Reproducción automática
Ejecutar en local
gemi_minimax_v1.safetensors
148 MB · SafeTensor · bf16
Las descargas las sirve Civitai. Algunos creadores piden iniciar sesión en Civitai primero.
Sobre este modelo
MINIMAX H3 · LoRAs
by tigertakato - gemi_minimax_v1
Notas del creador
This is a LoRA of an original character named Gemi. I aimed for a natural, approachable face like a woman you might see on the street,
Gemi is a fictional character created with AI and does not represent any real person.
GemiというオリジナルキャラクターのLoRAです。街で見かける普通の女性のような、自然で親しみやすい顔立ちを目指して作りました。
GemiはAIで生成した架空のキャラクターであり、実在の人物ではありません。
SHA256
DE2E5F261B5F6C2607FF4FFC8F4FF3BA46E8132474D4F0335C32569C851A25E5
ID de modelo de ModelTrends.ai
#26704
Denunciar contenido
Renders de ejemplo
Prompts y ajustes compartidos por quienes hicieron estos renders en Civitai. Elige un render para ver cómo se hizo.
Ajustes
Tamaño
2432x1344
Prompt
integrated_multimodal_description: [Shot 1] Live-action, cinematic, a medium shot inside a bright maid café with pastel pink walls, white lace curtains, heart-shaped wall clocks, and warm ceiling lights. A young Japanese woman in her early twenties with fair skin, large round eyes, and straight black shoulder-length hair with a blunt fringe steps out from the kitchen carrying a tray, wearing a white lace headdress, a black dress with puffed short sleeves, a frilled white apron tied in a large bow, a lace-trimmed collar, and knee-high white socks. On the tray sits a plate of omurice with a ketchup heart drawn on it and a tall pink melon soda. The camera trucks left with small amplitude at slow speed following her as she turns toward the seating area, smiles brightly, and the cheerful young woman with a high, bright voice and an upbeat sing-song delivery (S1) says: <d>[Japanese] お帰りなさいませ、ご主人様!</d> She closes her lips and starts down the aisle. [Shot 2] At 00:03.500, the camera cuts to a low tracking shot moving backward ahead of her as another maid pushing a loaded dessert cart blocks the narrow aisle, with occupied chairs pushed out on both sides leaving almost no gap. Without slowing, she lifts the tray high on her right hand, turns her shoulders sideways, and slips through the gap in one smooth pivot, her pleated skirt and apron frills swinging out and settling again. The melon soda's ice cubes rock but the tray stays perfectly level. She glances back at the cart with a small triumphant grin. [Shot 3] At 00:07.000, the camera cuts to a shot over a seated customer's shoulder at a small table. She arrives, lowers the tray, and sets the omurice down in front of him. She leans in, forms a small heart with both hands over the plate, and the cheerful young woman (S1) says: <d>[Japanese] おいしくなあれ、萌え萌えきゅん!</d> She closes her lips and tilts her head with a bright grin while the customer freezes with his fork halfway to his mouth.
overall_soundscape: Cheerful chatter from other tables, clinking cutlery, and a low espresso machine hiss run throughout. Rubber cart wheels squeak on tile as she passes, her shoes tap quickly on the floor, and the melon soda's ice cubes clink and settle after the pivot. The plate meets the table with a light clack.
non_diegetic_music: A bouncy major-key synth-pop loop at a fast tempo with a bright plucked lead and handclaps. A short cymbal swell rises through the pivot and lands on a full band hit as she straightens.
Ajustes
Tamaño
704x1056
Prompt
integrated_multimodal_description: [Shot 1] Live-action cinema, photorealistic, vertical
selfie framing shot on a phone front camera held at arm's length with slight natural
handheld shake, mild wide-angle selfie distortion, visible skin texture and pores, fine
grain, night. Two young Japanese women in gyaru style are pressed cheek to cheek on a
rooftop party terrace high above a city at night, string lights and paper cups behind
them and the whole skyline burning with lit office windows below and beyond the railing;
the phone screen throws a cold light up onto their faces. Closest to the camera, a woman
in her early twenties with long loosely curled milk-tea-blonde hair, heavy eye makeup
with false lashes, large gold hoop earrings, a white ribbed tank top and a short denim
skirt holds the phone out at arm's length and beams into the lens while her hair whips
across her face in the wind. Leaning in over her shoulder is a deeply tanned woman with
braided hair, neon-green nails and a cropped neon top. Far beyond the railing an
enormous tabby cat as tall as the towers stands between the buildings in the dark. Three
searchlight beams sweep up from the streets and cross the night sky, and as they catch
the animal its fur, whiskers and huge eyes flare out of the darkness, the eyes shining
back a flat green. The cat shifts its weight forward and swipes one massive paw across a
nearby high-rise, bending the upper floors and sending glass and chunks of concrete
falling into the street far below, and the dust cloud rising off the impact makes the
three shafts of light suddenly solid and visible. Both women first turn their heads and
shoulders toward the cat and react with exaggerated surprise and delight, then pivot back
to the lens one after another and snap into flashy influencer poses: the tanned woman
throws a peace sign beside her cheek and leans in with an over-the-top grin, while the
woman with the milk-tea hair tilts her head, pouts and lifts the phone higher as if the
collapsing tower were a backdrop she had booked. Their expressions stay shallow and
playful, treating the giant-cat attack as a glamorous photo opportunity. In a bright,
high, fast young female voice (S1) the woman holding the phone shouts happily over the
wind: <d>[Japanese] やば、ばえすぎなんだけど!</d> After she finishes, the tanned woman
leans further into frame and calls out in a lower, louder young female voice (S2):
<d>[Japanese] ねえ、みてみて、こっちきてる!</d> In the final second the cat slowly turns
its enormous head and looks directly into the phone camera, its green eyes flaring in the
crossing beams, while the two women keep posing without noticing. The camera stays in the
handheld selfie position and pulls out with small amplitude at slow speed, keeping both
faces large in the foreground and the giant cat clearly visible behind them. Any distant
street signage is far below and out of focus, too blurred to read. Photographic realism
throughout; this is a filmed live-action scene, not animation or illustration.
overall_soundscape: Strong rooftop wind buffets the phone microphone and clips as the two
women shriek and laugh over each other. Collapsing concrete, breaking glass, metallic
groans and scattered impacts of falling debris carry up from the street far below, mixed
with distant sirens and traffic. Paper cups rattle and clothing snaps in the wind close to
the microphone. Each movement of the giant cat lands as a deep heavy thud through the
building.
non_diegetic_music: Fast glossy pop at a high tempo with a bright synth hook and a
four-on-the-floor kick, building in intensity with an added clap layer as the two women
pivot into their poses. All music cuts out abruptly in the final second, leaving only wind
as the cat turns its head.
Ajustes
Pasos
30
Semilla
1094488329
Tamaño
704x960
Peso usado
1
Prompt
Princess Mononoke (San) stands in a breathtaking enchanted forest filled with towering waterfalls, glowing butterflies, bioluminescent flowers, drifting magical particles, lush moss-covered trees, and vibrant fantasy colors. Warm golden sunlight filters through the canopy, creating a dreamlike atmosphere.
A tiny Kodama from Princess Mononoke sits on top of San's head. San subtly giggles and smiles, her eyes looking upward as she tries to see the Kodama above her. The Kodama stands up, turns around curiously, then makes several tiny playful hops while balancing on her head. Its movements are adorable, innocent, and full of personality.
The waterfalls flow gently in the background. Leaves sway softly in the breeze. Butterflies flutter through the air. Magical particles drift around them. San's hair and fur clothing move naturally with the wind.
Subtle camera push-in. Smooth natural motion. Preserve character appearance and composition from the source image. Heartwarming whimsical fantasy atmosphere.
Modelos similares
Modelos de IA para generar imagen, vídeo y texto
gemi h3 es un LoRA para la familia MiniMax H3 listado en ModelTrends.ai, un catálogo de solo lectura de modelos de IA de imagen, vídeo y texto de código abierto. Compáralo con otros modelos MiniMax H3, consulta su puntuación de calor para ver su tendencia y ábrelo en PirateDiffusion o BitVector para probarlo.
Explorar por familia de modelos
Modelos Text / LLM
411
Modelos Anima
509
Modelos Chroma
14
Modelos Flux
1,071
Modelos Flux 2 / Klein
1,237
Modelos MiniMax H3
331
Modelos Hunyuan
197
Modelos Ideogram
20
Modelos Krea2
674
Modelos Qwen
17
Modelos Qwen2
36
Modelos Ltx2
150
Modelos Stable Diffusion 1.5
6,465
Modelos Stable Diffusion XL 1.0
15,432
Modelos Zimage
804
Modelos Wan
919

Model
Trends
.ai
© ModelTrends.ai
|
Hecho en Japón
|
© 2026
