This is a workflow for Amagi Live-action
**** 2024.06.23 ****
Metadata:
Checkpoint: CampurSari XL - Realistic (https://tensor.art/models/707666883865957727/CampurSari-XL-Realistic)
LoRA:
Amagi Azur Lane (https://tensor.art/models/740510722116807940/Amagi-Azur-Lane-P3)
Film Photography XL (https://tensor.art/models/712488830764192520/Film-Photography-XL-v1)
Prompt
Default/Background: (((ultra realistic, award-winning photo, realistic photo))), fuji velvia, 1girl, AmagiAL, brown hair, bang, purple eyes, thick eye brows, animal ears, high resolution, masterpiece, best quality
Positive Prompt - Outfit: You can put the outfit information here. Just for a better prompt design.
Positive Prompt - General: You can put other prompt that might be interesting here.
Negative prompt (by default): EasyNegative, badhandsv5-neg, verybadimagenegative_v1.3, ng_deepnegative_v1_75
Output Format: 1000 * 1500 (the portrait format)
Steps Basic: number of diffusion steps for the basic image
Steps Hires: number of diffusion steps for the Hires Fix
sampler: dpmpp_2m_sde_gpu
scheduler: karras
Denoise Hires Fix: denoise factor for the enlarged image
10 Random Seed
CFG
Outfits (according to the image provided by the author of the LoRA):
kimono: kimono, sakuramon, sash ,obi, red coat, oil-paper_umbrella
swimsuit: switsuit_Amagi, bikini, sash ,obi, thighstrap
dress: dress_Amagi, bare shoulder, jewelery
Optional: large breasts, cleavage
13. Face Prompt: prompt for the face detailer
Negataive prompt for the face detailer is
"""
EasyNegative, badhandsv5-neg, verybadimagenegative_v1.3, ng_deepnegative_v1_7, 3d, render, cgi, doll, cartoon, painting, illustration, fake, ugly face, 3d modeling, ugly, worst quality, low quality, normal quality, low-res, bad anatomy, blurry face
"""
Amagi Strength: the LoRA weight
Film Photography Strength: the LoRA weight
*** Some of the prompt in the negative prompt seems to be blocked by the system, please check the workflow for the detail if you are interested.