Midjourney_Analog - V1
추천 프롬프트
Comic book illustration
Midjourney, Cinematic, scratches on the film, Close-up, Dramatic, Realistic, cinematic lighting, chiaroscuro, Cinematic Realism, exquisite beauty, Photorealistic, intense shading, film noise, bright highlights, cinematic atmosphere, (Masterpiece), (vivid HDR photography, epic scene, cinematic photography, stop motion, Kodak Portra film, film grain, true color), (best quality), 100mm macro, a high-school delinquent in a Japanese anime setting, sitting on a rooftop in a school uniform with bandages on his fists, sunset sky glowing in the background, city skyline below, anime style inspired by Hirohiko Araki, dramatic perspective with stylized shading and color blocking, combat boots, muscular forearms, sleeves rolled up, loose tie, hair slicked down, rain falling, wet shirt
추천 매개변수
samplers
steps
cfg
resolution
other models
팁
Experiment with CFG scale values around 3.5.
Adjust steps between 14 and 30 for optimal results.
LoRA weight has visible effects starting from 0.4 and works best between 0.6 and 0.8; can be raised up to 1 based on preference.
High quality prompts reduce negative effects.
버전 하이라이트
CFG scale: 3.5, experiment with values
Steps: 14-30, experiment with values
Weight: 0.4-1.
Will start adding visible effects at 0.4+
Works great in the range (0.6-0.8), depending on your preference, experiment with weights up to 1. Experiment with values.
It depends on the model, but you can raise the Lora weight quite high.
High quality prompts reduce the negative effect.
Lora is trained on Midjourney and Flux images. The
LoRA model was created from 70 images taken from publicly available sources on the internet.
LoRA was trained on the FLUX_Dev model
Powered by Midjourney trigger words,
When added to the prompt (Comic book illustration), LoRA draws an illustration.
CFG scale: 3.5, experiment with values
Steps: 14-30, experiment with values
Weight: 0.4-1.
Will start adding visible effects at 0.4+
Works great in the range (0.6-0.8), depending on your preference, experiment with weights up to 1. Experiment with values.
It depends on the model, but you can raise the Lora weight quite high.
High quality prompts reduce the negative effect.
기여자
모델 세부사항
토론
댓글을 남기려면 log in하세요.







