MiniMax H3 Combat BASE V2: fight motion, impact and drama
Topic: Models
By Captain
Published 2026-10-01
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Steps
12
Guidance
1
Size
1440x832
Prompt
For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
integrated_multimodal_description: [Shot 1] The scene opens from <Picture 1>, preserving the three young women standing close together outdoors on a city street in winter, with European-style buildings and bare trees in the background under soft daylight. The camera has a natural handheld smartphone selfie shakiness, as if held by one of the girls at arm's length. The girl on the left with long straight black hair, a thick gray scarf, and a dark coat (S1) shivers slightly, pulling her scarf tighter around her neck with one hand. She looks directly into the camera lens with a bright, slightly complaining expression and says: <d>[Chinese] 今天有点冷啊,快看镜头啊!我们三个谁最好看啊?</d> The girl in the middle with chestnut-brown hair, a gray coat with bow buttons, and a white phone with a bear charm (S2) turns her gaze toward the camera, a playful smile forming on her lips. The girl on the right with a single braid, a gray sweater, and a gold necklace (S3) continues looking down at her dark phone, smiling faintly.
[Shot 2] At 00:05.000, the handheld camera wobbles slightly as the girls adjust their positions. The middle girl (S2) raises her hand in a cute peace-sign gesture beside her face, tilts her head playfully, and laughs with a cheeky, confident expression, saying: <d>[Chinese] 当然是我啦!</d> She winks one eye playfully after the line. The left girl (S1) reacts with a mock-offended expression, opening her mouth in playful protest and lightly nudging the middle girl's shoulder with her elbow. The right girl (S3) finally looks up from her phone toward the camera, an amused smile spreading across her face as she shakes her head at the other two.
[Shot 3] At 00:10.000, the right girl (S3) laughs warmly, her eyes crinkling with genuine amusement, and says in a light, scolding-but-affectionate tone: <d>[Chinese] 两个臭屁精!别拍了,赶快吃火锅去啦!</d> She puts her dark phone away into her coat pocket and starts to turn her body toward the street, gesturing with her hand for the others to follow. The middle girl (S2) giggles and lowers her peace-sign hand, while the left girl (S1) laughs and nods in agreement. The handheld camera begins to lower and tilt as if the person filming is putting the phone down, the three girls starting to move together toward the street, their shoulders brushing as they walk off, still laughing. The frame ends with a slight downward tilt as the selfie video concludes.
overall_soundscape:
Soft outdoor city street ambience continues throughout — distant traffic hum, occasional car passing, faint wind rustling through the bare tree branches, and the low murmur of pedestrians in the background. The girls' voices are clear and close, captured by the phone's microphone with a slight natural reverb from the open street. Subtle fabric rustling is audible as they adjust their coats and scarves, and the soft click of a phone lock button is heard near the end as the right girl puts her phone away. Light, cheerful laughter from all three girls overlaps naturally throughout the conversation.
non_diegetic_music:
N/A
Settings
Size
960x544
Prompt
V2BASE
Settings
Size
1376x768
Prompt
integrated_multimodal_description:
[Shot 1]
A surreal martial-arts action scene. A woman with exactly three legs stands in the center of a large training courtyard. She is wearing a traditional white karate gi with a black belt. She is surrounded by a group of masked ninjas dressed entirely in black, they are bare handed.
The woman suddenly raises her body onto her middle leg, using it as a single central pivot. Her two other legs extend horizontally in opposite directions, forming a three-point spinning shape.
She begins spinning rapidly around her middle leg like a human whirlwind. The middle leg remains planted firmly on the ground and acts as the central axis, while the two outer legs stay fully extended and rotate around her.
Several ninjas attempt to rush toward her from different directions, but each time one approaches, one of her two extended legs swings around and delivers a powerful spinning kick, sending the ninja tumbling backward. Other ninjas try to approach from different angles, only to be knocked away by the rotating legs.
The choreography is clear and continuous: one leg remains the stationary pivot while the other two legs remain extended and sweep around her in a wide circular motion. The woman maintains perfect balance and moves with exaggerated martial-arts precision.
The scene is spectacular and absurd, played completely straight, with dynamic camera movement emphasizing the circular motion and the increasingly desperate ninjas surrounding her.
overall_soundscape: Ambient noise.
non_diegetic_music: N/A
Settings
Size
720x960
Prompt
V2BASE
Settings
Size
416x736
Prompt
the girl from example.png finally meets ryu from streetfighter in a dark ally. the girl proves far more superior in hand to hand combat since she is fighting in her own comfyui environment using a modified workflow.
Settings
Steps
25
Seed
265159317415717
Size
1472x1472
Prompt
prfight2, high-end claymation combat sequence, tactile stop-motion texture. A square golden-brown waffle fighter with short articulated limbs and glossy chocolate-syrup eyes is surrounded in a narrow wooden breakfast arena by a surging horde of round pancakes; only three foreground pancake warriors have crude short stubby articulated limbs and receive individual hit reactions while the background mass closes as one blurred threat.
The waffle is on the defensive throughout: every foreground exchange begins with a pancake attack, followed by a visible block, parry, or dodge from the waffle, then one heavier counter that opens space to his right. Sequential single-target exchanges only; the camera pans with him to the right as he moves through the gaps created by his counters.
A first pancake lunges from ahead-right with an overhead batter-punch at his head; the waffle ducks under it and turns its momentum aside with a low forearm parry, then drives one heavy upward elbow strike into the pancake’s exposed center; it bends violently upward, cracks along its edge, syrup spurts outward, and collapses flat behind him, opening a narrow gap to his right.
A second pancake immediately surges through that gap with a horizontal batter-punch at his chest; the waffle absorbs it against his raised guard in a loud wet snap, recoils half a step right but stays upright, then answers instantly with a low forearm strike under the attacker’s rim; the pancake flips over, batter splashes in an exaggerated arc, lands flat and crumples with visible clay deformation, clearing another lane segment to his right.
A third pancake lunges overhead from the closing horde with a broadside edge punch; the waffle ducks under it and counters before it can recover by driving one heavy straight punch into its center; the attacker cracks diagonally, tumbling pieces flatten behind him as he continues rightward. The remaining blurred pancake mass recoils and collapses in broad waves behind him, ending with a low-angle victory pose at the right edge of the cleared arena as flattened pancakes trail behind him.
Dynamic tracking shot panning sharply right with his defensive movement throughout, impact-synced camera kicks, exaggerated squash-and-stretch while preserving coherent silhouettes, heavy physical consequences after every attack and counter.
Audio: Heavy punch and guard-clash impacts from both sides: wet slaps, batter snaps, floppy pancake squelches on incoming pancake attacks; deep cartoonish bass thuds and crunchy waffle cracks on the waffle’s defensive counters; thick syrup splatter whooshes; low-end impact drops synced to every landed counter hit. Percussive rhythm, no melody.
FourBunny's Combat BASE LoRA for MiniMax H3 improves fight choreography, hit reactions, continuity and physical cause and effect, and it helps dialogue scenes too. Learn the prfight1, prfin1 and prslow1 triggers and how to stage a scene.
Overview
MiniMax H3
Combat
BASE (V2) by FourBunny is a video
LoRA
focused on action: faster combat, better action continuity, believable hit reactions, cumulative damage, spatial movement and physical cause and effect. V2 goes beyond fights, adding richer body movement, finer sound detail and stronger shot-to-shot continuity to character performance.
Triggers: prfight1 for normal combat; add prfin1 after it for a clear finisher, knockout or takedown; add prslow1 for a brief slow-motion emphasis on the decisive strike. The author notes slow motion is not guaranteed.
Reference
Name | Type | What it is |
|---|---|---|
Trigger | prfight1 | Normal combat scenes. |
Finisher | prfin1 | After prfight1 for a decisive ending. |
Slow motion | prslow1 | Brief emphasis on the final strike. |
LoRA weight | 0.7-1.0 | |
Resolution | 1080p / 2 MP | 10 s clips take about 15 minutes on a 12 GB card per the author. |
AD

No install required - run AI models on the cloud
BitVector Prism is the easiest way to start: pick a model, type a prompt and generate in a clean web app, with nothing to configure. BitVector is also available on Discord and on the web (SpyGlass).
Step by step
- Describe the fighters, the space and who is winning in the integrated description.
- Put prfight1 at the start; add prfin1 if the clip ends the fight.
- Describe sound (impacts, breathing) in the soundscape.
- Weight 0.9, standard H3 steps.
- Keep each shot to one exchange of blows.
Examples
Sparring
prfight1. integrated_multimodal_description: [Shot 1] Two adult boxers spar in a dim gym. The taller one jabs, the shorter slips and lands a body shot; the taller staggers back into the ropes.
overall_soundscape: Glove impacts, squeaking shoes, heavy breathing.
non_diegetic_music: N/A
Finisher
prfight1, prfin1, prslow1. integrated_multimodal_description: [Shot 1] A swordswoman parries a strike and sweeps her opponent's legs; he falls and the blade stops at his collar.
overall_soundscape: Steel ring, boots on gravel, wind.
Creative idea: dialogue with tension
prfight1. integrated_multimodal_description: [Shot 1] Two negotiators face off across a table. One slams a hand down and says: <d>[English] Enough.</d> The other leans back slowly.
overall_soundscape: Hand on wood, chair creak.
Tips
- Name the hit reactions you want (staggers back, drops to one knee).
- Cumulative damage: mention earlier hits in later shots.
- Works for dialogue scenes too; it improves body language.
- Combine with Better Motion at 0.4 for walking and turning.
Troubleshooting
Fight ends without impact
Why it happens
No finisher trigger.
How to fix it
Add prfin1 after prfight1.
Limbs glitch in fast exchanges
Why it happens
Too many actions per shot.
How to fix it
One exchange per shot; add Better Motion at 0.4.
AD

No install required - run AI models on the cloud
PirateDiffusion is Telegram only and built for pros: thousands of models, LoRAs and workflows driven by chat commands, with unlimited generation on a fixed price plan.
Questions
Is slow motion reliable?
The author says prslow1 is not guaranteed; keep shots short.
Dialogue scenes?
Yes, V2 improves performance continuity in them.
Links and sources
Models in this guide
Written by
Captain
Related guides
Models
GalaxyAce LoRA for MiniMax H3: early-2010s low-end phone footage
aiguild's GalaxyAce LoRA recreates the look of a Samsung Galaxy Ace phone camera: muted colors, sensor noise, rolling shutter and everyday framing. Learn strengths per model, prompts and found-footage ideas.
By Captain
2026-10-02
Models
Better Human Motion for MiniMax H3: natural, consistent body movement
AdaptiveVision's Better Motion LoRA makes MiniMax H3 (and LTX) characters move naturally and consistently. Learn weight, resolution, step count and how to write short motion prompts.
By Captain
2026-10-01
Models
Passionate Kissing LoRA for MiniMax H3: convincing romantic scenes between adults
kermitfrog1202's LoRA improves kissing scenes in MiniMax H3 video. Learn the trigger sentence, the strength values the author found for different couples and how to stage a tasteful romantic shot.
By Captain
2026-10-01
Models
MiniMax H3 Turbo LoRAs: 4-8 step video with the larryvrh pack
The MiniMax H3 Turbo LoRA pack (larryvrh 4-step and friends) cuts video generation steps from dozens to a handful. Learn the per-variant step counts, samplers and strengths, plus how to prompt H3 for fast, clean clips.
By Captain
2026-10-01
Prompting
Prompting MiniMax H3: text to video, image to video, reference video and audio
How to direct MiniMax H3 from a chat command: the WHO + WHERE + ACTION + CAMERA + SOUND recipe for text to video, animating a still with image to video, giving every reference picture a job in reference mode, and getting clean dialogue instead of mumbling. With copy-and-try prompts and the author's PDF.
By Mark White
2026-09-20
More guides
Models
FLUX.1 Dev: how to prompt it, best settings and creative ideas
A practical guide to FLUX.1 Dev by Black Forest Labs: natural-language prompting, guidance and step settings, LoRA stacking, text rendering and prompt ideas that play to its strengths.
By Captain
2026-09-30
Models
Stable Diffusion XL 1.0: prompts, settings and what it still does best
How to get the most out of the official SDXL 1.0 base model: native resolutions, CFG and sampler settings, the refiner, negative prompts and ideas for styles where SDXL still shines.
By Captain
2026-10-01
Models
Stable Diffusion 1.5: the classic model, prompted properly
Stable Diffusion 1.5 is still worth knowing: the right resolution, CFG and sampler, how to use its huge library of LoRAs and embeddings, and creative prompt ideas suited to a 512-pixel model.
By Captain
2026-10-02
Models
FLUX.2 Dev: prompting the newest Black Forest Labs model
FLUX.2 Dev brings larger prompts, better text, stronger realism and multi-reference editing. This guide covers the turbo workflow, guidance and resolution settings, prompt structure and ideas that use its new strengths.
By Captain
2026-10-03
Models
Qwen-Image: long prompts, perfect text and bilingual posters
Qwen-Image is the model to reach for when the words in the picture matter. Learn how to write its long descriptive prompts, render English and Chinese text accurately, set CFG and steps, and explore layout-heavy creative ideas.
By Captain
2026-09-29
Models
SDXL-Lightning: four-step generation on any SDXL checkpoint
ByteDance's SDXL-Lightning LoRA turns a 30-step SDXL render into a 4-step one. Learn the step counts, the CFG you must use, the sampler, and how to combine it with your favorite checkpoints and style LoRAs.
By Captain
2026-09-30

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026





