensors
Model name: dreamshaperXL v21TurboDPMSDEsafetensors
[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: 0.8
Strength: 0.5
[K sampler]
CFG: 2
Sampling method: dpmpp sde
Scheduler: karras
Noise reduction: 0.7
Workflow name: Chinese ancient style portrait
[Workflow introduction]
Upload 1 headshot for ancient style portrait, select your favorite style to generate image. Now I have built-in 4 style images, you can choose one or re-upload it yourself. Generate prompt words through portrait master combined with joy_caption, combine controlnet to control the body structure, and instantID face migration to the sampler to generate the effect. Finally, use SUPIR to repair facial details. Now the built-in parameter settings are complete, click Run to generate the effect.
[Usage scenario]
Achieve freedom of portrait, select your favorite style image, and then select an image of your own, click Run to get a portrait photo, which is convenient and quick and greatly improves the fun of life.
[Key nodes]
instantID
[Model version]
SDXL
Model name: Hanfu Guofeng Taotian PLUS-V3 new V3-Dream Wonderland.safetensors
Model name: dreamshaperXL v21TurboDPMSDEsafetensors
[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: 0.8
Strength: 0.5
[K sampler]
CFG: 2
Sampling method: dpmpp sde
Scheduler: karras
Noise reduction: 0.7