### Role Assignment Examples

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Examples demonstrating how to assign specific roles to uploaded assets using the '@' reference system for detailed control over video generation.

```shell
First frame
@Image1 as the first frame
Last frame
@Image2 as the last frame
Character appearance
@Image1's character as the subject
Scene / background
scene references @Image3
Camera movement
reference @Video1's camera movement
Action / motion
reference @Video1's action choreography
Visual effects
completely reference @Video1's effects and transitions
Rhythm / tempo
video rhythm references @Video1
Voice / tone
narration voice references @Video1
Background music
BGM references @Audio1
Sound effects
sound effects reference @Video3's audio
Outfit / clothing
wearing the outfit from @Image2
Product appearance
product details reference @Image3
```

--------------------------------

### Multi-Reference Combination Example

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

An example showcasing how to combine multiple asset references for complex scene composition, character control, and audio-visual synchronization.

```shell
@Image1's character as the subject, reference @Video1's camera movement
and action choreography, BGM references @Audio1, scene references @Image2
```

--------------------------------

### Install Generative Media Skills

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/README.md

Install all skills for the Generative Media Skills package or a specific skill. Skills can also be installed for specific agents.

```bash
# Install all skills to your AI agent
npx skills add SamurAIGPT/Generative-Media-Skills --all
```

```bash
# Or install a specific skill
npx skills add SamurAIGPT/Generative-Media-Skills --skill muapi-media-generation
```

```bash
# Install to specific agents
npx skills add SamurAIGPT/Generative-Media-Skills --all -a claude-code -a cursor
```

--------------------------------

### Install muapi CLI

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/README.md

Install the muapi CLI using npm, pip, or run it directly with npx. Recommended to install globally.

```bash
# via npm (recommended — no Python required)
npm install -g muapi-cli
```

```bash
# via pip
pip install muapi-cli
```

```bash
# or run without installing
npx muapi-cli --help
```

--------------------------------

### Create Music Example

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/core/media/SKILL.md

Use this script to create music based on style and prompt. Supports various music generation tasks.

```bash
bash create-music.sh --style "lo-fi hip hop" --prompt "chill beats for studying"
```

--------------------------------

### Create Video Pipeline: Text to Video

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/workflow/SKILL.md

Example of creating a workflow to generate a short cinematic video from a text prompt.

```bash
muapi workflow create "generate a 10-second cinematic video from a text prompt using kling-master"
```

--------------------------------

### Upload File Example

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/core/media/SKILL.md

Use this script to upload local files to a CDN, making them available for use with other skills.

```bash
bash upload.sh --file ./my-image.jpg
```

--------------------------------

### Create Video Pipeline: Image to Animated Video with Lipsync

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/workflow/SKILL.md

Example of creating a workflow that animates an input image and applies lipsync from an audio file.

```bash
muapi workflow create "animate an input image with seedance, then apply lipsync from an audio file"
```

--------------------------------

### Generate Video with Custom Style

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/one-shot-video/SKILL.md

Example demonstrating how to specify a custom visual style for the generated video. Ensure your MUAPI_API_KEY is configured.

```bash
muapi video generate --model veo3.1-text-to-video --prompt "a futuristic cityscape at sunset, one continuous uncut shot, no transitions, camera slowly moves through scene, noir, handheld, golden hour, ultra cinematic, film grain, 4K quality" --aspect_ratio 16:9 --duration 10s
```

--------------------------------

### Create Image Pipeline: Text to Upscaled Image

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/workflow/SKILL.md

Example of creating a workflow that generates an image from text and then upscales it.

```bash
muapi workflow create "take a text prompt, generate with flux-dev, upscale the result"
```

--------------------------------

### Generate Video Example

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/core/media/SKILL.md

Use this script to generate a video from a text prompt using a specified model. The `--view` flag displays the generated video.

```bash
bash generate-video.sh --prompt "ocean waves at golden hour" --model minimax-pro --view
```

--------------------------------

### Create Image Pipeline: Product Shot

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/workflow/SKILL.md

Example of creating a workflow for generating a product image, removing its background, and creating a professional product shot.

```bash
muapi workflow create "generate a product image with hidream, remove background, create professional product shot"
```

--------------------------------

### Direct API Call Example (Fallback)

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/award-ceremony-video/SKILL.md

Example of how to make a direct API call using curl for model IDs without a CLI alias. This is used for advanced configurations or when a CLI command is not yet available. Remember to poll for results using the returned request ID.

```bash
curl -X POST https://api.muapi.ai/api/v1/<endpoint> \
-H "x-api-key: $MUAPI_API_KEY" \
-H 'content-type: application/json' \
-d '{...}'
```

--------------------------------

### Generate Image Example

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/core/media/SKILL.md

Use this script to generate an image from a text prompt using a specified model. The `--view` flag displays the generated image.

```bash
bash generate-image.sh --prompt "a sunset over mountains" --model flux-dev --view
```

--------------------------------

### Animate Image Example

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/core/media/SKILL.md

Use this script to animate a static image into a video with a given prompt and model. Requires an image URL and a prompt describing the animation.

```bash
bash image-to-video.sh --image-url "https://..." --prompt "camera slowly pans right" --model kling-pro
```

--------------------------------

### Generate Keyframes for a Storyboard

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/visual/storyboard/SKILL.md

This example demonstrates how to use the `muapi image generate` command to create keyframes for a storyboard. It specifies the model, aspect ratio, and prompt based on a beat description and visual style.

```bash
muapi image generate --model nano-banana-2 --aspect_ratio 16:9 --prompt "<beat description>. cinematic, photoreal, soft lighting, 16:9" --tier balanced
```

--------------------------------

### Claude Desktop MCP Server Configuration

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/README.md

Example configuration for Claude Desktop to connect to the muapi MCP server. Ensure the command, arguments, and environment variables are correctly set.

```json
{
  "mcpServers": {
    "muapi": {
      "command": "muapi",
      "args": ["mcp", "serve"],
      "env": { "MUAPI_API_KEY": "your-key-here" }
    }
  }
}
```

--------------------------------

### Negative Prompting Example

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Append negative guidance directly to your prompt using plain language at the end to specify elements to avoid. This helps refine the output by excluding unwanted characteristics.

```markdown
[your director brief above]
Avoid: camera shake, jump cuts, lens distortion, overexposure, watermarks, text overlays.
```

--------------------------------

### Submit UGC Video Generation Request

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/ugc-video-factory/SKILL.md

Use the `muapi video from-image` command to generate a UGC-style video. Ensure all parameters like start image, aspect ratio, duration, and prompt are correctly set. The prompt should describe the desired video content and style.

```bash
muapi video from-image \
  seedance-2-vip-image-to-video \
  --input "{{hero_image}}" \
  --aspect-ratio 9:16 \
  --duration 10 \
  --generate-audio true \
  --cfg-scale 0.5 \
  --negative-prompt "blur, distort, low quality" \
  --prompt "Create a 10-second vertical UGC-style video (9:16).

A person is interacting naturally with their setting and product.

The product is used naturally:
- If wearable → the person is wearing it.
- If handheld → the person is holding or applying it.

The video is a single, uninterrupted shot. No cuts. No color changes. No text on screen.

The person looks directly at the camera with a relaxed and natural expression.
They interact comfortably with the product using their hands (adjusting, holding, pointing).

They say in a natural, conversational tone:

\"{{script}}\" 

Subtle hand gestures while speaking.
End with a small smile or nod.

Style: authentic UGC, handheld phone feel, light natural movement, soft daylight, shallow depth of field, TikTok/Reels aesthetic."
```

--------------------------------

### Example muapi image edit command

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/social/social-pack/SKILL.md

This snippet shows an example of how to use the `muapi image edit` command to reframe an image for a specific aspect ratio. It includes placeholders for the source image, aspect ratio, and caption idea.

```bash
muapi image edit "$source_image" --model nano-banana-2-edit --prompt "Reframe the composition to {{aspect_ratio}} for social media. Keep the subject centred and uncropped. Match the original lighting and palette. {{caption_idea_hint}}"
```

--------------------------------

### Storyboard Structure Example

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/social/social-media-video/SKILL.md

Defines a typical structure for a social media video storyboard, including scene durations and content.

```text
0–3s:  [Opening scene — hook/visual surprise — camera move]
3–7s:  [Core message — product/subject in action — camera move]
7–10s: [Resolution — brand moment — CTA text on screen]
10–15s: [Logo/tagline hold — background music fade]
```

--------------------------------

### Draft Video Generation (480p)

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/ai-fight-scene/SKILL.md

Use the `seedance-2.0-i2v-480p` model for a cheaper preview pass to draft the video before committing to a full-resolution run. This helps in iterating on the prompt or storyboard quickly.

```bash
muapi video from-image --model seedance-2.0-i2v-480p --reference_image <storyboard_image> --prompt "..." --duration {{duration}} --aspect_ratio {{aspect_ratio}}
```

--------------------------------

### Subject Generation with nano-banana-pro

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/visual/multi-angle-reshoot/SKILL.md

Use this step to generate the base subject image when no reference image is provided. Ensure the prompt includes a detailed description of the subject and desired photographic qualities.

```bash
muapi image generate --model nano-banana-pro --prompt "A high-quality, professional photograph of {{subject_description}}. Clean studio lighting, sharp focus, realistic textures, cinematic quality." --aspect_ratio "3:4"
```

--------------------------------

### Extend Video - Chinese Tier with Directional Prompt

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Extends a video with specific subject, intent, and quality parameters for a guided continuation.

```bash
bash scripts/generate-seedance.sh --mode extend \
  --request-id "abc-123-def-456" \
  --subject "camera continues pulling back, revealing the vast city below" \
  --intent reveal --duration 10 --quality high --view
```

--------------------------------

### Generate Front View Product Shot

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/visual/multi-angle-shots/SKILL.md

Generates a front-facing product image. Use 'ai-product-photography' if a reference image is provided, otherwise 'nano-banana-pro'.

```bash
muapi image generate --model ai-product-photography --prompt "{{product_name}} — perfectly centered FRONT VIEW, eye-level angle. {{background_style}} background. {{lighting}}. Sharp focus, commercial product photography, ultra detailed, no props." --aspect-ratio 1:1
```

```bash
muapi image generate --model nano-banana-pro --prompt "{{product_name}} — perfectly centered FRONT VIEW, eye-level angle. {{background_style}} background. {{lighting}}. Sharp focus, commercial product photography, ultra detailed, no props." --aspect-ratio 1:1
```

--------------------------------

### Extend Video - Chinese Tier

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Extends an existing video using its request ID. Can be a natural extension or guided by directional prompts.

```bash
bash scripts/generate-seedance.sh --mode extend \
  --request-id "abc-123-def-456" --duration 10
```

--------------------------------

### Generate Vertical Video

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/one-shot-video/SKILL.md

Example for generating a vertical video, including specific prompt additions for smartphone framing. Ensure your MUAPI_API_KEY is configured.

```bash
muapi video generate --model veo3.1-text-to-video --prompt "a person walking through a bustling market, one continuous uncut shot, no transitions, camera slowly moves through scene, vertical format, smartphone framing, cinematic, anamorphic lens, shallow depth of field, dramatic lighting, ultra cinematic, film grain, 4K quality" --aspect_ratio 9:16 --duration 10s
```

--------------------------------

### E-commerce / Product Showcase Script

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Generate a product showcase video using a bash script. This snippet focuses on deconstructing a product with dynamic visual effects and specific aspect ratios.

```bash
bash scripts/generate-seedance.sh \
  --mode i2v \
  --file product.jpg \
  --subject "Deconstruct the product. Static camera. Hamburger suspended mid-air, rotating slowly. Ingredients separate and reassemble. Cheese continues to melt and drip. Ultimate food aesthetics." \
  --intent "product" \
  --aspect "9:16" \
  --duration 15 --quality high
```

--------------------------------

### Get Workflow Definition

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/workflow/SKILL.md

Retrieve the definition and node graph of a specific workflow using its ID. This is useful for understanding the structure of an existing workflow.

```bash
muapi workflow get <id>
```

--------------------------------

### Generate Animal Vlogger Video with Lip-Sync

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/animal-video-generator/SKILL.md

After image approval, use `muapi video generate` or `muapi video from-image` to animate the vlogger. The reference image from Phase A is required. The prompt should describe the video's action, setting, and the animal's expression. Include the dialogue for lip-sync if the tool supports it. Maintain a 9:16 aspect ratio.

```bash
muapi video from-image --model veo3.1-fast-image-to-video --reference-image <generated_image_path> --prompt "Create an ultra-realistic cinematic video featuring a lifelike {{animal_type}} vlogging with a selfie stick on the {{location}}. The film starts in selfie mode, camera slightly wide-angle. The {{animal_type}} is expressive, looks mildly disgruntled, and speaks naturally. Occasional quick zoom-in on the disappointed face. Background features busy street life, vibrant colors. Smooth gimbal-like camera motion." --dialogue "{{script}}" --aspect-ratio 9:16
```

--------------------------------

### Director Brief Structure

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Use this six-component hierarchy to structure your prompts for Seedance 2.0. The order is crucial, starting with composition and ending with texture and micro-motion.

```markdown
| Component | Instruction Type |
|:---|:---|:---|
| **Scene** | Environment + Lighting |
| **Subject** | Identity + Detail |
| **Action** | Fluid Interaction |
| **Camera** | Movement + Lens + Speed |
| **Audio** | Music + SFX + Ambience |
| **Pacing/Style** | Timing + Mood + Grade |
```

--------------------------------

### Image-to-Video (i2v) - VIP Fast Tier with Multiple Images

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Uses multiple images (3+) for i2v generation in VIP fast mode, enabling omni reference mode.

```bash
bash scripts/generate-seedance.sh --mode i2v --tier vip --fast \
  --file char.jpg --file env.jpg --file style.jpg \
  --subject "@image1 character walks through @image2's environment in @image3's style" \
  --duration 10
```

--------------------------------

### Generate Video from Storyboard

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/ai-fight-scene/SKILL.md

Use this command to generate a video from a 16-cell storyboard reference image. Ensure the prompt strictly follows the storyboard cell-by-cell and incorporates specified camera movements and audio cues. The duration and aspect ratio can be customized.

```bash
muapi video from-image --model seedance-v2.0-i2v --reference_image <storyboard_image> --prompt "Generate a {{duration}}-second action sequence that strictly follows the 16-cell storyboard reference image, cell-by-cell, top-left to bottom-right.

- Honour each cell's labelled SHOT SIZE and CAMERA-MOVE — match cuts to the storyboard's rhythm notes.
- Strong cinematic feel and shot language. Exaggerated dynamics. Hits land hard with motion blur and impact frames.
- Camera language: anamorphic, handheld where the storyboard calls for it, locked-off where it doesn't.
- Native audio: impact sfx on every IMPACT cell, footsteps, fabric/Foley, restrained low score under the action.

Action being rendered: {{action_script}}.
Aesthetic: {{style_direction}}."
--duration {{duration}}
--aspect_ratio {{aspect_ratio}}
```

--------------------------------

### Image-to-Video (i2v) - Chinese Tier with References

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Animates a video from an image, using video and audio references for motion and background.

```bash
bash scripts/generate-seedance.sh --mode i2v \
  --file character.jpg --video-file ref_motion.mp4 --audio-file bgm.mp3 \
  --subject "@image1's character walks forward, @video1's camera movement, BGM references @audio1" \
  --quality high --view
```

--------------------------------

### Generate Cooking Video CLI Command

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/storyboard-to-cooking-video/SKILL.md

Use this CLI command to generate a cooking video. It requires a person image, a reference sheet, and various parameters to define the video's aspect ratio, duration, resolution, and prompt.

```bash
muapi video generate \
  --model bytedance-seedance-2-0-reference-to-video-fast \
  --image "{{person_image}}" \
  --image "{{reference_sheet_url}}" \
  --aspect-ratio "{{aspect_ratio}}" \
  --duration "{{duration_seconds}}" \
  --resolution "{{resolution}}" \
  --generate-audio true \
  --prompt "The person in @Image1 is the subject — preserve their exact face, hair, eye color, skin tone, and all facial features with 100% accuracy throughout the entire video.
Use @Image2 as the visual and narrative guide — follow the cooking steps, kitchen setting, outfit, and atmosphere shown in the reference sheet exactly.
A single continuous cinematic video of the person from @Image1 making {{dish}} in the {{kitchen_style}} kitchen shown in @Image2. They wear {{outfit}} throughout.

VIDEO STRUCTURE
Follow the exact 9-step sequence as shown in @Image2, beat by beat, from raw ingredients through preparation to a final plated close-up.

MOTION STYLE
- Slow, deliberate, satisfying transitions between each step
- Natural hand and body movement with clear culinary intent
- Continuous flow with no jump cuts
- Warm and immersive pacing

CAMERA & CINEMATOGRAPHY
- Close-up shots for hands during mixing, kneading, cutting, plating
- Medium shots showing the person working at the counter
- Pull back slightly for the final plating to reveal the full kitchen
- Shallow depth of field — focus on hands and food, soft background blur
- No abrupt cuts — smooth match cuts and fluid transitions

VISUAL STYLE
- Warm natural daylight from a large kitchen window
- Rich tactile textures matching @Image2's environment
- Full color, warm cinematic color grading

CONSISTENCY RULES
- Same character throughout — face of @Image1 in every frame
- Same outfit across entire video
- Same kitchen environment as shown in @Image2

AUDIO
- Soft kitchen ambience, gentle culinary SFX (chopping, sizzling, pouring), light cinematic underscore
- No dialogue, no narration

OUTPUT STYLE
- Duration: exactly {{duration_seconds}} seconds
- Polished, cinematic, premium cooking show quality
- Ends with a beautiful close-up of the finished plated {{dish}}"
```

--------------------------------

### Get Workflow Details

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/workflow/SKILL.md

Retrieve the details of a specific workflow, including its structure and required inputs. Use the --output-json flag for raw JSON output.

```bash
muapi workflow get <workflow_id>
```

```bash
muapi workflow get <workflow_id> --output-json
```

--------------------------------

### Fallback to Raw Endpoint with Curl

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/one-shot-video/SKILL.md

Use this command when a direct CLI alias is not available for a specific muapi endpoint. This example shows a POST request to the generation endpoint.

```bash
curl -X POST https://api.muapi.ai/api/v1/video/generate -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{ "model": "veo3.1-text-to-video", "prompt": "a chef plating food in a moody Michelin-star kitchen, one continuous uncut shot, no transitions, camera slowly moves through scene, cinematic, anamorphic lens, shallow depth of field, dramatic lighting, ultra cinematic, film grain, 4K quality", "aspect_ratio": "16:9", "duration": "10s" }'
```

--------------------------------

### Product Rendering with muapi image edit

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/product-video-ad-maker/SKILL.md

Use this command to re-render a product image in a premium setting. Ensure the reference image is provided and the prompt includes scene descriptions and desired photographic qualities.

```bash
muapi image edit --model flux-2-pro-edit \
  --reference-image "{{product_image}}" \
  --prompt "A high-end, professional commercial photograph of the product from the reference image, {{scene_description}}. Soft studio lighting, realistic reflections, cinematic depth of field, sharp focus on the product. 8k resolution, elegant and minimal composition." \
  --aspect-ratio "1:1 or 4:5"
```

--------------------------------

### Generate Desktop Redesign Mockup (without screenshot)

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/visual/url-to-design/SKILL.md

Use 'muapi image generate' to create a full-page desktop redesign mockup when no screenshot is provided. This is part of the 'URL to Design' skill.

```bash
muapi image generate \
  --model gpt4o-text-to-image \
  --prompt "Professional UI/UX redesign of a {{page_type}} for the website at {{url}}. {{redesign_style}} design. Modern web design, 2025 aesthetic. Includes: hero section with clear headline and CTA button, features/benefits section, social proof, clean footer. Pixel-perfect, Figma-quality mockup. Desktop viewport, 1440px width design." \
  --aspect_ratio 9:16
```

--------------------------------

### Get Workflow Outputs

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/workflow/SKILL.md

Retrieve the final output URLs of a completed workflow execution. Use the `--download` flag to specify a local directory for downloading results.

```bash
muapi workflow outputs <run_id> --download ./results
```

--------------------------------

### Time-Segmented Prompt Example

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

For videos longer than 10 seconds, break down prompts into timed segments for precise control over the narrative flow. Each segment should ideally contain a single action.

```markdown
0–3s: [opening scene, camera move, establishing action]
3–6s: [mid-section development, subject in motion]
6–10s: [climax or key action beat]
10–15s: [resolution, brand/product hold, text/tagline fade in]
```

--------------------------------

### Generate Desktop Redesign Mockup (with screenshot)

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/visual/url-to-design/SKILL.md

Use 'muapi image edit' to generate a full-page desktop redesign mockup when a screenshot is provided. This is part of the 'URL to Design' skill.

```bash
muapi image edit \
  --model gpt4o-edit \
  --prompt "Professional UI/UX redesign of a {{page_type}} for the website at {{url}}. {{redesign_style}} design. Modern web design, 2025 aesthetic. Includes: hero section with clear headline and CTA button, features/benefits section, social proof, clean footer. Pixel-perfect, Figma-quality mockup. Desktop viewport, 1440px width design." \
  --aspect_ratio 9:16 \
  --screenshot {{screenshot}}
```

--------------------------------

### Drone Flythrough Prompt Enrichment Example

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/social/social-media-video/SKILL.md

Enhance prompts for drone flythrough shots with cinematic details. Specify altitude, camera movement, atmosphere, and aesthetic for aerial cinematography.

```text
Cinematic aerial drone shot. Camera descends from 200m altitude toward [subject/scene],
sweeping lateral arc as it descends. Gimbal-stabilized smooth motion.
Golden hour atmosphere, long shadows across [terrain/scene].
Final frame settles into medium establishing shot.
Aerial cinematography, DJI Inspire aesthetic.
```

--------------------------------

### Prompt Optimization - Physics Directives

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Employ physics-related terms to describe lighting conditions more effectively. Instead of 'good lighting,' use phrases like 'caustic patterns' or 'volumetric rays'.

```markdown
2. **Physics Directives**: Use "caustic patterns," "volumetric rays," or "subsurface scattering" instead of "good lighting."
```

--------------------------------

### Generate Reference Sheet using muapi CLI

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/storyboard-to-cooking-video/SKILL.md

Use the muapi image edit command to create a composite reference board. This includes character details, kitchen environment, and a 9-panel action board for the cooking tutorial. Ensure the `--prompt` accurately reflects the desired dish, style, and character appearance.

```bash
muapi image edit \
  --model gpt-image-v2-edit \
  --image "{{person_image}}" \
  --image-size "3840x2160" \
  --quality auto \
  --background auto \
  --moderation low \
  --output-format png \
  --prompt "Create one single composite reference sheet for a {{duration_seconds}}-second realistic {{dish}}-making tutorial video. The image should be a clean, high-end production reference board, not a poster with heavy text. Format: {{aspect_ratio}} wide reference sheet, elegant white margins, clean grid layout, realistic cinematic photography style. Concept: {{dish}} tutorial in a {{kitchen_style}} kitchen.

Top row: motion / choreography guide with 9 numbered cinematic action panels showing the {{dish}} process step-by-step from raw ingredients to final plated dish.

Middle-left: realistic character reference sheet of the uploaded person — preserve their exact face, hair color, hair texture, eye color, skin tone, and all facial features with 100% accuracy. Show the same person in: face close-up, full-body front view, side/action working pose, and back view. Dress them in {{outfit}}. Keep them grounded, approachable, skilled, and cinematic.

Middle-right / background: location reference sheet of an elegant {{kitchen_style}} kitchen with tactile surfaces, natural daylight from a large window, hanging cookware, herbs, and premium cooking atmosphere appropriate to the cuisine.

Style: realistic, cinematic, warm natural light, shallow depth of field, tactile food photography, premium cooking show aesthetic, rich surface textures.

Bottom strip: simple visual icons only for {{duration_seconds}} seconds, {{aspect_ratio}}, realistic, cinematic, tasty, natural camera. Minimal text, no dense paragraphs. Let the visuals do the heavy lifting."
```

--------------------------------

### Create Music Track

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/music-video/SKILL.md

Creates a music track for the video using specified style tags and duration. The duration should account for all scenes plus a short tail.

```bash
muapi audio create --kind music --music_style "{{music_style}}" --duration "N*5 + 2"
```

--------------------------------

### Animating Scenes with Image-to-Video Models

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/character-story-video/SKILL.md

Animate the generated scenes into video parts using an image-to-video model. This snippet shows example prompts for animating different parts of the story.

```bash
muapi kling-v3.0-pro-image-to-video --input "Scene 1 Image" --prompt "Cinematic animation of the scene, character comes to life, subtle natural movements, high quality 3D animation."
```

```bash
muapi veo3.1-image-to-video --input "Scene 2 Image" --prompt "Cinematic animation of the scene, character comes to life, dynamic action, high quality 3D animation."
```

```bash
muapi kling-v3.0-pro-image-to-video --input "Scene 3 Image" --prompt "Cinematic animation of the scene, character comes to life, triumphant resolution, high quality 3D animation."
```

--------------------------------

### Async Job Submission and Status Check

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Submit a job asynchronously to get a request ID immediately. Later, check the job status using the obtained request ID.

```bash
# Submit and get request_id immediately
RESULT=$(bash scripts/generate-seedance.sh --tier vip --fast --subject "..." --async --json)
REQUEST_ID=$(echo "$RESULT" | jq -r '.request_id')

# Check status later
bash ../../../../core/media/generate-video.sh --result "$REQUEST_ID"
```

--------------------------------

### Prompt Optimization - Multi-Image i2v

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Provide up to 9 reference images for image-to-video generation. The model will blend stylistic, identity, and environmental aspects from all provided images.

```markdown
6. **Multi-Image i2v**: Provide up to 9 reference images. The model blends aspects (style, identity, environment) across all inputs.
```

--------------------------------

### Camera Language - Basic Movements

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Reference for basic camera movements used in prompt optimization. These terms describe fundamental ways the camera can reposition or rotate.

```markdown
| Term | Description |
|:---|:---|:---|
| Push in / Slow push | Camera moves toward subject |
| Pull back / Pull away | Camera moves away from subject |
| Pan left/right | Camera rotates horizontally |
| Tilt up/down | Camera rotates vertically |
| Track / Follow shot | Camera follows subject movement |
| Orbit / Revolve | Camera circles around subject |
| One-take / Oner | Continuous shot with no cuts |
```

--------------------------------

### Run muapi as MCP Server

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/README.md

Run muapi as a Model Context Protocol server to allow MCP-compatible agents to call generation tools directly. This command starts the server.

```bash
muapi mcp serve
```

--------------------------------

### Video Ad Generation with muapi video from-image

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/product-video-ad-maker/SKILL.md

Generate a cinematic product advertisement video from a premium product image. This command uses the 'wan2.5-image-to-video-fast' model and requires a prompt detailing the desired video style and camera movement.

```bash
muapi video from-image --model wan2.5-image-to-video-fast \
  --reference-image "<premium_image_from_phase_A>" \
  --prompt "A cinematic product advertisement video. Smooth, slow-motion camera movement panning across the product. Subtle environmental movements (e.g., leaves swaying, light shifting). High-quality commercial cinematography, elegant transitions, professional look." \
  --aspect-ratio "16:9 or 9:16"
```

--------------------------------

### Fashion Video Generation Command

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/visual/fashion-try-on/SKILL.md

Use this command to generate a professional fashion video from a try-on image. This is an optional step after the image try-on.

```bash
muapi video from-image --model seedance-v1.5-pro-i2v-fast --reference-image "{{try_on_image}}" --prompt "Shot type of Three-Quarter Length Shot. [Push in] as model gracefully places hand on hip, shifts weight to one side, tilts head slightly with soft smile, and gently adjusts hair with fingertips, creating elegant movement and confidence." --aspect-ratio 9:16
```

--------------------------------

### FPV Prompt Enrichment Example

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/social/social-media-video/SKILL.md

Enrich your prompts with specific details for First-Person View (FPV) shots. This includes camera motion, scene details, and subject visibility for an immersive experience.

```text
Immersive first-person POV shot. Camera glides forward through [scene] at eye level.
Slight natural motion stabilization with GoPro-style wide angle.
Peripheral detail rushing past — [details]. Smooth continuous forward motion.
No cuts throughout. [Subject] visible in foreground periphery.
```

--------------------------------

### Install/Upgrade muapi CLI

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/workflow/SKILL.md

Ensure the muapi CLI is up-to-date by reinstalling from the local source path. Replace the placeholder with the actual directory path.

```bash
pip install --upgrade /path/to/muapi-cli
```

--------------------------------

### Common Negative Prompt Additions

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Utilize these common negative prompt additions to further guide the generation process, tailored for specific output requirements like single-take shots or product-only content.

```markdown
- `Avoid: abrupt cuts, scene changes, multiple locations.` (for single-take shots)
- `Avoid: human faces, realistic people.` (for product-only content)
- `Avoid: fast motion, blur, unstable framing.` (for smooth product reveals)
```

--------------------------------

### Generate Short Ad Video

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/social/product-campaign/SKILL.md

Creates a short ad video for the product campaign. Uses 'kling-v3.0-pro-image-to-video' if a product image is provided, otherwise 'veo3.1-text-to-video'. The video should be 8-10 seconds long with a 16:9 aspect ratio.

```bash
muapi video generate --model kling-v3.0-pro-image-to-video --aspect-ratio 16:9 --duration 8-10 --prompt "{{campaign_message}} — product campaign video for {{product_name}}. {{visual_style}} cinematic style. Dynamic reveal, product hero moment, {{target_audience}} lifestyle context. Professional commercial grade, 4K quality, smooth camera motion."
```

```bash
muapi video generate --model veo3.1-text-to-video --aspect-ratio 16:9 --duration 8-10 --prompt "{{campaign_message}} — product campaign video for {{product_name}}. {{visual_style}} cinematic style. Dynamic reveal, product hero moment, {{target_audience}} lifestyle context. Professional commercial grade, 4K quality, smooth camera motion."
```

--------------------------------

### Prompt Optimization - Technical Grammar

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Incorporate specific camera terminology into your prompts for precise control over visual elements. Use terms like 'Dolly In/Out' and 'Shallow Depth of Field' to guide the AI.

```markdown
1. **Technical Grammar**: Use camera terms: *Dolly In/Out, Crane Shot, Whip Pan, Tracking Shot, Anamorphic Lens, Shallow Depth of Field, High-Speed Dive, Orbital Arc*.
```

--------------------------------

### Global/VIP Omni Input References

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/seedance-2/SKILL.md

Syntax for assigning roles to uploaded assets in Global/VIP tiers for omni modes. Video references are not supported.

```shell
@image1  @image2  ...  @image9    (images_list order)
@audio1  @audio2  @audio3         (audio_files order)
```

--------------------------------

### Create Fintech Logo

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/visual/logo-creator/SKILL.md

Invoke the create-logo.sh script to generate a logo for a fintech brand named 'Aura'. This example specifies a concept of a geometric security shield with a spark, a minimalist style, and a black and gold color scheme.

```bash
bash scripts/create-logo.sh \
  --brand "Aura" \
  --concept "geometric security shield with a spark" \
  --style minimalist \
  --color "black and gold"
```

--------------------------------

### Seedance Director Prompt for Social Media Video

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/social/social-media-video/SKILL.md

This prompt guides the Seedance Director to generate specific video segments, detailing camera angles, lighting, and subject focus for a premium cold brew coffee ad.

```text
0–2s:  Cinematic aerial drone shot. Camera descends at 30° angle toward a rooftop terrace at sunrise.
Golden hour atmosphere, San Francisco bay fog below horizon. Gimbal-stabilized smooth descent.
2–5s:  Drone rapidly closes toward a glass of cold brew coffee on white marble.
Steam curling upward. Macro lens approach. Caustic light patterns on wet glass surface.
5–9s:  Slow precision orbit around cold brew bottle. Black matte label with gold embossed text catching
specular highlights. Ice cubes with subsurface light scattering. Commercial macro aesthetic.
9–11s: Static product hero shot. Letterbox crop, deep focus, black fade in from sides.
Sound: Minimal ambient beat, single piano note, coffee liquid sound effect at 5s mark.
Maintain cinematic color grade — deep blacks, warm gold midtones throughout.
```

--------------------------------

### Generate Lifestyle Image (with existing product image)

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/visual/amazon-product-listing/SKILL.md

Generates a lifestyle image showing the product in use by the target buyer, using the 'ai-product-shot' model when an existing product image is provided.

```bash
muapi image generate --model ai-product-shot --prompt "Amazon lifestyle image of {{product_name}} being used by {{target_buyer}} in a natural setting. {{product_category}} product in real-life use context. Warm natural lighting, aspirational but relatable, slight bokeh background. Commercial lifestyle photography, professional quality." --aspect-ratio 1:1 --output-dir ./output --output-prefix lifestyle-image
```

--------------------------------

### Execute a Workflow with Specific Inputs

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/workflow/SKILL.md

Run a previously created or discovered workflow, providing specific input values for its nodes. Use the --download flag to save results locally.

```bash
muapi workflow execute <workflow_id> \
  --input "node1.prompt=a glowing crystal cave at midnight"
```

```bash
muapi workflow execute <workflow_id> \
  --input "node1.prompt=a sunset" \
  --download ./outputs
```

--------------------------------

### Run Expert Skill: Nano-Banana Art Generation

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/README.md

Execute the Nano-Banana script to generate a 2K art masterpiece from a source image, specifying subject, style, and resolution.

```bash
bash library/visual/nano-banana/scripts/generate-nano-art.sh \
  --file ./my-source-image.jpg \
  --subject "a glass hummingbird" \
  --style "macro photography" \
  --resolution "2k" \
  --view
```

--------------------------------

### Generate Video from Text

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/motion/one-shot-video/SKILL.md

Use this command to generate a video from a text description when no reference image is provided. Ensure your MUAPI_API_KEY is configured.

```bash
muapi video generate --model veo3.1-text-to-video --prompt "a chef plating food in a moody Michelin-star kitchen, one continuous uncut shot, no transitions, camera slowly moves through scene, cinematic, anamorphic lens, shallow depth of field, dramatic lighting, ultra cinematic, film grain, 4K quality" --aspect_ratio 16:9 --duration 10s
```

--------------------------------

### Generate Hero Image (with existing product image)

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/visual/amazon-product-listing/SKILL.md

Generates a professional Amazon hero image with a pure white background using the 'ai-product-photography' model when an existing product image is provided.

```bash
muapi image generate --model ai-product-photography --prompt "Professional Amazon main listing hero image of {{product_name}}. Pure white background #FFFFFF. Product centered, perfectly lit with soft studio lighting, no shadows. High resolution, commercial product photography, sharp focus on all details, 2000x2000px equivalent quality." --aspect-ratio 1:1 --output-dir ./output --output-prefix hero-image
```

--------------------------------

### Fashion Try-On Command

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/visual/fashion-try-on/SKILL.md

Use this command to perform the virtual try-on by combining a person's image and a clothing item. Ensure both reference images are provided.

```bash
muapi image edit --model qwen-image-edit-2511 --reference-images "{{person_image}}" "{{clothing_image}}" --prompt "A high-quality fashion photograph of the person from the first reference image wearing the exact clothing item from the second reference image. The fit should be natural and realistic, maintaining the person's pose and the clothing's texture and patterns. Soft studio lighting, neutral background, professional fashion photography style." --aspect-ratio 1:1
```

--------------------------------

### Generate 360 Spin Video

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/visual/multi-angle-shots/SKILL.md

Suggests creating a 360-degree spin video from generated images using the 'kling-v3.0-pro-image-to-video' model.

```bash
kling-v3.0-pro-image-to-video
```

--------------------------------

### Browse Workflow Templates

Source: https://github.com/samuraigpt/generative-media-skills/blob/main/library/workflow/SKILL.md

Use `muapi workflow templates` to view available workflow templates. This command requires no arguments.

```bash
muapi workflow templates
```