「トレーナーさぁあん！」

このシーン好き。【備考】公式キャラストリー第４話より参照。参考画像機能を使用。公式の再現やる度に、公式が一番可愛いと思い知らされる… ゴリゴリにエフェクト掛けたところでどうしようもない

#Lens flare #Letterboxed #Track jacket #Uma Musume Pretty Derby #Nishino Flower #Tracen Academy

Veröffentlicht am Jul 19, 2026

ニシノフラワーが可愛いすぎて

1girl, solo, nishino_flower_(umamusume), child, horse ears, bob cut, blunt bangs, horse tail, big eyes, tracen training uniform, red and white track jacket, white shirt, red pants, red ear covers, leaning_forward:0.5, looking at viewer, happy, smile, blush, closed eyes, open mouth, outdoors, stands at the stadium, fence, running track background, running track, stadium lights, forest background, forest, rim lighting, dramatic light, light particles, depth of field, aerial perspective, letterboxed, Kyoto Animation, Kyoto Animation style, Kyoto Animation aesthetics, soft facial features, cinematic lighting, detailed background, delicate lineart, ultra high detail, anime art style, (cool tones:1.4), (blue tint:1.3), (intense backlighting:1.4), (vivid colors:1.2), (high-saturation:1.1), (high detail:1.5), (ultra-sharp focus:1.5), fully detailed realistic environment, subsurface scattering, vibrant pastel tones, anime coloring:1.5, photo style, cinematic lighting:1.3, shallow depth of field, bokeh, soft focus, HDR effect, volumetric light, strong lens flare, blue ambient light, cinematic color grading, rich crystal clear atmosphere, (((chromatic_aberration:2.0))),((noise,glitch,hatching \(texture\))),(film grain),(over exposure:1.4), beautiful composition, cinematic lighting, extremely detailed, 8k, cinematic postprocessing, masterpiece, best quality, highest quality, absurdres, very aesthetic, super detailed, detailed eyes, 1girl, solo, nishino_flower_(umamusume), child, horse ears, bob cut, blunt bangs, horse tail, big eyes, tracen training uniform, red and white track jacket, white shirt, red pants, red ear covers, leaning_forward:0.5, looking at viewer, happy, smile, blush, closed eyes, open mouth, outdoors, stands at the stadium, fence, running track background, running track, stadium lights, forest background, forest, rim lighting, dramatic light, light particles, depth of field, aerial perspective, Kyoto Animation, Kyoto Animation style, Kyoto Animation aesthetics, soft facial features, cinematic lighting, detailed background, delicate lineart, ultra high detail, anime art style, (cool tones:1.4), (blue tint:1.3), (intense backlighting:1.4), (vivid colors:1.2), (high-saturation:1.1), (high detail:1.5), (ultra-sharp focus:1.5), fully detailed realistic environment, subsurface scattering, vibrant pastel tones, anime coloring:1.5, photo style, cinematic lighting:1.3, shallow depth of field, bokeh, soft focus, HDR effect, volumetric light, strong lens flare, blue ambient light, cinematic color grading, rich crystal clear atmosphere, (((chromatic_aberration:2.0))),((noise,glitch,hatching \(texture\))),(film grain),(over exposure:1.4), beautiful composition, cinematic lighting, extremely detailed, 8k, cinematic postprocessing, masterpiece, best quality, highest quality, absurdres, very aesthetic, super detailed, detailed eyes,

Parameter anzeigen

Qualitäts-Tag: ﹝Prompts﹞, nhl-001, sketchy, cutest, pastel, beautiful anime aesthetic, very aesthetic, high definition, amazing quality, masterpiece, best quality, very aesthetic, highres, absurdres, sensitive
Größe: 1024 x 674
Sampling-Schritte: 33
Sampling-Methode: Euler a
CFG scale: 3.1
Negativ: nsfw, worst quality, bad quality, low quality, lowres, anatomical nonsense, artistic error, bad anatomy, interlocked fingers, extra fingers, text, artist name, signature, bad feet, extra toes, ugly, poorly drawn, censor, blurry, watermark, simple background, transparent background, old, oldest, glitch, deformed, mutated, disfigured, long body, bad hands, missing fingers, extra digit, fewer digits, cropped, very displeasing, sketch, jpeg artifacts, username, censored, bar_censor, mosaic_censor, conjoined, bad ai-generated, nsfw, long neck, skin blemishes, skin spots, acne, the wrong limb, error, black line, excess hands

Gesichtskorrektur

Hohe Auflösung

Verwendetes Modell und LoRA