PixAI 멤버십
PixAI
PixAI
Generate
Sign in
홈
생성
모델
Studio
NEW
콘테스트
Mio.2 창작
AI 도구
NEW
가이드

사용자 LoRA

XL
복장

Formidable's Evening Gown (Azur Lane) | 可畏的晚礼服(碧蓝航线)

#이브닝 드레스#비디오 게임#벽람항로
AI 도구
  • AI 애니메 생성기
  • 애니메 피규어 생성기
  • 캐릭터 시트 생성기
  • 잡지 표지 생성기
  • 봉제인형 생성기
  • 대형 동상 생성기

찾아보기

  • 인기 태그
  • 랭킹
  • 모델 마켓
  • 콘테스트
  • 뉴스

소개

  • 가이드
  • PixAI 블로그
  • Tsubaki.2
  • Mio 소개
  • 콘텐츠 규칙

요금 및 도움말

  • 멤버십
  • 크레딧 팩
  • 연락처

모바일 앱

  • PixAI 앱 다운로드
  • 앱 스토어
  • 구글 플레이
© 2026 PixAI
  • 개인정보
  • 개인정보 처리방침
  • 저작권 정책
  • 저작자 표시
  • 특정상업거래법
Mio with expression sulk

커버 제거됨: 콘텐츠 규칙 위반

콘텐츠 검사를 통과하지 못했지만 걱정하지 마세요. 모델은 여전히 완전히 검색 가능하고 사용할 수 있습니다! 모두에게 적합한 커버로 바꿔 주세요.

업로드 날짜
2025. 7. 15. 오전 1:11
이용수
10
리뷰
리뷰 없음
트리거 단어

white evening gown, blue cross-laced slit, blue-white cape, black hair spikes

권한
  • 이미지 생성 및 공유 허용
  • 다른 사용자가 내 모델을 다운로드하도록 허용합니다
  • 생성된 이미지의 상업적 이용 허용

설명

前言(Preamble):从可畏那里借了白色晚礼服。I took a white evening gown from Formidable😋更新日志(Update Log):2025.07.10:尝试使用正则化技术制作服饰 LoRA,后续会做些小调整(也许?)Attempted to create a clothing LoRA using regularization techniques, with potential minor adjustments to follow (maybe?)主要触发词:white evening gown,blue cross-laced slit,blue-white cape,black hair spikes。次要触发词:see-through veil,white veil,pumps,white shoes,empty picture frame。Primary trigger word: white evening gown, blue cross-laced slit, blue-white cape, black hair spikes.Secondary trigger words: see-through veil, white veil, pumps, white shoes, empty picture frame.训练集(Training Set):number of images = 278_default = 27epochs = 15[Illustrious XL]Evening Gown (Anniversary Memories) v1[LoRA][REG].toml:model_train_type = "sdxl-lora" pretrained_model_name_or_path = "D:/AIGC/ComfyUI-AKI/models/checkpoints/Illustrious XL v1.0.safetensors" train_data_dir = "D:/AIGC/lora-scripts/train/Evening Gown (Anniversary Memories)/train" reg_data_dir = "D:/AIGC/lora-scripts/train/Evening Gown (Anniversary Memories)/reg" prior_loss_weight = 1 resolution = "1024,1536" enable_bucket = true min_bucket_reso = 512 max_bucket_reso = 2048 bucket_reso_steps = 64 bucket_no_upscale = true output_name = "[Illustrious XL]Evening Gown (Anniversary Memories) v1 EP" output_dir = "D:/AIGC/lora-scripts/output/LoRA/[Illustrious XL]Evening Gown (Anniversary Memories) v1[LoRA][REG]" save_model_as = "safetensors" save_precision = "bf16" save_every_n_epochs = 1 save_state = false max_train_epochs = 20 train_batch_size = 2 gradient_checkpointing = true gradient_accumulation_steps = 13 network_train_unet_only = true network_train_text_encoder_only = false learning_rate = 1 unet_lr = 1 text_encoder_lr = 1 lr_scheduler = "constant" lr_warmup_steps = 0 optimizer_type = "Prodigy" network_module = "networks.lora" network_dim = 8 network_alpha = 4 randomly_choice_prompt = false positive_prompts = "(masterpiece, extremely aesthetic, best quality, amazing quality), newest, highres, absurdres, cowboy shot, from side, sleepy, 1girl, elf, frieren, long hair, white hair, twintails, black hair spikes, pointy ears, crystal earrings, red gemstone, parted bangs, thick eyebrows, half-closed eyes, green eyes, blush, open mouth, parted lips, bare shoulder, collarbone, white evening gown, blue cross-laced slit, hand up, open hand, yawning, squeans, blue-white cape, white background" negative_prompts = "(worst aesthetic, worst quality, low quality), low details, bad quality, poorly drawn, (logo, watermark, signature, artist name), (bad hands, mutated hands), extra digits, fewer digits, bad feet, multiple views, 4koma, furry, anthro" sample_width = 1024 sample_height = 1536 sample_cfg = 5.5 sample_seed = 2333 sample_steps = 28 sample_sampler = "euler" sample_every_n_epochs = 1 log_with = "tensorboard" log_prefix = "[Illustrious XL]Evening Gown (Anniversary Memories) v1 " logging_dir = "./logs/LoRA" caption_extension = ".txt" shuffle_caption = true keep_tokens = 4 max_token_length = 255 seed = 1919810 mixed_precision = "bf16" xformers = true lowram = false cache_latents = true cache_latents_to_disk = true persistent_data_loader_workers = true optimizer_args = [ "decouple=True", "weight_decay=0.01", "use_bias_correction=True", "d_coef=2.0" ]

댓글