SpaceSkills AI Filmmaking

Snowy Shrine Demon Slaying

Short Film Anime 2026-07-30

Snowy Shrine Demon Slaying preview

Footage © @yourPlugAI · View original post

The clip was published publicly by its creator and is linked here directly; rights holders may request removal.

Full prompt

No more guessing frames—Hailuo MiniMax H3 just leveled up AI anime⚔️🔥
@Hailuo_AI

Kagura steps onto the snow-covered shrine floor under a blood-red moon, drawing her spirit katana against the shadows.

Translating this level of fast action into AI used to mean broken frames and shifting faces. Testing Hailuo's new MiniMax H3 completely changed that.

Using Omni Reference, Kagura’s face, robes, and glowing blade stayed locked frame-for-frame.

Combine that with H3’s upgraded physics engine, and the way the snow blasts off her boots while cyan spirit light cuts through the red night feels insanely real. 

Workflow and prompts👇🏾

#MiniMaxH3

### 作者补充

[补充1]
No more guessing frames—Hailuo MiniMax H3 just leveled up AI anime⚔️🔥
@Hailuo_AI

Kagura steps onto the snow-covered shrine floor under a blood-red moon, drawing her spirit katana against the shadows.

Translating this level of fast action into AI used to mean broken frames and shifting faces. Testing Hailuo's new MiniMax H3 completely changed that.

Using Omni Reference, Kagura’s face, robes, and glowing blade stayed locked frame-for-frame.

Combine that with H3’s upgraded physics engine, and the way the snow blasts off her boots while cyan spirit light cuts through the red night feels insanely real. 

Workflow and prompts👇🏾

#MiniMaxH3

[补充2]
MiniMax H3 didn't just render a fight—it brought physical weight to the light. ⚔️🔥 

I pushed MiniMax H3 on @Hailuo_AI to keep the action grounded and tight.

From heavy parries on a burning bridge to character physics held locked in flight, it nailed spatial awareness and https://t.co/lrJJ2hhQ55

[补充3]
Character Lead Concept

• Name: KAGURA

• Archetype: A solitary, fierce exorcist warrior.

• Visual Anchor: Tattered white-and-crimson robes, long jet-black hair bound in a high ponytail, glowing spirit katana, and glowing blue paper talismans (ofuda) strapped to her arms and belt.

[补充4]
Visual Story Image Prompt

A cinematic first frame for a 15-second solo supernatural katana fight video, 16:9 horizontal frame.

Scene:
A crumbling ancient Shinto shrine courtyard at midnight, covered in fresh white snow under a giant, blood-red lunar eclipse. Weathered wooden torii gates, cracked stone lanterns, drifting snow, deep crimson ambient moonlight, high-contrast high-shadow sacred atmosphere.

Action:
Start directly in action. Kagura is mid-air, executing a sweeping diagonal spirit-blade slash across the frame. Her body is twisted with explosive momentum, holding the glowing cyan katana with both hands. A luminous blue light trail follows the blade, cutting through the red-lit falling snow.

Elemental effects:
Glowing blue spirit energy trailing the blade, snow particles blasting outward from the kinetic shockwave, black shadow smoke curling beneath her boots. Dark crimson moonlight contrasting against cyan spirit energy.

Composition:
Kagura cuts diagonally from upper-left to lower-right. Snow-covered shrine ruins create background depth. Flaming red eclipse sits low in the sky behind the torii gate. Strong readable silhouette, full-body visibility.

Camera:
Low-angle cinematic action shot, slightly handheld energy, 28mm wide lens feel, dynamic scale, fast movement already underway.

Style:
Stylized cinematic realism, high-end 3D painterly anime animation, dynamic cloth and snow simulation, aggressive blade physicality, rich dual-tone lighting (crimson vs cyan), natural motion blur.

Details

Target model MiniMax H3
Use case Short Film
Style Anime
Media Video
Duration 15.1s
Aspect ratio 16:9
Likes 110
Published 2026-07-30

Attribution

Author: @yourPlugAI · View original post

Prompts remain the copyright of their authors. We index and quote them with attribution plus a link to the original post; rights holders may request removal.

Run this prompt through the API

Copy the prompt above into a MiniMax H3 (Hailuo) text-to-video call to reproduce the shot. When adapting it, swap subject, setting and camera move one clause at a time. Access and licensing details are on About.

← Back to all prompts