### Example I2V Prompt

Source: https://help.scenario.com/articles/4698346156-happy-horse-by-alibaba-taotian-lab-the-essentials

This prompt demonstrates how to describe evolving actions and atmosphere for I2V generation, starting from a given image.

```text
A fox, owl, rabbit, and bear gather around a campfire,
cooking stew together. The owl reads from a book while the bear tastes soup.
```

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

### MAI Image 2.5 Text-to-Image Prompt Example

Source: https://help.scenario.com/articles/8103274871-mai-image-2-5-photorealistic-generation-and-editing

Example prompt for fantasy key art. Describe the scene, characters, mood, and any text for a high-impact visual.

```text
Epic fantasy video game key art. Colossal crystal-armored serpent rising from a cracked desert arena, four heroes in dramatic combat poses below, storm clouds and lightning. Title text "ABYSS WARDEN" in bold metallic serif across the top sky. Cinematic Unreal Engine lighting, ultra-detailed VFX, AAA promotional quality.
```

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

### Example MiniMax Music Cover Prompts

Source: https://help.scenario.com/articles/2874927950-minimax-music-cover-the-essentials

These examples demonstrate how to structure prompts to define the desired musical style, instrumentation, vocal characteristics, genre, and mood for the generated music cover.

```text
Bossa nova, nylon string guitar, gentle percussion, breathy female vocal, 110 BPM, sunny and breezy
```

```text
Vintage jazz, warm upright bass, walking piano chords, brushed snare, crooner male vocal, 100 BPM, smoky and intimate
```

```text
Festival EDM, massive synth leads, four-on-the-floor kick, euphoric female vocal chops, 128 BPM, anthemic
```

```text
Cinematic orchestral, full strings, brass fanfare, epic choir, no solo vocal, 70 BPM, heroic and sweeping
```

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

### Multi-stage BACKWARD Transformation Example 1

Source: https://help.scenario.com/articles/3604099375-building-edit-lora-training-sets

Chain multiple BACKWARD steps when a single step does not achieve the desired BEFORE state. This example shows converting a finished render to a rough sketch.

```text
Finished render (AFTER) → flat color base → line art → rough sketch (BEFORE)
```

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

### Text to Motion 3.0 - Combat Combo Example

Source: https://help.scenario.com/articles/6720109441-uthana-motion-the-essentials

Another example for Text to Motion 3.0, focusing on a combat sequence. This demonstrates generating a sword-drawing and striking motion.

```text
prompt: draws a sword, performs a three-strike combo, then sheathes it
length: 8
fps: 30
rewritePrompt: true
```

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

### Multi-stage BACKWARD Transformation Example 2

Source: https://help.scenario.com/articles/3604099375-building-edit-lora-training-sets

Use intermediate states that mimic a real user's input at inference time. This example illustrates converting a realistic portrait to a sketch at a different angle using multiple steps.

```text
AFTER → intermediate state 1 → intermediate state 2 → BEFORE
```

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

### Effective T2V Prompt Example

Source: https://help.scenario.com/articles/4698346156-happy-horse-by-alibaba-taotian-lab-the-essentials

This is an example of a well-structured prompt for T2V generation. It focuses on scene description and visual elements, which the model interprets to create video.

```text
Luxury treehouse spiraling around a giant redwood, glass balconies
with tropical ferns, warm golden interior lights,
morning mist
drifting through pine forest, small waterfall in background,
golden hour, cinematic, photorealistic
```

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

### Constructing Basic Authentication Header

Source: https://help.scenario.com/articles/5230750240-getting-started-authentication

This example demonstrates how to combine your API key and secret, encode them in Base64, and format the Authorization header for Basic Authentication.

```text
Authorization: Basic <Base64String>
```

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

### MAI Image 2.5 Text-to-Image Prompt Example

Source: https://help.scenario.com/articles/8103274871-mai-image-2-5-photorealistic-generation-and-editing

Example prompt for generating a food poster. Detail the subject, style, and any text elements required. Focus on descriptive language for desired outcome.

```text
Japanese tonkotsu ramen promotional poster. Black ceramic bowl with rich creamy broth, soft-boiled egg halved, chashu pork belly slices, crisp nori, vibrant scallions. Dramatic steam curling upward against a near-black background. Vertical Japanese text "ラーメン" beside the bowl. Michelin-level food photography, award-winning chiaroscuro composition.
```

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

### Memory Entry Examples

Source: https://help.scenario.com/articles/9101671137-node-agent-memory

Examples of short, factual lines you can use to seed or edit the assistant's memory for consistent future interactions.

```plaintext
Lyra (recurring hero): silver hair, amber eyes, lavender cloak.
We ship store screenshots at 3:2; in-game art caps at 16:9.
Prefers GPT Image 2 for stills and Seedance 2.0 for video.
Edits in place with a mask rather than regenerating.
Rejects the first background pass and asks for stronger rim light.
```

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

### MAI Image 2.5 Text-to-Image Prompt Example

Source: https://help.scenario.com/articles/8103274871-mai-image-2-5-photorealistic-generation-and-editing

Example prompt for an athletic campaign poster. Include details on the subject, action, background, and text elements for a dynamic visual.

```text
Premium athletic brand campaign poster. Male sprinter exploding from starting blocks, chalk dust frozen mid-air, veins and sweat hyperreal. Matte black compression kit with subtle reflective strips. Deep charcoal gradient background with blazing amber motion trails. Large metallic headline "FORGE" top left, subhead "BREAK LIMITS" in sharp modern sans-serif woven into smoke. Cinematic sports photography masterpiece.
```

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

### MAI Image 2.5 Text-to-Image Prompt Example

Source: https://help.scenario.com/articles/8103274871-mai-image-2-5-photorealistic-generation-and-editing

Example prompt for generating a fashion editorial cover. Specify subject, style, mood, composition, lighting, and exact text. Long, specific prompts yield better results.

```text
1960s high-fashion magazine cover blending photoreal portrait with fashion-illustration linework. Model in sculptural ivory coat with sharp geometric shoulder wings and sunray pleats across the torso, aloof editorial gaze. Masthead text "MAISON" in bold classic red serif across the top. Date line "SEPTEMBER 1968" upper left. Right column headlines "THE NEW SILHOUETTE" and "ARCHITECTURAL CHIC" in elegant italic serif. Warm aged paper texture, visible pencil sketch strokes in garment folds, premium editorial masterpiece.
```

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

### Multi-Character R2V Prompt Example

Source: https://help.scenario.com/articles/4698346156-happy-horse-by-alibaba-taotian-lab-the-essentials

This prompt example demonstrates a dramatic, high-stakes battle between two characters, detailing their actions, the environment, and the overall atmosphere. It highlights how to describe complex interactions and cinematic elements.

```text
character1 and character2 face off in a dramatic, high-stakes battle for survival, 
with character1 wielding a long range weapon as character2 charges and lashes out 
with sharp limbs, sparks flying and debris scattering as their movements clash, 
intense energy and determination in the air, distant thunder and the heavy sound of 
metal striking carapace echo around them, cinematic lighting highlighting sweat and 
tension on character1 while menacing growls and screeches from character2 fill the 
soundscape, fast camera moves to heighten the epic, life-or-death atmosphere.
```

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

### Text to Motion 3.0 - Reaction Example

Source: https://help.scenario.com/articles/6720109441-uthana-motion-the-essentials

Example for Text to Motion 3.0 generating a reaction motion. This snippet focuses on a character stumbling and recovering.

```text
prompt: stumbles backward, catches their balance, and shakes it off
length: 6
fps: 30
```

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

### Build Workflow Using Reference Images

Source: https://help.scenario.com/articles/6218410180-node-agent-the-essentials

Use this snippet to guide the agent in building a workflow that incorporates reference images. Specify how each image should be used, such as for character or style.

```text
Drop both images on the canvas. Use Image A as a character reference and Image B as a style reference. Build a workflow that produces new images in the same style, featuring the character in different poses.
```

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

### Example I2V Prompt Structure

Source: https://help.scenario.com/articles/4698346156-happy-horse-by-alibaba-taotian-lab-the-essentials

For image-to-video (I2V) mode, structure your prompt to describe the subject's actions, environmental responses, and atmosphere, building upon the provided first frame.

```text
[What the character or subject does], [how the environment responds], [atmosphere]
```

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

### MAI Image 2.5 Text-to-Image Prompt Example

Source: https://help.scenario.com/articles/8103274871-mai-image-2-5-photorealistic-generation-and-editing

Example prompt for a narrative still. Focus on the subject, setting, mood, and specific details to convey a quiet, intimate moment.

```text
Astronaut floating in the ISS cupola, both hands wrapped around a warm mug, eyes on a tablet clipped to the thigh—not looking at Earth. Blue planet fills the curved windows behind, soft rim light on suit fabric. Quiet documentary NASA authenticity, natural film grain, intimate narrative moment, no text.
```

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

### Riverflow Scoring Prompt Example

Source: https://help.scenario.com/articles/6956458231-riverflow-2-5-the-essentials

Use a free-form instruction to guide the model's candidate selection based on specific criteria. This example focuses on luxury beauty product imagery.

```text
scoringPrompt: "Score this image as a luxury beauty hero shot for a high-end
direct-to-consumer brand website. Reject any candidate with warped or
unreadable brand text, soft focus on the labels, or amateur lighting."
```

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

### Text to Motion 3.0 Example

Source: https://help.scenario.com/articles/6720109441-uthana-motion-the-essentials

Use this snippet to generate motion from a text description. Specify the prompt, desired length, frames per second, and output format. Optionally provide a character file for retargeting.

```text
prompt: performs a fluid capoeira sequence, ducking low then sweeping into a cartwheel kick
length: 8
fps: 30
rewritePrompt: true
characterFile: (optional GLB or FBX)
outputFormat: glb
```

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

### Audio Extract Pipeline Example

Source: https://help.scenario.com/articles/4344568406-audio-extract-the-essentials

This illustrates a common workflow on Scenario where video is first processed by Audio Extract, followed by other audio tools like Audio Cut and Speech to Text.

```text
Video asset
  → Audio Extract (full track, MP3 or WAV)
    → Audio Cut (trim to the line you need)
    → Speech to Text (subtitles or transcript)
    → ElevenLabs Voice Isolator (clean speech only, if the mix is noisy)
```

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

### Metal Plate Texture Prompt

Source: https://help.scenario.com/articles/2574453096-train-a-custom-texture-model

Example of a prompt for generating a polished metal plate texture.

```text
a polished metal plate with subtle scratches
```

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

### Example Agent Report

Source: https://help.scenario.com/articles/6218410180-node-agent-the-essentials

A typical report from a structured prompt detailing the nodes, their connections, and their functions within the agent's pipeline.

```text
Mecha + Character Pipeline is ready. It has 5 nodes wired end-to-end:

- Image A (Character Reference) and Image B (Style Reference): drop your two images here.
  Both feed into the LLM vision step, and Image B also feeds the image generator as a
  style reference.

- Vision Analysis & Prompt Generation (LLM): receives both images plus a detailed
  instruction prompt. It analyzes the character's appearance and the example's art style,
  then outputs a tailored image-generation prompt describing the character beside a
  matching mecha.

- Mecha + Character Image (Gemini image generator, 2:3 portrait, 2K): takes the
  LLM-generated prompt as its text input and Image B as a reference image, then generates
  the final illustration.

The LLM's intermediate text output is also visible on the canvas for inspection. Just
upload your two reference images and hit Run.
```

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

### Example T2V Prompt Structure

Source: https://help.scenario.com/articles/4698346156-happy-horse-by-alibaba-taotian-lab-the-essentials

Use this structure for text-to-video prompts. Describe the scene, environment, lighting, atmosphere, and visual style. Keep prompts concise and avoid camera instructions.

```text
[Subject + action], [environment], [lighting], [atmosphere], [visual style]
```

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

### Lyria 3 Image-to-Music Prompt Example

Source: https://help.scenario.com/articles/9763266293-google-lyria-the-essentials

Combine text prompts with reference image asset IDs to influence the generated music's mood, era, and atmosphere. The model analyzes visual content to infer sonic qualities. Images work best as mood references.

```text
prompt: "Orchestral, cinematic, slow build, 60 BPM"
images: ["asset_xxx"]
```

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

### Get All Tags

Source: https://help.scenario.com/articles/7782236276-tags

Retrieves a list of all available tags in the Scenario system.

```APIDOC
## Get All Tags

### Description
Retrieves a list of all tags.

### Method
GET

### Endpoint
/tags
```

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

### Video Generation with Start and End Frames

Source: https://help.scenario.com/articles/1727809780-luma-ray-3-2-the-essentials

Animate between a start and end frame by providing both `startFrame` and `endFrame` inputs. Duration is limited to 5 seconds when using anchor frames.

```text
prompt: "The lighting shifts from blue hour to full sunrise as the camera
slowly dollies forward across the bay"
startFrame: asset_xxx   // opening still
endFrame:   asset_yyy   // closing still
duration:   "5s"        // 10s not allowed with anchor frames
```

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

### Text-to-Video for Live Performance

Source: https://help.scenario.com/articles/4185158276-happy-horse-1-1-the-essentials

Generate dynamic performance scenes with crowd audio using a text prompt. This example focuses on a live music scenario with energetic visuals and native sound.

```text
prompt: A punk rock singer screams into a microphone on a packed stage, strobe lights, crowd surfing energy, raw live performance with native audio and crowd roar
duration: 14
resolution: 1080P
aspectRatio: 16:9
```

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

### Example Video Edit Prompt

Source: https://help.scenario.com/articles/4698346156-happy-horse-by-alibaba-taotian-lab-the-essentials

Use this prompt structure to describe the desired visual transformation for your video edit. Focus on the target world, key visual elements, lighting, color palette, and atmosphere.

```text
Remove the black background and add an industrial background with machines working 
to manufacture parts of the same robot.
```

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

### Rodin Gen-2.5 Fast Text Generation Configuration

Source: https://help.scenario.com/articles/6155258011-rodin-hyper3d-models-the-essentials

Example configuration for generating a 3D model from text using a Fast tier. Specifies the prompt, tier, mesh quality, and material.

```yaml
prompt: "A modular sci-fi crate with hex panels and orange status lights"
tier: "Gen-2.5-Low"
qualityMeshOption: "Auto"
material: "PBR"
```

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

### Scenario API Usage Response Structure

Source: https://help.scenario.com/articles/7658213402-scenario-analytics-api

Example JSON response from the Scenario API detailing usage totals, consumption by user, spend by model, and output volume by asset kind.

```json
{
  "totals": { "totalCU": 93910.5, "users": 4,
  "startDate": "2026-05-01", "endDate": "2026-05-31" },

  // CU per user (userId prefixed apiu_ = an API key, not a human)
  "consumption": [
    { "userId": "c452b444…", "value": 91944.5, "total": 91944.5 },
    { "userId": "apiu_x89E…", "value": 944, "total": 944 }
  ],

  // spend by model — sorted desc, with friendly names
  "modelUsages": [
    { "modelName": "Seedance 2.0", "totalCU": 32792, "totalJobs": 56, "totalApiKeyCU": 0 },
    { "modelName": "GPT Image 2", "totalCU": 19956, "totalJobs": 645, "totalApiKeyCU": 0 }
  ],

  // output volume by asset kind
  "assetUsages": [
    { "kind": "image", "total": 1388, "totalApiKey": 36 },
    { "kind": "video", "total": 544 }, { "kind": "3d", "total": 32 }
  ]
}
```

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

### Rodin Gen-2.5 Fast Image Generation Configuration

Source: https://help.scenario.com/articles/6155258011-rodin-hyper3d-models-the-essentials

Example configuration for generating a 3D model from an image using a Fast tier. Sets image input, tier, mesh quality, material, and enables Creative Mode.

```yaml
images: [asset_concept]
tier: "Gen-2.5-Extreme-Low"
qualityMeshOption: "Auto"           // → 20K Triangle on supported tiers
material: "All"
enableCreativeMode: true            // optional, Fast-only
```

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

### Riverflow Scoring Rubric Example

Source: https://help.scenario.com/articles/6956458231-riverflow-2-5-the-essentials

Employ a structured JSON list of dimensions with weights for detailed brand standard enforcement. This example defines criteria for clarity and thumbnail readability.

```json
scoringRubric: [
  {
    "key": "clarity",
    "label": "Clarity",
    "description": "How easy is the text to read? Letters are sharp and high-contrast against their background, with no blurring, warping, or overlapping characters.",
    "weight": 0.5,
    "passing_score": 7
  },
  {
    "key": "thumbnail",
    "label": "Thumbnail readability",
    "description": "How well does it hold up at small size? The main subject and any text stay recognizable at roughly 200x200 pixels.",
    "weight": 0.5
  }
]
```

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

### Effective vs. Less Effective Sound Prompt Examples

Source: https://help.scenario.com/articles/6777086009-kling-video-to-audio-the-essentials

Compares effective prompt writing techniques with less effective ones. Effective prompts are specific and descriptive, while less effective prompts are vague.

```text
// good
soundEffectPrompt:     "claws on concrete, low growl, fabric tear"
backgroundMusicPrompt: "minimal piano, three notes, 60 BPM, lots of space"

// less effective
soundEffectPrompt:     "scary monster sounds"
backgroundMusicPrompt: "build suspense"
```

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

### Basketball Uniform Prompt Example

Source: https://help.scenario.com/articles/6412500128-generate-highly-consistent-outfits

Use this prompt to generate a character wearing a specific basketball uniform. Adjust the character description while keeping uniform details consistent for varied outputs.

```text
A teenager girl wearing big glasses in holding a basketball, her basketball uniform features a vibrant green base with blue and white accents. The sleeveless jersey includes a "Flight Club" logo with wings and a basketball, along with the number 11 in bold white on the front. The matching shorts have horizontal white and blue stripes near the hem, completing the energetic and sporty look.
```

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

### JSON Response Structure for Asset Details

Source: https://help.scenario.com/articles/4345248040-how-to-retrieve-the-asset-url

This is an example of the JSON response you will receive when querying the asset endpoint. It contains the direct 'url' to the asset.

```json
{
  "asset": {
    "id": "asset_1gHMbHjSjWYLyAnd7ZxzPkcQ",
    "url": "https://cdn.scenario.com/assets/asset_1gHMbHjSjWYLyAnd7ZxzPkcQ.png",
    "type": "image",
    "createdAt": "2024-03-20T10:00:00Z",
    "metadata": {
      "prompt": "A futuristic city..."
    }
  }
}
  
```

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

### Python Universal Generation Workflow

Source: https://help.scenario.com/articles/3896230951-quick-start-universal-generation-video-audio-3d-image

This script demonstrates how to trigger and poll for generation jobs using the Scenario API. It includes configuration for API keys, authentication, and a reusable function for handling generation requests across different modalities. Ensure you have the 'requests' library installed.

```python
import requests
import time
import base64

# --- CONFIGURATION ---
API_KEY = "YOUR_API_KEY"
API_SECRET = "YOUR_API_SECRET"
BASE_URL = "https://api.cloud.scenario.com/v1"

# Basic Auth Header
auth_str = f"{API_KEY}:{API_SECRET}"
b64_auth = base64.b64encode(auth_str.encode()).decode()
headers = {
    "Authorization": f"Basic {b64_auth}",
    "Content-Type": "application/json"
}

def run_generation(model_id, payload):
    """
    Generic function to trigger generation and poll for the result.
    """
    url = f"{BASE_URL}/generate/custom/{model_id}"
    
    print(f"\n--- Starting Generation: {model_id} ---")
    
    # 1. Start the Job
    try:
        response = requests.post(url, headers=headers, json=payload)
        response.raise_for_status()
        job_data = response.json()
        job_id = job_data['job']['jobId']
        print(f"Job Initiated. ID: {job_id}")
    except requests.exceptions.RequestException as e:
        print(f"Error starting job: {e}")
        if response.text: print(response.text)
        return

    # 2. Poll for Completion
    poll_url = f"{BASE_URL}/jobs/{job_id}"
    while True:
        resp = requests.get(poll_url, headers=headers)
        status_data = resp.json()
        status = status_data['job']['status']
        
        if status == 'success':
            # Result is usually a list of assetIds or a direct URL depending on model
            result = status_data['job'].get('result', {})
            metadata = status_data['job'].get('metadata', {})
            
            # Try to grab the Asset ID or URL
            asset_ids = metadata.get('assetIds', [])
            print(f"SUCCESS! Assets created: {asset_ids}")
            print(f"Full Result: {result}")
            break
        elif status in ['failed', 'cancelled']:
            print(f"Job Failed: {status_data['job'].get('error')}")
            break
            
        print(".", end="", flush=True)
        time.sleep(3) # Wait 3 seconds before next check

# ==========================================
# UNCOMMENT A BLOCK BELOW TO TEST A MODALITY
# ==========================================

# --- 1. VIDEO GENERATION ---
# Model: Kling v2.6 T2V Pro
# Docs: https://docs.scenario.com/docs/video-generation
# video_model = "model_kling-v2-6-t2v-pro"
# video_payload = {
#     "prompt": "A cinematic drone shot of a futuristic city at sunset, highly detailed",
#     "aspectRatio": "16:9",
#     "duration": 5
# }
# run_generation(video_model, video_payload)


# --- 2. AUDIO GENERATION (Music) ---
# Model: Google Lyria 2
# Docs: https://docs.scenario.com/docs/audio-generation
# audio_model = "model_lyria-2"
# audio_payload = {
#     "prompt": "Futuristic country music, steel guitar, huge 808s, synth wave elements space western cosmic twang soaring vocals",
# }
# run_generation(audio_model, audio_payload)


# --- 3. 3D GENERATION (Text-to-3D) ---
# Model: Meshy Text to 3D
# Docs: https://docs.scenario.com/docs/3d-model-generation
# threed_model = "model_meshy-txt23d" 
# threed_payload = {
#     "prompt": "A low-poly treasure chest with gold coins"
# }
# run_generation(threed_model, threed_payload)


# --- 4. THIRD-PARTY IMAGE GENERATION ---
# Model: Imagen 4 Ultra
# Docs: https://docs.scenario.com/docs/third-party-model-generation
# image_model = "model_imagen4-ultra"
# image_payload = {
#     "prompt": "A photorealistic portrait of an astronaut in a garden",
#     "aspectRatio": "4:3"
# }
# run_generation(image_model, image_payload)

```

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

### Get All Collections

Source: https://help.scenario.com/articles/9230394463-collections

Retrieves a list of all collections available in the Scenario API.

```APIDOC
## GET /collections

### Description
Retrieves a list of all collections.

### Method
GET

### Endpoint
/collections
```

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

### Military Uniform Prompt Example

Source: https://help.scenario.com/articles/6412500128-generate-highly-consistent-outfits

This prompt is designed to generate a character in a detailed military uniform. The 'Style Reference' mode can influence not only the outfit but also the character's pose and proportions.

```text
A Black female soldier with glowing purple eyes and curly hair, striking a victory pose, wearing a uniform that features a dark, tailored military coat with silver buttons, shoulder epaulettes, and decorative chest stripes. Black gloves, knee-high boots with silver armor plating, and tactical pouches add a modern combat edge. Sharp creases and metallic details give it a high-ranking, ceremonial look.
```

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

### Retrieve Specific Model Details

Source: https://help.scenario.com/articles/4632354614-generating-from-your-custom-trained-models-via-api

Get detailed information and status for a particular custom model using its unique model ID.

```bash
GET /v1/models/{modelId}
```

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

### Match Reframe Prompt to Source Environment

Source: https://help.scenario.com/articles/1727809780-luma-ray-3-2-the-essentials

Ensure the Reframe prompt accurately describes the source scene to achieve quality results. For example, 'Extend the rooftop bar to the left, keeping the same neon signage and night sky' is more effective than a generic prompt.

```json
{
  "operation": "reframe",
  "source": "path/to/source.mp4",
  "aspectRatio": "21:9",
  "prompt": "Extend the rooftop bar to the left, keeping the same neon signage and night sky"
}
```

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

### Submit Custom Model Generation Request

Source: https://help.scenario.com/articles/4632354614-generating-from-your-custom-trained-models-via-api

Use this endpoint to start an image generation job with your custom model. Replace {modelId} with your model's ID. Authentication is handled via HTTP Basic Auth with your API Key and Secret. The request requires a prompt and aspectRatio.

```bash
curl -X POST "https://api.cloud.scenario.com/v1/generate/custom/model_YOUR_MODEL_ID"
-u "YOUR_API_KEY:YOUR_API_SECRET"
-H "Content-Type: application/json"
-d '{
"prompt": "a warrior character in a forest, cinematic lighting",
"aspectRatio": "1:1"
}'
```

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

### Large Format Output Upscaling Strategy

Source: https://help.scenario.com/articles/9102417820-clarity-pro-upscaler-the-essentials

For large prints, use sequential 2x upscales. Start with creativity 0 for the first pass, then a slightly higher value (e.g., 1) for the second pass.

```text
Pass 1 — Scale Factor: 2, Creativity: 0
Pass 2 — Scale Factor: 2, Creativity: 1
```

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

### T2V Prompt Causing Errors Example

Source: https://help.scenario.com/articles/4698346156-happy-horse-by-alibaba-taotian-lab-the-essentials

Avoid prompts that include explicit camera directions or are excessively long, as they can lead to processing errors. Focus on describing the scene instead.

```text
A breathtaking multi-story luxury treehouse spiraling around an ancient
giant redwood, circular glass balconies wrapped in lush ferns and tropical
plants, warm golden interior lights glowing through floor-to-ceiling windows,
a slow cinematic drone shot begins at ground level in misty forest and rises
steadily upward along the trunk, revealing each level one by one...
```

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

### Example Test Prompts for Character Models

Source: https://help.scenario.com/articles/4280773511-train-a-consistent-character-model

Utilize all four test prompt slots to cover different aspects of character identity, including baseline pose, novel poses, new environments, and varied framing or art direction.

```text
Vendalixia, standing, neutral expression
```

```text
Vendalixia running
```

```text
Vendalixia on a beach at sunset
```

```text
close-up portrait of Vendalixia, anime style
```

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

### Ray 3.2 Reframe: Aspect Ratio Conversion Example

Source: https://help.scenario.com/articles/1727809780-luma-ray-3-2-the-essentials

Use this snippet to reframe an existing video to a new aspect ratio. Provide a prompt to describe how the new canvas area should be filled. The source video and target aspect ratio are required.

```json
prompt: "Extend the kitchen scene to the left and right, keeping the same
warm tungsten lighting, copper cookware on the back wall, and a window
with afternoon light spilling in."
video:        asset_source_clip   // a 16:9 source, for example
aspectRatio:  "9:16"              // target ratio
resolution:   "1080p"
```

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

### Basic Video Generation with Prompt

Source: https://help.scenario.com/articles/1727809780-luma-ray-3-2-the-essentials

Use a simple prompt to generate a video. Defaults for duration, resolution, and aspect ratio are applied.

```text
prompt: "A lone surfer paddles toward a glassy point break at golden hour,
slow handheld camera, warm volumetric light, cinematic 35mm look"
// duration: "5s", resolution: "720p", aspectRatio: "16:9" defaults
```

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

### Generate Product Packshot with Scenario

Source: https://help.scenario.com/articles/2664328768-getting-started-with-the-scenario-mcp-server

Use plain language to instruct the agent to generate a product packshot. Specify the item, background, aspect ratio, model, and request a cost estimate.

```plaintext
Using Scenario, generate a product packshot of a ceramic mug on a warm background. Square. Pick a strong model and show me the result with the cost.
```

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

### Using Sound Effect and Background Music Prompts

Source: https://help.scenario.com/articles/6777086009-kling-video-to-audio-the-essentials

Demonstrates how to use both sound effect and background music prompts to layer distinct audio elements. The prompts are combined to create a mixed audio track.

```text
soundEffectPrompt:     "footsteps on gravel, distant crows, wind in dry grass"
backgroundMusicPrompt: "tense cinematic strings with a low drone, slow build"
```

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

### Lyria 3 Pro Prompt with Structure Tags

Source: https://help.scenario.com/articles/9763266293-google-lyria-the-essentials

Use structure tags within your prompt to guide Lyria 3 Pro in arranging the song into distinct sections. This helps in producing a more composed and intentional output.

```text
Indie folk, acoustic guitar and warm vocal harmonies, 90 BPM, key of G major, bittersweet mood.
[Intro] Gentle fingerpicking sets the scene.
[Verse] Soft lead vocal over sparse guitar.
[Chorus] Full harmony vocals with strummed chords and light percussion.
[Bridge] Stripped back to just guitar and a single voice.
[Outro] Fade on the chorus melody.
```

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

### Project Instructions Template

Source: https://help.scenario.com/articles/9101671137-node-agent-memory

Adapt this template for project-specific instructions, including art direction, model usage, and prompt style. This ensures the AI assistant understands the unique requirements of each project.

```text
Project: "Aurora", a stylized fantasy mobile RPG.
Art direction: painterly, warm rim light, cool blue-violet shadows.
Characters: generate with our trained "Aurora Characters" model, then run Character Turnaround for 4-view sheets.
Stills: GPT Image 2; dusk lighting; 3:4 for character art, 16:9 for environments.
Edits: GPT Image 2 with a mask so the character and style stay intact.
Video: animate hero shots with Seedance 2.0 from a clean first frame.
Textures: a Realistic Textures LoRA for seamless ground and walls.
Prompt style: detailed and comma-separated, with lighting, lens, and mood. Avoid text in image and watermarks.
```

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

### Get Collection By ID

Source: https://help.scenario.com/articles/9230394463-collections

Retrieves a specific collection by its unique identifier.

```APIDOC
## GET /collections/{collectionId}

### Description
Retrieves a specific collection by its ID.

### Method
GET

### Endpoint
/collections/{collectionId}

### Parameters
#### Path Parameters
- **collectionId** (string) - Required - The unique identifier of the collection.
```

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

### Call Scenario API with Basic Auth

Source: https://help.scenario.com/articles/7658213402-scenario-analytics-api

Use curl with Basic Authentication to retrieve usage data for a specific date range. The API key and secret are passed as username and password.

```bash
# Org usage for May 2026 (Basic auth: key:secret)

curl -u "$SCENARIO_KEY:$SCENARIO_SECRET" \
"https://api.cloud.scenario.com/v1/usages?startDate=2026-05-01&endDate=2026-05-31"
```

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

### Retrieve Specific Model Details

Source: https://help.scenario.com/articles/4632354614-generating-from-your-custom-trained-models-via-api

Get detailed information and status for a specific custom-trained model.

```APIDOC
## GET /v1/models/{modelId}

### Description
Retrieves details and status for a specific model.

### Method
GET

### Endpoint
/v1/models/{modelId}

### Parameters
#### Path Parameters
- **modelId** (string) - Required - The unique identifier of the model.
```

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

### Get Third-Party Models

Source: https://help.scenario.com/articles/7872808247-managing-filtering-models-with-the-scenario-api

Filter public models to retrieve models from the broader community or partners using the 'sc:third-party' tag.

```curl
curl -X GET "https://api.cloud.scenario.com/v1/models/public?tags=sc:third-party" \
  -H "Authorization: Basic <YOUR_BASE64_CREDENTIALS>" \
  -H "Accept: application/json"
```

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

### Basic Texture Prompt

Source: https://help.scenario.com/articles/2574453096-train-a-custom-texture-model

Use a direct prompt to generate a texture with your custom model.

```text
a rugged stone wall
```

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

### Using Interjections in Speech

Source: https://help.scenario.com/articles/9232650555-minimax-speech-the-essentials

Incorporate parenthetical interjections for natural-sounding non-verbal sounds within speech. Examples include laughs, sighs, and gasps.

```text
"I can't believe it worked. (laughs) We actually did it."
"The results were... (gasps) I had no idea it would go this far."
```

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

### Create Seamless Background Loops at 5 Seconds

Source: https://help.scenario.com/articles/1727809780-luma-ray-3-2-the-essentials

Generate seamless background loops for landing pages or retail screens. Set `loop: true` and a duration of 5 seconds, as seamless loops are not available at 10 seconds.

```json
{
  "operation": "generate",
  "model": "ray3.2",
  "prompt": "Abstract flowing colors, calming atmosphere",
  "duration": 5,
  "loop": true
}
```

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

### Kling Video to Audio with ASMR Mode Enabled

Source: https://help.scenario.com/articles/6777086009-kling-video-to-audio-the-essentials

Shows how to enable ASMR mode for detailed audio generation, typically used for close-ups of materials, fabric, or food. Requires a video asset and specific sound effect prompts.

```text
video:                 asset_macro_perfume_pour
soundEffectPrompt:     "glass on marble, liquid pour, soft droplets"
asmrMode:              true
```

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

### Portrait Upscaling Settings

Source: https://help.scenario.com/articles/9102417820-clarity-pro-upscaler-the-essentials

For portraits, keep creativity at 0 or negative to prevent hallucinated details. Start with -3 for a clean 2x upscale.

```text
Image: portrait photograph
Scale Factor: 2
Creativity: -3
```

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

### Prompt for Product Cutout Pipeline with Conditional Upscale

Source: https://help.scenario.com/articles/6218410180-node-agent-the-essentials

Use this prompt for a product photo pipeline that includes background removal and an adaptive upscale pass for smaller images.

```text
"Take a product photo, run background removal, and output a transparent PNG. Add an
If/Else node so that images smaller than 1024px get an extra upscale pass to 4K before
background removal."
```

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

### Prompt for Transforming the Environment

Source: https://help.scenario.com/articles/3017545134-reve-v2-1-the-essentials

Change the environmental setting of a scene, for example, from a tropical to an arctic landscape. Specify the elements to transform, such as water, shore, and lighting.

```plaintext
Keep the same aerial composition and lagoon shape, but transform the tropical scene into a frozen arctic lagoon: turquoise water becomes icy blue, the shore becomes snow and glaciers, floating icebergs, cold pale light.
```

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

### Get Official Scenario Models

Source: https://help.scenario.com/articles/7872808247-managing-filtering-models-with-the-scenario-api

Filter public models to retrieve only the curated list of official Scenario models using the 'sc:scenario' tag.

```curl
curl -X GET "https://api.cloud.scenario.com/v1/models/public?tags=sc:scenario" \
  -H "Authorization: Basic <YOUR_BASE64_CREDENTIALS>" \
  -H "Accept: application/json"
```

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

### Texture Prompt with Seamless Keywords

Source: https://help.scenario.com/articles/2574453096-train-a-custom-texture-model

Add keywords like 'seamless tileable texture' and 'no visible seams' to reinforce desired behavior if seams appear or the style is not coming through.

```text
a rugged stone wall, seamless tileable texture, no visible seams
```

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

### Get Asset URL

Source: https://help.scenario.com/articles/4345248040-how-to-retrieve-the-asset-url

This endpoint retrieves the direct URL for a specific asset using its asset ID. It requires authentication with your API key and secret.

```APIDOC
## GET /v1/assets/{assetId}

### Description
Retrieves the direct URL for a specific asset.

### Method
GET

### Endpoint
`https://api.cloud.scenario.com/v1/assets/{assetId}`

### Parameters
#### Path Parameters
- **assetId** (string) - Required - The unique identifier of the asset.

### Request Example
(No request body for GET requests)

### Response
#### Success Response (200)
- **asset** (object) - Contains asset details.
  - **id** (string) - The asset ID.
  - **url** (string) - The direct URL to the asset.
  - **type** (string) - The type of the asset (e.g., 'image').
  - **createdAt** (string) - The timestamp when the asset was created.
  - **metadata** (object) - Additional metadata about the asset.

#### Response Example
```json
{
  "asset": {
    "id": "asset_1gHMbHjSjWYLyAnd7ZxzPkcQ",
    "url": "https://cdn.scenario.com/assets/asset_1gHMbHjSjWYLyAnd7ZxzPkcQ.png",
    "type": "image",
    "createdAt": "2024-03-20T10:00:00Z",
    "metadata": {
      "prompt": "A futuristic city..."
    }
  }
}
```
```

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

### Build Workflow from Text Description

Source: https://help.scenario.com/articles/6218410180-node-agent-the-essentials

Use this snippet to instruct the agent to create a new workflow based on a detailed text description. Specify inputs, transformations, and output format.

```text
Build a workflow that takes a product photo as input, removes the background, upscales the result to 4K, and outputs a transparent PNG ready for an e-commerce listing.
```

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

### Video Generation with Looping and HDR

Source: https://help.scenario.com/articles/1727809780-luma-ray-3-2-the-essentials

Enable seamless looping with `loop: true` or richer contrast with `hdr: true` at 720p or 1080p. Both flags are mutually exclusive with 10-second durations.

```text
prompt: "A seamless loop of a gentle stream flowing through a forest"
loop: true
resolution: "720p"
```

```text
prompt: "A futuristic cityscape at night with neon lights"
hdr: true
resolution: "1080p"
```

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

### Example Character Caption

Source: https://help.scenario.com/articles/4280773511-train-a-consistent-character-model

A well-formed character caption includes a trigger word, defining physical traits, variable elements like pose and environment, and optional art-style notes.

```text
Vendalixia, a young woman with silver hair and a red scarf, three-quarter view, smiling, standing in a forest at dusk, soft warm light
```

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

### Construct Song with Advanced v2 Sections

Source: https://help.scenario.com/articles/2555204997-elevenlabs-music-v2-the-essentials

Build a 60-second acoustic-pop song using ElevenLabs Music Advanced v2 by defining an ordered list of sections, including intro, verse, chorus, and outro. Each section can have specific text, duration, styles, and context adherence.

```json
sections:
  - text: "[Intro] {soft solo piano, sparse, rubato}"
    durationSeconds: 8
    positiveStyles: ["acoustic pop", "warm", "fingerpicked guitar"]
    negativeStyles: ["drums", "vocals"]
    contextAdherence: "high"
  - text: "[Verse] Morning light spills through the open door, I'm chasing dreams I've never had before"
    durationSeconds: 20
    positiveStyles: ["acoustic pop", "gentle female vocals", "singer-songwriter"]
    contextAdherence: "high"
  - text: "[Chorus] So I'll run, run, run toward the rising sun, this is just the start of something we've begun"
    durationSeconds: 20
    positiveStyles: ["uplifting", "catchy", "full band", "vocal harmonies"]
    contextAdherence: "high"
  - text: "[Outro] {soft fade with gentle humming}"
    durationSeconds: 12
    positiveStyles: ["gentle", "acoustic", "warm"]
    contextAdherence: "medium"
```

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

### Configure Scenario MCP Server for Cursor and VS Code

Source: https://help.scenario.com/articles/2664328768-getting-started-with-the-scenario-mcp-server

Add the Scenario MCP server URL to your MCP configuration for Cursor and VS Code.

```json
{
  "mcpServers": {
    "scenario": { "url": "https://mcp.scenario.com/mcp" }
  }
}
```

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

### Text-to-Video with Native Audio Prompt

Source: https://help.scenario.com/articles/4185158276-happy-horse-1-1-the-essentials

Use this prompt for generating scenes, action, or talking heads from text descriptions. Include visual details, camera movements, dialogue, and sound. Specify lip-sync for spoken dialogue.

```text
prompt: A professional news anchor at a studio desk speaks directly to camera with clear lip-sync, saying welcome to tonight's briefing, subtle camera push-in, broadcast lighting, confident delivery with native studio ambience
duration: 12
resolution: 1080P
aspectRatio: 16:9
```

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

### Configure Scenario MCP Server with mcp-remote

Source: https://help.scenario.com/articles/2664328768-getting-started-with-the-scenario-mcp-server

Configure the Scenario MCP server using mcp-remote for clients like Claude Desktop, Windsurf, Zed, and Warp.

```json
{
  "mcpServers": {
    "scenario": {
      "command": "npx",
      "args": ["-y", "mcp-remote@latest", "https://mcp.scenario.com/mcp"]
    }
  }
}
```

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

### Fetch Usage Data with Python

Source: https://help.scenario.com/articles/7658213402-scenario-analytics-api

Use this Python snippet to retrieve monthly usage data from the Scenario API. It requires environment variables for API key and secret. The output includes total Compute Units (CU) and CU per model for the top 5 models.

```python
import os, requests

r = requests.get(
  "https://api.cloud.scenario.com/v1/usages",
  params={"startDate": "2026-05-01",
  "endDate": "2026-05-31"},
  auth=(os.environ["SC_KEY"],
  os.environ["SC_SECRET"]),
)

data = r.json()
print(data["totals"]["totalCU"])
for m in data["modelUsages"][:5]:
  print(m["modelName"], m["totalCU"])
```

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

### Using Audio Tags in Gemini TTS

Source: https://help.scenario.com/articles/5604258483-gemini-tts-the-essentials

Audio tags, enclosed in square brackets, control speech delivery like emotion, pacing, and performance notes. Place them at the start of a sentence for consistent application.

```text
[determination] We are not leaving without the artifact.
[whispers] The vault door was already open.
[enthusiasm] This is going to change everything.
[slow] Read each step carefully before you begin.
[laughs] I cannot believe that actually worked.
[soft] The people using the tools. That always brings it back to earth.
```

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

### Organization Instructions Template

Source: https://help.scenario.com/articles/9101671137-node-agent-memory

Use this template to define organization-wide guidelines for AI model usage, brand voice, and content creation rules. Keep each rule on a new line.

```text
Brand voice: concise, professional, plain language. No hype.
Stills: GPT Image 2. In-image text (logos, UI, banners): Ideogram V4.
Edits: GPT Image 2 with a mask, or Nano Banana for conversational changes.
Video: Seedance 2.0, or Grok Imagine Video 1.5 when you want speed and audio.
Lip-sync: Veed Fabric with your own audio. 3D: Rodin Gen-2.5.
Aspect ratios: 16:9 for hero and marketing, 1:1 for icons, unless a project overrides it.
People: never depict real, identifiable people without sign-off from the project lead.
```

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

### Marker-Based Editing with Instructions

Source: https://help.scenario.com/articles/4017270637-seedream-models-the-essentials

For Seedream 5.0 Pro, use markings on a reference image to direct local edits. Specify changes within marked areas and request removal of markings in the final output. Match scene lighting for seamless integration.

```text
In the area marked with the red circle, replace the vending machine with a retro arcade cabinet. Its glowing marquee reads 'STARFALL' and its screen shows a colorful space shooter in attract mode. Keep everything else in the scene exactly the same. Remove the red circle and arrow markings from the final image. Match the station's cool fluorescent lighting.
```

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

### Generate Instrumental Music with ElevenLabs

Source: https://help.scenario.com/articles/6780010880-elevenlabs-music-the-essentials

Use a text prompt, duration, and forceInstrumental flag to generate instrumental audio. Specify output format for desired quality.

```text
Prompt example (instrumental):
"Retro 80s synthwave with pulsing arpeggios, gated reverb drums, neon-soaked atmosphere"
musicLengthMs: 45000
forceInstrumental: true
outputFormat: "mp3_44100_192"
```

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

### Apply Exact Color and Finish to Marked Area

Source: https://help.scenario.com/articles/4017270637-seedream-models-the-essentials

Use sketches or exact values like hex codes to guide edits in marked regions. The model can apply specified colors and finishes while preserving the original structure, stitching, and reflections.

```text
One sneaker, matched to three exact hex codes: #3E4A2E, #DB973E, #1F3A5F
```

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

### Foreground vs Background with Video to Layers

Source: https://help.scenario.com/articles/8235214611-image-to-layers-and-video-to-layers-the-essentials

Use this instruction to split a video's main subject from the background. Set Max Layers to 1 for a simple foreground/background split.

```text
Separation Instruction: Split the dancer from the background scenery.
Max Layers: 1
```

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

### Personal Instructions Template

Source: https://help.scenario.com/articles/9101671137-node-agent-memory

Paste this template into your User Settings to define your default preferences for image generation, editing, and prompt writing.

```plaintext
Default to GPT Image 2 and give me 4 variations, and tell me the model and ratio you used.
When I share a reference image, match its composition and lighting.
Edits: GPT Image 2 with a mask, keep my character and style fixed.
Video: Seedance 2.0, and Veed Fabric when I need lip-sync to my own audio.
Write prompts as short, comma-separated phrases.
```

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

### Editing with Keyframes

Source: https://help.scenario.com/articles/1727809780-luma-ray-3-2-the-essentials

Provide up to 64 `keyframes` with explicit frame indexes for multi-anchor control during editing. This is mutually exclusive with using a single `startFrame`.

```text
prompt: "Restyle the animation sequence, ensuring specific poses at key moments."
video: asset_source_clip
keyframes: [
  { frame: 0, prompt: "Character enters frame"
  }, { frame: 50, prompt: "Character strikes a dynamic pose"
  }, { frame: 100, prompt: "Character exits frame"
}]
editStrength: "reimagine_2"
```

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

### Video to Motion 2.1 Input Parameters

Source: https://help.scenario.com/articles/6720109441-uthana-motion-the-essentials

Use this snippet for Uthana Video to Motion 2.1. Upload a video of the motion and specify FPS and character file for retargeting. Set animationOnly to true if only motion data is needed.

```text
video: (required: full body, one person, fixed camera, textured or grid floor, background a different tone than the floor)
fps: 30
characterFile: (optional GLB or FBX)
animationOnly: false
outputFormat: glb
```

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

### Generate Image with Detailed Prompt

Source: https://help.scenario.com/articles/4017270637-seedream-models-the-essentials

Use a detailed prompt to describe the scene, style, and any text to be rendered exactly. Style directions should be outside quotes. Set output size and optionally enable sequence generation for related images.

```text
A key art poster for an indie deep-sea survival game. A lone diver in a battered brass helmet stands on the spine of a sunken whale, looking up at a distant surface glow. Bioluminescent jellyfish drift around her. Cold teal and amber palette, painterly digital illustration. At the top in a tall weathered serif, the title 'ABYSSAL'. Along the bottom in small clean sans caps, the tagline 'THE PRESSURE REMEMBERS'.
```

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

### Rodin Gen-2.5 Text to 3D Configuration

Source: https://help.scenario.com/articles/6155258011-rodin-hyper3d-models-the-essentials

Configure Rodin Gen-2.5 for text-to-3D generation. Uses a text prompt to drive 3D model creation with specified quality and material settings.

```yaml
prompt: "A stylized low-poly fantasy potion bottle with a glowing teal liquid
and an ornate cork wrapped in twine."
tier: "Gen-2.5-Medium"
qualityMeshOption: "18K Quad"          // default for the text variant
material: "All"
```

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

### Restyling Existing Footage with Prompt and Strength

Source: https://help.scenario.com/articles/1727809780-luma-ray-3-2-the-essentials

Change the visual style of existing footage using a prompt and an `editStrength` preset. The `video` input is required.

```text
prompt: "Restyle the shot as a vintage 16mm film with warm tungsten lighting,
heavy grain, and a 1970s color palette. Preserve the actor's blocking and
camera motion."
video: asset_source_clip
editStrength: "flex_2"
resolution: "1080p"
```

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

### Generate Lyrics Automatically (MiniMax 2.6)

Source: https://help.scenario.com/articles/1574698333-minimax-music-the-essentials

Set `lyricsOptimizer: true` with an empty `lyrics` field to have the model generate lyrics from the style prompt. The generated lyrics will follow the genre and mood described in `prompt` and include appropriate structure tags. Do not set both `lyricsOptimizer: true` and `isInstrumental: true` simultaneously.

```yaml
prompt: "Upbeat pop, 120 BPM, major key, summer anthem about chasing dreams"
lyrics: ""
lyricsOptimizer: true
```