Ltx 2.3 Quality

curl -X POST https://superpowers.tools/v1/run \
  -H 'Authorization: Bearer $SP_KEY' \
  -d '{"tool":"fal.ltx-2.3-quality-inpaint-lora","input":{"mask_video_url":"","prompt":"","video_url":"","loras":["marketing digital"]},"idempotency_key":"example-request-1"}'

{
  "type": "object",
  "required": [
    "loras",
    "prompt",
    "video_url",
    "mask_video_url"
  ],
  "properties": {
    "sync_mode": {
      "type": "boolean",
      "description": "If True, the media is returned as a data URI inline in the response. Useful for short-lived requests and tests.",
      "default": false
    },
    "num_frames": {
      "type": "integer",
      "description": "The number of frames to generate.",
      "default": 121
    },
    "num_inference_steps": {
      "type": "integer",
      "description": "Number of inference steps. Defaults to 15 and can be increased up to 30.",
      "default": 15
    },
    "negative_prompt": {
      "type": "string",
      "description": "The negative prompt to steer generation away from.",
      "default": "color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards"
    },
    "enable_prompt_expansion": {
      "type": "boolean",
      "description": "Whether to enable prompt expansion.",
      "default": true
    },
    "seed": {
      "type": "integer",
      "description": "Random seed for reproducibility. If None, a random seed is chosen."
    },
    "mask_video_url": {
      "type": "string",
      "description": "The mask video. White regions are regenerated; black regions are preserved from the source video."
    },
    "video_strength": {
      "type": "number",
      "description": "Strength of the IC-LoRA video guide for the preserved content. Higher values keep the source video structure more strongly.",
      "default": 1
    },
    "prompt": {
      "type": "string",
      "description": "The prompt describing what to generate inside the masked area."
    },
    "enable_safety_checker": {
      "type": "boolean",
      "description": "Whether to enable the safety checker.",
      "default": true
    },
    "generate_audio": {
      "type": "boolean",
      "description": "Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.",
      "default": true
    },
    "video_write_mode": {
      "type": "string",
      "description": "The write mode of the generated video.",
      "default": "balanced",
      "enum": [
        "fast",
        "balanced",
        "small"
      ]
    },
    "guidance_scale": {
      "type": "number",
      "description": "Classifier-free guidance scale. The default is tuned for fast, high-quality generation.",
      "default": 1
    },
    "video_quality": {
      "type": "string",
      "description": "The quality preset of the generated video.",
      "default": "high",
      "enum": [
        "low",
        "medium",
        "high",
        "maximum"
      ]
    },
    "video_url": {
      "type": "string",
      "description": "The source video to inpaint."
    },
    "loras": {
      "type": "array",
      "description": "Up to 3 LoRAs to apply on top of LTX-2.3. Each path is downloaded through the registry SSRF-safe downloader before it is loaded. Max size: 3 GB per LoRA."
    },
    "frames_per_second": {
      "type": "number",
      "description": "Frames per second of the generated video.",
      "default": 24
    }
  }
}