青髪&紫髪チャイナドレスさん その1
2026/4/21使用したAI Stable Diffusion XL
年齢制限 全年齢
AIイラスト生成で最近好きになったモデルの Flowing Light Rendering v10 でIRIAM配信者さんのアバターを基に白いチャイナ服で点心を美味しく食べる姿をAI画像生成しました
レンゲとか食器類を綺麗に持たせることが難しかったので、ソコは今後の研究に生かそうと思いました
プロンプト
1girl, solo, dynamic pose, dynamic angle, looking at viewer, sitting, upper body, hands on table, eating, food, plate, bowl, meatballs, dumplings, dim sum, bamboo steamer, teacup, blue and white porcelain, indoors, chinese lattice window, vase, pink flower, camellia, table, sunlight, soft lighting, detailed background, depth of field, cinematic lighting, masterpiece, high score, great score, absurdres, BREAK ((split-color hair:1.3), ((purple hair:1.2), (dark blue hair:1.2)):1.3), (two-tone hair:1.2), (long hair:1.2), (long wavy hair:1.3), bangs, (white hair:-1), (pink hair:-1), hair ornament, white flower, hairpin, earrings, tassel earrings, red tassel, (blue eyes:1.2), (purple eyes:-1), japanese_girl, (medium breasts:1.3), (curvy:1.3), cleavage, (voluptuous:1.2), (shiny skin, gleaming skin:1.4), smile, open mouth, blush, BREAK (chinese clothes, cheongsam:1.2), (wide sleeves, long sleeves), (white dress:1.3), purple accents, black ribbon, frog button, ((8k, masterpiece ,best quality ,ultra-detailed)), game cg, masterpiece, year 2025, newest, (perfect face:1.1025), (perfect arms:1.1025), (perfect legs:1.1025), (perfect hands:1.1025), (perfect fingers:1.1025), <lora:xl_more_art-full_v1:0.6> <lora:add-detail-xl:1> <lora:Fixhands_anime_bdsqlsz_V1:1>
ネガティブプロンプト
(worst quality, low quality, normal quality, bad quality:1.4), (lowres, jpeg artifacts, compression noise:1.2), (bad anatomy, deformed, disfigured, malformed limbs:1.4), (bad hands, poorly drawn hands, missing fingers, extra digits, fused fingers, too many fingers, webbed fingers:1.4), (poorly drawn face, ugly, bokeh, asymmetrical face, cloned face:1.3), bad proportions, gross proportions, long neck, extra arms, extra legs, disjointed, text, signature, watermark, username, logo, 3d, 3d render, cgi, photorealistic, realistic, cartoon, sketch, monochrome, grayscale, multiple views, comic, oversaturated, blurry, out of focus, depth of field artifacts, aliasing, bad perspective, 3rd party watermark, artist name,
Steps
28
Scale
7
Seed
3943020031
Sampler
Euler a
Noise
0.7
Strength
コメント

 
zanteiban(ざん) zanteiban(ざん) 2023年6月より活動開始 91投稿23フォロー29フォロワー 艦これ、ウマ娘、配信者さんのAI画像生成をしています AI生成環境はGoogle Colab、Stable Diffusion Web UI Forgeを使っています AI画像生成は始めて半年くらいです、皆さんと仲良く出来れば嬉しいです