← All models
Generate high-quality video with audio from audio, text and images using LTX-2.3
Example
Details
- Accepts
- text + image + video + audio
Pricing
- Price
- 0.301 cr / megapixel
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Random seed for reproducibility. If None, a random seed is chosen. |
| promptrequired | string | The prompt to guide the video generation. |
| image_url | string | The URL of the starting image. |
| sync_mode | boolean | If True, the media is returned as a data URI inline in the response. Useful for short-lived requests and tests. |
| num_frames | integer | The number of frames to generate. |
| resolution | — | The size of the generated video. 'auto' derives the size from the input image aspect ratio. |
| video_quality | stringenum: low, medium, high, maximum | The quality preset of the generated video. |
| generate_audio | boolean | Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track. |
| guidance_scale | number | Classifier-free guidance scale. The default is tuned for fast, high-quality generation. |
| image_strength | number | Conditioning strength on the start image. 1.0 = exact first-frame match, lower = more freedom for the model. |
| negative_prompt | string | The negative prompt to steer generation away from. |
| video_write_mode | stringenum: fast, balanced, small | The write mode of the generated video. |
| frames_per_second | number | Frames per second of the generated video. |
| num_inference_steps | integer | Number of inference steps. Defaults to 15 and can be increased up to 30. |
| enable_safety_checker | boolean | Whether to enable the safety checker. |
| enable_prompt_expansion | boolean | Whether to enable prompt expansion. |
| audio_url | string | The URL of the audio track that drives generation. |
| match_audio_length | boolean | When enabled, derives the number of frames from the audio duration and frames_per_second. When disabled, uses num_frames. |
| video_url | string | The source video to spatially outpaint. |
| aspect_ratio | stringenum: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16… | Target aspect ratio for the outpainted video. Choose a different ratio than the input video to extend the frame cleanly, e.g. use 16:9 for a 4:3 source. |
| source_scale | number | Scale of the source video inside the target canvas before outpainting. 1.0 uses the largest source size that fits the target canvas, which is recommended for true aspect-ratio outpainting such as 4:3 to 16:9. Lower values create a zoom-out border around the source and are less stable. |
| video_strength | number | Strength of the IC-LoRA video guide for the original content. Higher values preserve the source video more strongly inside the outpainted canvas. |
| output_resolution | stringenum: 480p, 720p, 1080p | Output resolution tier. 480p is faster, 720p is the default balance, and 1080p gives a larger canvas when it fits LTX limits. |
| mask_video_url | string | The mask video. White regions are regenerated; black regions are preserved from the source video. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | The seed actually used for generation. |
| video | — | The generated video. |
| prompt | string | The prompt used for generation (after any expansion). |