Skip to main content
ClaudeWave
EN, English
Skill780 repo starsupdated 1mo ago

higgsfield-vibe-motion

Vibe Motion is a Claude-powered motion graphics tool that generates Remotion code for programmatic video rather than predicting pixel sequences, ensuring text remains crisp and physics stays controllable. Use it for kinetic typography, logo animations, explainer graphics, data visualizations, and branded motion assets where structure and timing matter more than cinematic storytelling.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill /tmp/higgsfield-vibe-motion && cp -r /tmp/higgsfield-vibe-motion/skills/higgsfield-vibe-motion ~/.claude/skills/higgsfield-vibe-motion
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Higgsfield Vibe Motion

## What Vibe Motion Actually Is (And How It Differs from Video Generation)

This is the most important thing to understand about Vibe Motion:

| Standard AI Video Generation | Vibe Motion |
|------------------------------|------------|
| Predicts pixel sequences | Generates Remotion code |
| Text can hallucinate or distort | Text is always crisp (it's code) |
| Each change = full re-render | Real-time edits on live canvas |
| Physics is emergent/unpredictable | Physics is a slider you control |
| Output: video file | Output: motion graphic + deployable code |
| Good for: cinematic scenes | Good for: brand, typography, data, structure |

**Vibe Motion is powered by Claude (Anthropic) and Remotion** — the open-source
React framework for programmatic video. It generates actual code that renders
deterministically, meaning the same prompt always produces the same output.
Text never breaks. Colors stay exact. Brand consistency is guaranteed.

**Location:** higgsfield.ai/vibe-motion

---

## What Vibe Motion Is Built For

Use Vibe Motion when your content is about **structure, timing, and information**
rather than cinematic storytelling.

✅ **Perfect use cases:**
- Kinetic typography and text animations
- Logo animations and brand intros/outros
- Product feature explainer animations
- Infographic animations and data visualization
- Presentation slide animations
- Social media motion graphics (lower thirds, title cards, CTAs)
- App demo animations
- Countdown timers, score boards, data dashboards
- Launch campaign motion assets

❌ **Wrong tool for:**
- Cinematic scenes with characters (use Kling/Sora/Cinema Studio)
- Photorealistic video (use standard video generation)
- Nature/environment footage (use Veo 3)
- Anything requiring actor performance (use Kling + Lipsync)

---

## The Vibe Motion Workflow

### Step 1: Start in Chat
Describe your motion idea in natural language — as if briefing a motion designer.
Upload any assets you want animated: logo, product image, brand photos, PDFs.

**The AI remembers the full conversation** — you can refine iteratively through
follow-up messages without starting over.

```
Example opening prompts:
"Create a kinetic typography intro for a productivity app called Flowstate.
The tagline is 'Do less. Achieve more.' Brand colors: deep navy and electric lime."

"Animate this logo [upload] with a clean reveal — letters coming in one by one,
finishing with a subtle pulse. Professional, not flashy."

"Build an infographic animation showing our 3 key stats:
42% faster, 10x more leads, $2M saved. Minimal style, white background."
```

---

### Step 2: Choose a Format or Template
Vibe Motion has templates for common formats — start from one to skip setup:

| Template category | Examples |
|-------------------|---------|
| **Text Animation** | Kinetic typography, quote cards, lyric videos |
| **Infographics** | Stat reveals, bar charts, comparison slides |
| **Posters** | Animated poster with text + image |
| **Brand** | Logo animation, brand intro/outro, bumper |
| **Social** | Story animations, Reels titles, YouTube intros |
| **Product** | Feature callouts, spec animations, launch reveals |

**When to use a template:** Always for standard formats. Templates have complex
motion logic already built in — you just replace the content.

**When to start from scratch:** Custom motion systems, unusual layouts, highly
specific brand behavior.

---

### Step 3: Set the Vibe (Color + Energy)

**Color palette presets:** Mosaic · Prism · Candy · Minimal · Dark · Brand (custom)

**Animation Speed slider:** Controls the Physics parameter
- **Slow:** Smooth, luxurious, editorial — good for fashion, premium brand
- **Medium:** Balanced, professional — good for most business content
- **Fast/Sharp:** Energetic, snappy — good for tech, sports, trend content

---

### Step 4: Real-Time Editing Controls

After generation, every element is directly editable:

| Control | What you can change |
|---------|-------------------|
| **Font Family** | Any typeface — click text element to change |
| **Text Color** | Exact color — use hex for brand accuracy |
| **Font Size** | Scale text elements independently |
| **Background Color** | Global or per-element background |
| **Animation Speed** | Global physics slider — dial up or down |

**Iterating with chat:** Any follow-up instruction adjusts the existing animation
without regenerating from scratch:

```
"Make the entrance faster — cut the timing in half"
"Change the headline font to something more geometric"
"The blue is too bright, move it to #1A2B8C"
"Add a subtle particle effect in the background"
"Make it feel more like an Apple keynote"
```

---

## Prompting Patterns for Vibe Motion

### Typography / Text Animation

Structure: `[What text] + [how it enters] + [timing feel] + [style]`

```
"The words 'CLARITY. SPEED. RESULTS.' appear one at a time, each letter
scaling in from small with a sharp snap. Inter font, all caps, white on black.
Each word holds for 0.8 seconds then the next appears. Total: 4 seconds."
```

```
"A single sentence builds word by word from left to right:
'The future of [pause] design [pause] is [pause] here.'
Clean sans-serif, navy blue, minimal white background.
Elegant timing — feels like Apple copy."
```

---

### Logo Animation

Structure: `[Logo behavior] + [reveal style] + [hold duration] + [feel]`

```
"The logo [upload] fades in letterform by letterform, left to right.
Once fully revealed, it pulses once subtly — scale up 3%, back down.
Clean, professional. White background. Total: 2.5 seconds."
```

```
"The icon [upload] draws itself on — like a pen tracing the outline —
then the wordmark slides in from the right. Bold, confident, tech brand feel.
Dark background, logo in white."
```

---

### Infographic / Stats Animation

Structure: `[What data] + [reveal animation] + [visual hierarchy] + [style]`

```
"Three statistics animate in sequence:
1. '10M+' — counter counts up from 0, l
higgsfieldSkill

>

higgsfield-actingSkill

Writes the character-performance layer of a video prompt as behavior under pressure, not displayed emotion — objective, obstacle, tactics, beats, subtext, listening, body/status/proxemics, and mandatory eye life. Produces a reusable 150–220-word acting master profile per character plus a per-scene rewrite of it, and a locked voice prompt. Use whenever a prompt needs acting, performance, or emotion direction; whenever characters read wooden, dead-eyed, or 'AI'; whenever a character must stay themselves across many shots; or when the user asks for character behavior, mannerisms, tics, a gait, or how someone reacts. Pairs with higgsfield-facs (muscle-level AU codes) and higgsfield-seedance (the prompt the paragraph goes into).

higgsfield-appsSkill

>

higgsfield-assistSkill

>

higgsfield-audioSkill

>

higgsfield-cameraSkill

>

higgsfield-canvasSkill

Use when the user mentions Higgsfield Canvas, a node-based or node graph workspace, an infinite board/canvas, chaining generations into a pipeline, or wants to wire prompts → images → videos across models on one surface. Covers what Canvas is, the node categories, the seven models that run inside Canvas, the named canvas patterns (Simple Seedance, Extend Video, Image Edit, StoryBoard With Elements, Long Video fan-out), the build-free / generate-paid cost model, reusable templates, assets-as-nodes, and Shared Canvas live collaboration. Also trigger on 'Higgsfield ComfyUI alternative', 'node workflow', or 'connect nodes to build a scene/campaign'.

higgsfield-character-designSkill

Pre-production story-and-character development for Higgsfield projects — the upstream layer that decides WHAT to prompt before any model runs. Use when the user wants to build a character, design a world, develop a story or premise, create a character sheet / character bible / story bible, lock a visual style or 'visual DNA', plan a multi-shot narrative with consistent characters, or says things like 'help me design a character', 'build the world', 'I need a backstory', 'make this character consistent across shots', 'develop my film/series concept', or 'I keep getting generic AI characters'. Routes the locked outputs into higgsfield-prompt + the right model. Adapted from Higgsfield's official character-design framework by @vavavinca.