DEV Community

张洲诚(Zack.ZHANG)
张洲诚(Zack.ZHANG)

Posted on

I've Been Trying to Write AI Video Prompts for Months. They All Sucked Until I Found a Formula.

The Problem Nobody Talks About

Everyone's posting AI-generated videos — characters speaking with lip-sync, manga panels coming alive, virtual idols dancing. The pitch: "just describe what you want."

I tried. For months. Here's what I got:

  • Character's face morphed by frame 2
  • "Slowly looks up" became "violent head shake"
  • Voice-over sounded like Google Translate
  • Same prompt, 3 runs, 3 completely different results
  • No idea what to include or how long the prompt should be

Tutorials were either too vague ("be detailed") or too technical (parameter tuning from line 1).

The real issue: video prompts are structurally different from text/image prompts. You need to simultaneously control visuals, motion, audio, camera, and consistency constraints — in the right order, at the right length.


What I Found

A Skill in the Model Studio official repo called happyhorse-prompt-studio. It doesn't teach you theory — it asks you questions and assembles the prompt for you.

4-phase flow:

1. Inspiration Menu

Shows you 4 "flavors" of what HappyHorse can do:

Flavor What it does
A · Voiced Manga Drama Characters talk to each other, with voice + lip-sync
B · Character Voice PV Single character self-introduction, 8-10 sec
C · Manga Panel Motion Static manga panel starts breathing
D · Virtual Idol MV Idol performance with choreography

2. Discovery

Asks you conversationally: character appearance, scene, emotion, dialogue, voice type, art style, camera.

3. Prompt Assembly

Assembles using the HappyHorse Formula:

Scene + Subject + Motion + Audio + Quality
Enter fullscreen mode Exit fullscreen mode

Key techniques:

  • @「Image n」 syntax locks character identity across shots
  • Dialogue ≤15 characters (split shots if longer)
  • Japanese prompts work best (HappyHorse is JP-optimized)
  • Always end with キャラの顔・髪・衣装が変わらない (face/hair/outfit stays unchanged)

4. Quality Check

Auto-reviews: completeness, compliance, cost estimate, optimization tips.


Before vs. After

Dimension Writing myself With Prompt Studio
Attempts needed 10-20 before one usable 2-3 to satisfaction
Time per prompt 1-2 hours (research + trial) 5-10 minutes
Character consistency Collapsed by frame 2 R2V syntax locks it
Common pitfalls Learned by failing Built-in troubleshooting

Honest Limitations

  • No guarantee of perfection on first try (AI video has inherent randomness)
  • Can't replace your creativity (character design is still yours)
  • Max ~30 seconds per generation
  • Requires API key (free tier available)
  • Japanese prompts get best results; CN/EN work but JP is optimized

Setup

npx skills add modelstudioai/skills --skill happyhorse-prompt-studio -g
Enter fullscreen mode Exit fullscreen mode

Then tell your AI assistant: "I want to make a video with HappyHorse"

Execute the assembled prompt:

bl video generate --image ./char.png --prompt "[assembled prompt]" --download output.mp4
Enter fullscreen mode Exit fullscreen mode

Links


Open-source Skill. Free tier available. Results subject to model randomness.

Top comments (1)

Collapse
 
albania_sandhu_cc7ea38a97 profile image
Albania Sandhu

The key insight here is that video prompts need temporal structure, not just a richer image description. I like separating the identity block from action, camera, audio, and continuity constraints. For testing, I’d keep the character and scene blocks verbatim, then change only one motion or camera instruction per run. That makes it much clearer whether the failure came from identity drift, timing, or conflicting directions.