Text to video - Recommended Usage Settings
Model: 720p (Portrait)
Duration: 4 seconds
Generation Mode: Stable
Prompt Example : A mesmerizing MMD dance unfolds, captured in vibrant cel-shaded anime style. The performance opens with a medium close-up of a stoic female character, her long red hair framing a slightly displeased expression. Initially rigid, her posture subtly shifts throughout the choreography, progressing through relaxed yet defiant poses, a hint of contrapposto in the mid-section, and subtle leans and weight shifts. The camera maintains a close-up perspective, emphasizing the character's expressive face and ornate black and white maid outfit, adorned with delicate lace and ruffles. The dance unfolds with a fluid grace, transitioning from near-static stances to moments of implied movement, suggesting a controlled power. The background features a bright, sunlit garden in full bloom, filled with green foliage and colorful flowers, enhancing the cheerful and fresh mood of the scene. Subtle waves appear in her hair as the dance progresses, mirroring the gentle swaying of nearby trees and blossoms. The final pose mirrors the initial one, but with a slight defiant tilt, leaving the viewer with a lingering sense of quiet intensity. The entire sequence showcases a masterful blend of stillness and implied movement, characteristic of both anime and MMD animation styles, resulting in a captivating visual narrative.
Prompt Structure Template (with Trigger Keywords)
"A captivating MMD dance unfolds, featuring a {adjective} female anime character with {hair style/color}, wearing {outfit}. The performance begins with {gesture/pose}, followed by stylized movements like {gesture1}, {gesture2}. Her facial expressions shift from {emotion1} to {emotion2}, in a background of {environment}. Camera angles include {close-up/three-quarter/full-body}, highlighting the fluid choreography and emotional storytelling. The sequence ends with {final gesture/pose}."
Use Phrases Like:
“MMD dance unfolds”
“stylized movements”
“captivating performance”
“playful smirk”, “hand-to-chin gesture”
“camera captures”, “three-quarter view”
“blurred background”, “dynamic choreography”
Tips for Better Results
Use action verbs like: unfolds, begins, transitions, ends.
Use emotive adjectives: confident, shy, playful, serene.
Match the style from training captions: blurred background, vibrant or cel-shaded animation, stylized choreography.
Include common gestures from training: hand-to-chin, peace sign, smirk, interlaced fingers, prayer-like hands.
Mention camera framing: close-up, three-quarter view, full-body.