digital art h3
Vergleichen
8214°
Autoplay
Lokal ausführen
minimax_digita_art_v2.0.safetensors
148 MB · SafeTensor · bf16
Downloads werden von Civitai bereitgestellt. Manche Ersteller verlangen zuerst eine Anmeldung bei Civitai.
AD
Auf Graydient installieren / ausführen
Mitgliedschaft erforderlich
<digital-art-h3>
Über dieses Modell
MINIMAX H3 · LoRAs
by PinkPromptPrincess - Minimax H3 Digital Art Style - The target video is an edgy indie 2D animation, bold sharp digital ink outlines, trendy webtoon aesthetic, flat cel shading.
Notizen des Erstellers
Minimax H3 Digital Art Style
Trigger words
Edgy 2D animation, sharp digital ink outlines, comic book style, flat cel shading.
Captures the look of edgy American indie 2D animation, blending sharp digital ink outlines with a highly expressive, trendy webtoon aesthetic. Built around a modern lo-fi comic book style and flat cel shading, it delivers crisp, clean production quality and bold outlines right out of the box. There is no hidden prompt engineering or secret sauce required here—this LoRA is highly responsive and ready for your ideas. If your scene calls for glowing tattoos, burning amber effects, or specific details, simply type them directly into your prompt and watch the style mold around them perfectly.
This is V2, by the way. I doubled the entire image dataset because I wasn't completely satisfied with the first run. After a lot of extra oven time, it's finally ready.
Recommended strength
The sweet spot sits between 0.8 and 1.5, but 1.0 is the absolute baseline flavor.
-
Crank it to 1.5: You’re getting maximum indie animation aggression—thick, uncompromising outlines and intense cel-shaded contrasts.
-
Dial it to 0.8: It lets the base model breathe a little, softening those sharp edges into a subtler graphic novel look.
Example Prompt
integrated_multimodal_description: [Shot 1] Edgy American indie 2D animation, sharp digital ink outlines, trendy webtoon aesthetic, highly expressive, modern lo-fi comic book style, crisp clean production quality, flat cel shading, bold outlines. The scene opens in the bustling cityscape from , where the sky is filled with moving, swirling clouds and the air is thick with floating embers and dust particles. In the center of the frame, Tom stands with his arms crossed, wearing the black sweater and the large, patterned tan and black scarf from . His dark hair and the ends of his scarf rustle slightly in a steady breeze. The camera holds a static shot, maintaining a shallow depth of field with heavy bokeh that blurs the neon signs and structures of the city in the background. At 02.500s, Tom takes a slow, deep breath, his chest rising and falling steadily; his expression remains calm and composed. At 04.000s, a sudden, supernatural light begins to pulse from the blue geometric tattoo on his neck and throat, the glow shimmering and traveling from one edge of the pattern to the other in a bright, electric cyan light. At 06.000s, Tom slowly uncrosses his arms, his gaze shifting directly toward the lens with a determined, piercing look. He begins to walk forward toward the camera, his heavy footsteps silent against the ambient city hum. As he approaches, the camera remains static but the composition tightens on his face until his figure fills the entire frame, his shadow casting a dark veil over the lens. At 07.800s, he reaches out toward the camera, his hand obscuring the view, leading to a total black screen.
overall_soundscape: The ambient sound of a busy, futuristic city with distant hums and the rustle of wind through fabric. The sound of a deep, controlled intake of breath is heard from Tom, followed by the subtle, electric hum and crackle of the glowing tattoo. As he walks, the sound of his movement is muffled by the atmospheric wind.
non_diegetic_music: A high-energy punk rock track with driving electric guitar riffs and a steady, aggressive drum beat that builds in intensity as the tattoo begins to glow.
subject_definitions:
is the man Tom, with the facial features and appearance from .
retention_analysis:
(appears in [Shot 1]): fully_preserved - Tom's facial features and appearance from are used for the character.
(appears in [Shot 1]): fully_preserved - The cityscape environment with moving clouds and floating embers is used as the environment.
Yes, i love to give extreme details to Minimax
SHA256
D68C4517A011BDBFE3DC573E16CCBCCA316CF8E8B5E40834880AB3C0CD9DB8FF
ModelTrends.ai-Modell-ID
#27044
Inhalt melden
Beispielbilder
Prompts und Einstellungen, geteilt von den Leuten, die diese Bilder auf Civitai erstellt haben. Wähle ein Bild, um zu sehen, wie es entstanden ist.
Einstellungen
Größe
784x1408
Prompt
subject_definitions:
<Subject 1> is the woman Jessica, with the facial features and appearance from <Picture 2>.
summary:
[reference generation] The target video is a 2D animated scene set in the bedroom environment of <Picture 1>. <Subject 1>, the woman Jessica, sits at her cluttered desk, wearing her oversized dark forest green crewneck sweatshirt with a pink ribbed collar and a thick-knit pink sweater vest, her large cream-colored headphones on her head. She is focused on her notebook, listening to music while the afternoon sun illuminates the room.
retention_analysis:
<Subject 1> (appears in [Shot 1]): fully_preserved - Jessica's facial features and appearance from <Picture 2> are used for the character.
<Picture 1> (appears in [Shot 1]): fully_preserved - The bedroom environment, including the green walls, string lights, bed with pink bedding, and the desk with books and lamp, is used as the environment.
detailed_description:
The target video is an edgy American indie 2D animation, sharp digital ink outlines, trendy webtoon aesthetic, highly expressive, modern lo-fi comic book style, crisp clean production quality, flat cel shading, bold outlines.
[Shot 1] The scene opens in the bedroom from <Picture 1>, a cozy room with green walls adorned with photos and warm string lights. In the foreground, the desk is cluttered with a laptop, open notebooks, and a red ceramic mug filled with pens. In the mid-ground, <Subject 1>, the woman Jessica, is seen from a medium side profile. She is wearing her heavy, oversized dark forest green crewneck sweatshirt with a wide, folded pink ribbed collar that bunches around her neck, and her bulky, thick-knit pink sweater vest. Her large, matte cream-colored headphones are pressed against her hair as she leans her chin on her right hand. Her left hand holds a black pen, poised over an open notebook. She is staring intently at the pages, her expression serious and focused, though her eyes occasionally dart slightly as if reacting to the music in her ears. The bright, direct afternoon sunlight streams through the window in the background, casting long, soft shadows and illuminating dust motes that dance in the air. The light hits the copper lamp and the edges of the books, creating high-contrast warmth against the cool shadows. The orange and red striped cat lies stretched out on the windowsill, appearing to sleep peacefully. The camera holds a static shot, maintaining the intimate, lo-fi atmosphere.
overall_soundscape:
The soft, rhythmic lo-fi indie music plays through the headphones, creating a muffled, internal sound for the viewer. Ambient room sounds include the distant, faint hum of the city outside the window and the occasional soft rustle of paper as Jessica shifts her weight slightly.
non_diegetic_music:
A chill, lo-fi hip-hop beat with a steady, mellow tempo and soft, jazzy electric piano chords that maintain a relaxed atmosphere.
Einstellungen
Größe
1152x640
Prompt
subject_definitions:
<Subject 1> is the woman, with the facial features and appearance from <Picture 1>, wearing an american teen dress.
<Subject 2> is the man, with the wardrobe and appearance from <Picture 2>.
summary:
[reference generation] The target video is a 2D animated sequence in an edgy American indie style. <Subject 1> is seen working at a desk before <Subject 2> enters the room to present her with a rose, leading to a close-up interaction with the flower. The scene is driven by the visual storytelling of the characters' proximity.
retention_analysis:
<Subject 1> (appears in [Shot 1]): fully_preserved - The woman's facial features and appearance from <Picture 1> are used for the character.
<Subject 2> (appears in [Shot 2]): fully_preserved - The man's wardrobe and appearance from <Picture 2> are used for the character.
detailed_description:
The target video is an edgy American indie 2D animation, sharp digital ink outlines, trendy webtoon aesthetic, highly expressive, modern lo-fi comic book style, crisp clean production quality, flat cel shading, bold outlines.
[Shot 1] 0.00–4.00s The scene opens with a close-up of a ceramic coffee cup sitting on a dark, textured wooden table. Wisps of steam rise from the surface of the dark liquid. A hand enters from the right side of the frame; the fingers are slender and move with a deliberate, slow motion. As the hand lifts the cup, a dark, wet coffee stain is left behind on the wood grain, reflecting the dim indoor light. The camera remains static.
[Shot 2] 4.00–10.00s The camera cuts to a medium shot of <Subject 1> sitting at a large desk cluttered with papers, a laptop, and various desk accessories. She is focused on her work, her expression serious and concentrated. The lighting is soft, suggesting a home office environment. Suddenly, <Subject 2> enters the frame from the background, stepping toward the desk. He holds a single red rose in his hand, extending it toward her. <Subject 1> freezes, her eyes widening as she slowly turns her head toward him, her expression shifting from focus to surprised curiosity.
[Shot 3] 10.00–15.00s The camera cuts to an extreme close-up of the red rose. The petals are a deep, saturated red, and the green stem is held firmly by the hand of <Subject 2>. <Subject 1>'s hand enters the frame from the bottom, her fingers reaching up toward the stem. Her movements are cautious yet certain. She pinches the stem between her thumb and forefinger, slowly pulling the flower away from his grasp. The camera maintains a tight, intense focus on the contact between her fingers and the stem as the shot holds on the tension of the moment.
overall_soundscape:
The quiet, ambient hum of a room is punctuated by the soft clink of a ceramic cup being lifted from a wooden surface and the subtle rustle of paper. The sound of footsteps on a floor approaches, followed by the faint, sharp movement of fabric as <Subject 2> moves.
non_diegetic_music:
N/A
Einstellungen
Größe
1152x640
Prompt
subject_definitions:
<Subject 1> is the woman, with the facial features and appearance from <Picture 1>, wearing an american teen dress.
<Subject 2> is the man, with the wardrobe and appearance from <Picture 2>.
summary:
[reference generation] The target video high quality cinimatic style. <Subject 1> is seen working at a desk before <Subject 2> enters the room to present her with a rose, leading to a close-up interaction with the flower. The scene is driven by the visual storytelling of the characters' proximity.
retention_analysis:
<Subject 1> (appears in [Shot 1]): fully_preserved - The woman's facial features and appearance from <Picture 1> are used for the character.
<Subject 2> (appears in [Shot 2]): fully_preserved - The man's wardrobe and appearance from <Picture 2> are used for the character.
detailed_description:
[Shot 1] 0.00–4.00s The scene opens with a close-up of a ceramic coffee cup sitting on a dark, textured wooden table. Wisps of steam rise from the surface of the dark liquid. A hand enters from the right side of the frame; the fingers are slender and move with a deliberate, slow motion. As the hand lifts the cup, a dark, wet coffee stain is left behind on the wood grain, reflecting the dim indoor light. The camera remains static.
[Shot 2] 4.00–10.00s The camera cuts to a medium shot of <Subject 1> sitting at a large desk cluttered with papers, a laptop, and various desk accessories. She is focused on her work, her expression serious and concentrated. The lighting is soft, suggesting a home office environment. Suddenly, <Subject 2> enters the frame from the background, stepping toward the desk. He holds a single red rose in his hand, extending it toward her. <Subject 1> freezes, her eyes widening as she slowly turns her head toward him, her expression shifting from focus to surprised curiosity.
[Shot 3] 10.00–15.00s The camera cuts to an extreme close-up of the red rose. The petals are a deep, saturated red, and the green stem is held firmly by the hand of <Subject 2>. <Subject 1>'s hand enters the frame from the bottom, her fingers reaching up toward the stem. Her movements are cautious yet certain. She pinches the stem between her thumb and forefinger, slowly pulling the flower away from his grasp. The camera maintains a tight, intense focus on the contact between her fingers and the stem as the shot holds on the tension of the moment.
overall_soundscape:
The quiet, ambient hum of a room is punctuated by the soft clink of a ceramic cup being lifted from a wooden surface and the subtle rustle of paper. The sound of footsteps on a floor approaches, followed by the faint, sharp movement of fabric as <Subject 2> moves.
non_diegetic_music:
N/A
Einstellungen
Größe
784x1408
Prompt
subject_definitions:
<Subject 1> is the woman Jess, with the facial features and appearance from <Picture 3>, wearing a black jacket with chains and rock band logos and blue jeans.
<Subject 2> is the man Tom, with the facial features and appearance from <Picture 2>, wearing his normal clothes.
summary:
[reference generation] The target video is an edgy action sequence set in a sunny basketball court. <Subject 1>, the woman Jess, outmaneuvers <Subject 2>, the man Tom, in a high-speed athletic play, ultimately scoring the basket while he remains stunned. The scene is driven by the kinetic movement of the basketball play.
retention_analysis:
<Subject 1> (appears in [Shot 1]): fully_preserved - Jess's facial features and appearance from <Picture 3> are used for the character.
<Subject 2> (appears in [Shot 1]): fully_preserved - Tom's facial features and appearance from <Picture 2> are used for the character.
detailed_description:
The target video is an edgy American indie 2D animation, sharp digital ink outlines, trendy webtoon aesthetic, highly expressive, modern lo-fi comic book style, crisp clean production quality, flat cel shading, bold outlines.
[Shot 1] 0.00–4.00s, the scene opens in a sunny basketball court with a high-contrast, vibrant color palette. In the mid-ground, <Subject 1>, the woman Jess, wearing her black jacket with chains and rock band logos and blue jeans, dribbles the basketball with intense focus, her eyes sharp and determined. In the foreground, <Subject 2>, the man Tom, in his normal clothes, shifts his weight defensively, trying to block her path. The camera holds a static shot, capturing the tension of the standoff.
[Shot 2] At 04.00s, the camera cuts to a side profile shot. The motion is fast as Jess suddenly bursts forward, her feet kicking up dust from the court. She moves with extreme speed, weaving past Tom with a professional crossover. The camera remains static as she zips through the frame, leaving a blurred trail of motion.
[Shot 3] At 08.00s, the camera cuts to a slow-motion shot. Jess leaps high into the air, her body extending towards the hoop. The animation style emphasizes the stretch of her movement. Her face shows intense concentration as she releases the ball. The basketball arcs through the sunny sky, and the camera stays fixed on the hoop as the ball swishes through the net perfectly.
[Shot 4] At 12.00s, the camera cuts to a close-up shot. Jess stands near the hoop, looking back at Tom with a teasing, triumphant smirk, her eyes sparkling with victory. In the background, Tom is frozen in a shocked pose, his mouth agape and eyes wide, staring at the basket in disbelief. The background is heavily blurred with deep bokeh, keeping the focus on the emotional contrast between the winner and the loser.
overall_soundscape:
The rhythmic, heavy thud of a basketball bouncing on the asphalt echoes through the sunny court. Rapid, squeaky footsteps of sneakers against the ground punctuate the action. The sharp, satisfying 'swish' of the net occurs during the scoring moment, followed by the distant, muffled sounds of a neighborhood under a bright sun.
non_diegetic_music:
High-energy, fast-tempo punk rock with driving electric guitar riffs and aggressive drum beats that match the pace of the action.
Einstellungen
Größe
784x1408
Prompt
subject_definitions:
<Subject 1> is the woman, with the facial features and appearance from <Picture 2>.
summary:
[reference generation] The target video is a dramatic animation set in the environment of <Picture 1>. <Subject 1> is seen kneeling with her bow raised before she transitions into an intense action sequence, standing and sprinting toward the den as embers fly. The scene is driven by the dialogue of <Subject 1>.
retention_analysis:
<Subject 1> (appears in [Shot 1]): fully_preserved - Her facial features and appearance from <Picture 2> are used for the character.
<Picture 1> (appears in [Shot 1]): fully_preserved - The environment layout from <Picture 1> is used as the setting.
detailed_description:
edgy American indie 2D animation, sharp digital ink outlines, trendy webtoon aesthetic, highly expressive, modern lo-fi comic book style, crisp clean production quality, flat cel shading, bold outlines.
[Shot 1] The scene opens in the environment from <Picture 1>, with a heavy bokeh effect blurring the background. In the center of the frame, <Subject 1>, the woman, is kneeling on the ground, clutching her bow up toward the sky. The fire behind her crackles intensely, sending glowing amber embers and dark ashes swirling into the air around her. Her expression is tense and wary. At 02.00s, she shifts her weight, her eyes narrowing as she slowly stretches the bow toward the camera, the movement deliberate and threatening. She looks directly into the lens, her lips curling as she asks in a sharp, questioning American English voice: <d>[English] Who are you?</d> At 04.50s, she suddenly snaps her body upright, releasing the tension in her arms and transitioning into a sprint. The camera holds a static shot as she runs toward the dark entrance of the den. With every forceful footstep, sand and grit kick up from the ground, spraying into the air in small, sharp clouds. As she approaches the perimeter of the fire, she takes a long, leaping stride, jumping over the flickering flames. The light from the fire casts a brief, bright orange glow over her form before she disappears into the deep, heavy darkness of the den.
overall_soundscape:
The roar of a crackling fire dominates the scene, punctuated by the sharp hiss of embers hitting the ground. As she moves, the sound of her heavy, rhythmic footsteps through the sand creates a gritty, scraping noise. Her voice is clear and direct, cutting through the ambient heat of the fire. When she jumps, there is a sudden rush of wind and the soft thud of her landing.
non_diegetic_music:
N/A
Einstellungen
Größe
784x1408
Prompt
```text
subject_definitions:
<Subject 1> is the black cat, a stylized 2D animated character with sharp digital ink outlines and large, highly expressive eyes, possessing a sleek black fur texture and a long, tapering tail.
<Subject 2> is the white mouse, a small 2D animated character with clean white fur, large wide-open eyes, and a tiny pink nose, designed with a trendy webtoon aesthetic.
<Subject 3> is the red floral handkerchief, a small piece of fabric with a bright red base and a distinct white floral pattern.
<Subject 4> is the silver knife and fork, metallic kitchen utensils with sharp, clean digital outlines and high-contrast cel shading.
<Subject 5> is the dark alley environment, featuring gritty textures, old crumpled newspapers, a cardboard box, discarded soda cans, and colorful graffiti on the brick walls, all rendered in a modern lo-fi comic book style.
summary:
[reference generation + audio reference] The target video is an edgy, fast-paced 2D animation in an indie webtoon style. A black cat hunts a white mouse in a detailed dark alley, catches it, and presents it to the camera before the mouse plays dead. The scene shifts to a darkly comedic moment where the cat, wearing a floral handkerchief, prepares to eat the mouse with cutlery, licking its mouth with a long tongue as the mouse covers its eyes. The audio features fast-paced music and cat meows.
retention_analysis:
<Subject 1> (appears in [Shot 1], [Shot 2], [Shot 3]): fully_preserved - the black cat's expressive features and ink outlines are retained.
<Subject 2> (appears in [Shot 1], [Shot 2], [Shot 3]): fully_preserved - the white mouse's wide-eyed, dramatic expression and white fur are retained.
<Subject 3> (appears in [Shot 3]): fully_preserved - the red floral pattern on the handkerchief is retained.
<Subject 4> (appears in [Shot 3]): fully_preserved - the metallic sheen and sharp outlines of the cutlery are retained.
<Subject 5> (appears in [Shot 1], [Shot 2]): fully_preserved - the dark alley with graffiti, newspapers, and soda cans is retained.
detailed_description:
The target video is an edgy American indie 2D animation with sharp digital ink outlines, a trendy webtoon aesthetic, and flat cel shading. The colors are bold and multi-colored against a dark, moody background.
[Shot 1] The scene opens in <Subject 5>, a dark, gritty alleyway filled with old crumpled newspapers, a discarded cardboard box, and several colorful soda cans scattered near a brick wall covered in vibrant, edgy graffiti. The lighting is high-contrast, with sharp shadows. A black cat, <Subject 1>, with highly expressive, wide eyes, crouches behind a box, its body tensed for a hunt. A small white mouse, <Subject 2>, scurries nervously across the pavement near the newspapers. The camera follows the cat's sudden, extreme rapid movement as it lunges forward with a predatory burst of speed.
[Shot 2] At 00:04.000, the camera follows the action in a frantic, handheld-style motion as <Subject 1> catches <Subject 2> by the neck. The cat holds the mouse up close to the camera lens, its face showing a mischievous, wide-eyed grin. The mouse, <Subject 2>, goes completely limp, its eyes wide open and staring vacantly, acting dead with no visible breathing. <Subject 1> then drops the mouse onto the ground with a dull thud near a crushed soda can.
[Shot 3] At 00:08.500, the shot cuts to a medium close-up. <Subject 1> suddenly, and with comedic timing, wraps <Subject 3>, a red floral handkerchief, around its neck like a napkin. The cat reaches behind its back and pulls out <Subject 4>, a silver knife and fork, holding them with a stylized, anthropomorphic grip. The cat leans over the "dead" <Subject 2> and licks its own mouth with a long, pink, exaggerated tongue, a trail of drool glistening as it hangs from its chin. <Subject 2>, still lying on the floor, suddenly lifts a tiny white paw and places it over its own wide eyes in a dramatic, funny gesture of refusal.
overall_soundscape:
Fast-paced, edgy indie electronic music drives the rhythm. The scene is punctuated by the sharp, high-pitched meows of <Subject 1> and the frantic, cartoonish scuttling of the mouse. A heavy thud is heard when the mouse is dropped.
non_diegetic_music:
The music is a high-energy, lo-fi indie track with driving percussion and a gritty, synthesized bassline that matches the rapid action.
```
Ähnliche Modelle
Badges for creators
Made this model? Put its standing on your Civitai page, your Hugging Face card, your README or your site. Each badge is a small picture that shows the standing on the day you copy it and never changes afterwards, however the rankings move later. The date is part of the badge.
KI-Modelle für Bild-, Video- und Texterzeugung
digital art h3 ist ein LoRA für die Familie MiniMax H3 und wird auf ModelTrends.ai gelistet, einem reinen Lesekatalog für Open-Source-KI-Modelle für Bild, Video und Text. Vergleiche es mit anderen MiniMax H3-Modellen, prüfe den Hitzewert, um den Trend zu sehen, und öffne es auf PirateDiffusion oder BitVector, um es auszuprobieren.
Weitere MiniMax H3-ModelleWeitere MiniMax H3 LoRAsvideocartoonscomicsartstyleswebtooncel shadingstyles
Nach Modellfamilie stöbern
Text / LLM-Modelle
411
Anima-Modelle
509
Chroma-Modelle
14
Flux-Modelle
1,071
Flux 2 / Klein-Modelle
1,237
MiniMax H3-Modelle
332
Hunyuan-Modelle
198
Ideogram-Modelle
20
Krea2-Modelle
675
Qwen-Modelle
17
Qwen2-Modelle
37
Ltx2-Modelle
151
Stable Diffusion 1.5-Modelle
6,465
Stable Diffusion XL 1.0-Modelle
15,432
Zimage-Modelle
804
Wan-Modelle
920

Model
Trends
.ai
© ModelTrends.ai
|
© 2026
|
Alle Rechte vorbehalten






