LTX-2.3 22B

curl -X POST https://superpowers.tools/v1/run \
  -H 'Authorization: Bearer $SP_KEY' \
  -d '{"tool":"fal.ltx-2.3-22b-audio-to-video-lora","input":{"loras":["marketing digital"],"audio_url":"","prompt":""},"idempotency_key":"example-request-1"}'

{
  "type": "object",
  "required": [
    "loras",
    "prompt",
    "audio_url"
  ],
  "properties": {
    "acceleration": {
      "type": "string",
      "description": "The acceleration level to use.",
      "default": "regular",
      "enum": [
        "none",
        "regular",
        "high",
        "full"
      ]
    },
    "audio_modality_scale": {
      "type": "number",
      "description": "The modality scale for the audio. Controls the ratio between video and audio modalities.",
      "default": 3
    },
    "loras": {
      "type": "array",
      "description": "The LoRAs to use for the generation."
    },
    "fps": {
      "type": "number",
      "description": "The frames per second of the generated video.",
      "default": 24
    },
    "distill_lora_first_pass_scale": {
      "type": "number",
      "description": "The scale of the distill LoRA to use for the first pass. Set to 0 to disable.",
      "default": 0.2
    },
    "audio_strength": {
      "type": "number",
      "description": "Audio conditioning strength. Values below 1.0 will allow the model to change the audio, while a value of exactly 1.0 will use the input audio without modification.",
      "default": 1
    },
    "enable_safety_checker": {
      "type": "boolean",
      "description": "Whether to enable the safety checker.",
      "default": true
    },
    "use_multiscale": {
      "type": "boolean",
      "description": "Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.",
      "default": true
    },
    "audio_url": {
      "type": "string",
      "description": "The URL of the audio to generate the video from."
    },
    "camera_lora_scale": {
      "type": "number",
      "description": "The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.",
      "default": 1
    },
    "enable_prompt_expansion": {
      "type": "boolean",
      "description": "Whether to enable prompt expansion.",
      "default": true
    },
    "end_image_strength": {
      "type": "number",
      "description": "The strength of the end image to use for the video generation.",
      "default": 1
    },
    "seed": {
      "type": "integer",
      "description": "The seed for the random number generator."
    },
    "gradient_estimation_gamma": {
      "type": "number",
      "description": "The gamma of gradient estimation during denoising. Set to 0 to disable.",
      "default": 2
    },
    "sync_mode": {
      "type": "boolean",
      "description": "If `True`, the media will be returned as a data URI and the output data won't be available in the request history.",
      "default": false
    },
    "prompt": {
      "type": "string",
      "description": "The prompt to generate the video from."
    },
    "image_url": {
      "type": "string",
      "description": "Optional URL of an image to use as the first frame of the video."
    },
    "video_size": {
      "type": "string",
      "description": "The size of the generated video. Use 'auto' to match the input image dimensions if provided.",
      "default": "landscape_16_9",
      "enum": [
        "auto",
        "square_hd",
        "square",
        "portrait_4_3",
        "portrait_16_9",
        "landscape_4_3",
        "landscape_16_9"
      ]
    },
    "image_strength": {
      "type": "number",
      "description": "The strength of the image to use for the video generation.",
      "default": 1
    },
    "distill_lora_second_pass_scale": {
      "type": "number",
      "description": "The scale of the distill LoRA to use for the second and subsequent passes.",
      "default": 0.5
    },
    "scheduler": {
      "type": "string",
      "description": "The scheduler to use.",
      "default": "ltx2",
      "enum": [
        "ltx2",
        "linear_quadratic",
        "beta"
      ]
    },
    "audio_cfg_scale": {
      "type": "number",
      "description": "The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.",
      "default": 7
    },
    "camera_lora": {
      "type": "string",
      "description": "The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.",
      "default": "none",
      "enum": [
        "dolly_in",
        "dolly_out",
        "dolly_left",
        "dolly_right",
        "jib_up",
        "jib_down",
        "static",
        "none"
      ]
    },
    "video_rescaling_scale": {
      "type": "number",
      "description": "The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.",
      "default": 0.7
    },
    "video_quality": {
      "type": "string",
      "description": "The quality of the generated video.",
      "default": "high",
      "enum": [
        "low",
        "medium",
        "high",
        "maximum"
      ]
    },
    "end_image_url": {
      "type": "string",
      "description": "The URL of the image to use as the end of the video."
    },
    "video_output_type": {
      "type": "string",
      "description": "The output type of the generated video.",
      "default": "X264 (.mp4)",
      "enum": [
        "X264 (.mp4)",
        "VP9 (.webm)",
        "PRORES4444 (.mov)",
        "GIF (.gif)"
      ]
    },
    "negative_prompt": {
      "type": "string",
      "description": "The negative prompt to generate the video from.",
      "default": "news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static"
    },
    "video_cfg_scale": {
      "type": "number",
      "description": "The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.",
      "default": 3
    },
    "use_restart_sampling": {
      "type": "boolean",
      "description": "Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.",
      "default": false
    },
    "video_write_mode": {
      "type": "string",
      "description": "The write mode of the generated video.",
      "default": "balanced",
      "enum": [
        "fast",
        "balanced",
        "small"
      ]
    },
    "audio_stg_scale": {
      "type": "number",
      "description": "The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.",
      "default": 0
    },
    "num_inference_steps": {
      "type": "integer",
      "description": "The number of inference steps to use.",
      "default": 40
    },
    "num_frames": {
      "type": "integer",
      "description": "The number of frames to generate.",
      "default": 121
    },
    "video_modality_scale": {
      "type": "number",
      "description": "The modality scale for the video. Controls the ratio between video and audio modalities.",
      "default": 3
    },
    "preprocess_audio": {
      "type": "boolean",
      "description": "Whether to preprocess the audio before using it as conditioning.",
      "default": true
    },
    "audio_rescaling_scale": {
      "type": "number",
      "description": "The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.",
      "default": 0.7
    },
    "video_stg_scale": {
      "type": "number",
      "description": "The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.",
      "default": 0
    },
    "match_audio_length": {
      "type": "boolean",
      "description": "When enabled, the number of frames will be calculated based on the audio duration and FPS. When disabled, use the specified num_frames.",
      "default": true
    }
  }
}