kling-v3.0-std

Kling Video v3.0 Standard

Generate smooth video with synchronized audio through Frevana's OpenRouter video endpoint using kwaivgi/kling-v3.0-std.

Model Characteristics

• Model ID: kwaivgi/kling-v3.0-std
• Resolution: 720p (fixed)
• Aspect Ratios: 16:9 (default), 9:16, 1:1
• Durations: 3 to 15 seconds (default: 5)
• Frame Control: Supports both first_frame and last_frame (image-to-video)
• Input References: Reference images (image_url); audio and video references are unsupported
• Audio: Synchronized audio generation supported (default: enabled)
• Seed: Deterministic seed is not supported by this model
• Passthrough Controls: negative_prompt, cfg_scale

Prerequisites & Authentication

• FREVANA_TOKEN (or --token) or FREVANA_API_KEY (or --api-key) in the environment
• Optional FREVANA_AGENT_APP_INSTANCE_ID (or --agent-app-instance-id) sent as x-frevana-agent-app-instance-id
• curl, bash, and python3

Invocation

# Text-to-video: submit and wait for video completion
bash skills/kling-v3.0-std/scripts/generate_video.sh \
  --prompt "A cyberpunk sports car drifting through neon rain-slicked streets at night" \
  --duration 5 \
  --aspect-ratio 16:9 \
  --download-dir ./output

# Image-to-video with first frame
bash skills/kling-v3.0-std/scripts/generate_video.sh \
  --prompt "The camera pushes forward as smoke curls into the air" \
  --first-frame ./scene.jpg \
  --duration 5 \
  --download-dir ./output

# Status check
bash skills/kling-v3.0-std/scripts/generate_video.sh status --job-id <JOB_ID>

Allowed Options

• -p, --prompt TEXT: Text description of the video (required for create)
• --prompt-file PATH: Path to file containing prompt
• --model MODEL: Model slug (default: kwaivgi/kling-v3.0-std)
• --duration SEC: Duration in seconds (3-15, default: 5)
• --aspect-ratio RATIO: 16:9, 9:16, 1:1 (default: 16:9)
• --resolution RES: 720p (default: 720p)
• --size WIDTHxHEIGHT: Exact output dimensions; overrides --resolution and --aspect-ratio
• --first-frame, --image PATH/URL: Image path or URL for first frame
• --last-frame PATH/URL: Image path or URL for last frame
• --reference-image PATH/URL: Add a reference image; repeat for multiple images
• --reference-audio URL: Unsupported by this model
• --reference-video URL: Unsupported by this model
• --audio: Generate synchronized audio (default: true)
• --no-audio: Disable audio generation
• --negative-prompt TEXT: Negative prompt (e.g. "blurry, distorted, low quality")
• --cfg-scale NUM: CFG guidance scale (e.g. 0.5)
• --wait: Wait for job completion and download/output (default in CLI)
• --no-wait: Submit job and return immediately with Job ID
• --poll-interval SEC: Seconds between status checks (default: 10)
• --max-wait SEC: Maximum seconds to wait before timeout (default: 600)
• --download-dir DIR: Directory to download completed MP4 video
• -o, --output FILE: Path to save output JSON or MP4 file
• -t, --text-only: Output only the video URL or downloaded file path
• --dry-run: Print request payload JSON and exit without network calls
• --token TOKEN: Frevana Bearer token override
• --api-key KEY: Frevana API key override
• --agent-app-instance-id ID: Agent App instance ID override

Guardrails

• For semantic requests such as "720p landscape" or "square video", use --resolution with --aspect-ratio.
• Use --size only when the user explicitly requires exact WIDTHxHEIGHT pixels; it overrides and replaces both semantic dimension fields in the request payload.
• Validate that --duration is between 3 and 15 seconds.
• Validate that --resolution is 720p.
• Validate that --aspect-ratio is one of 16:9, 9:16, or 1:1.
• --size is format-checked locally but not matched against a static model allowlist; model/provider compatibility is validated by the API.
• Do not pass --seed; Kling Standard does not support deterministic seed.
• Frame images and input references may be sent together; OpenRouter gives frameImages precedence and treats the request as image-to-video.