← All models
Generate video with audio from audio, text and images using LTX-2
Example
Details
- Accepts
- text + image + video + audio
Pricing
- Price
- 0.201 cr / megapixel
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| fps | number | The frames per second of the generated video. |
| seed | — | The seed for the random number generator. |
| promptrequired | string | The prompt to generate the video from. |
| scheduler | stringenum: ltx2, linear_quadratic, beta | The scheduler to use. |
| sync_mode | boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. |
| num_frames | integer | The number of frames to generate. |
| video_size | — | The size of the generated video. |
| camera_lora | stringenum: dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down… | 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. |
| acceleration | stringenum: none, regular, high, full | The acceleration level to use. |
| video_quality | stringenum: low, medium, high, maximum | The quality of the generated video. |
| generate_audio | boolean | Whether to generate audio for the video. |
| use_multiscale | boolean | 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. |
| audio_cfg_scale | number | The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content. |
| audio_stg_scale | number | The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content. |
| negative_prompt | string | The negative prompt to generate the video from. |
| video_cfg_scale | number | The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content. |
| video_stg_scale | number | The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content. |
| video_write_mode | stringenum: fast, balanced, small | The write mode of the generated video. |
| camera_lora_scale | number | 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. |
| video_output_type | stringenum: X264 (.mp4), VP9 (.webm), PRORES4444 (.mov), GIF (.gif) | The output type of the generated video. |
| num_inference_steps | integer | The number of inference steps to use. |
| audio_modality_scale | number | The modality scale for the audio. Controls the ratio between video and audio modalities. |
| use_restart_sampling | boolean | 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. |
| video_modality_scale | number | The modality scale for the video. Controls the ratio between video and audio modalities. |
| audio_rescaling_scale | number | The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance. |
| enable_safety_checker | boolean | Whether to enable the safety checker. |
| video_rescaling_scale | number | The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance. |
| enable_prompt_expansion | boolean | Whether to enable prompt expansion. |
| gradient_estimation_gamma | number | The gamma of gradient estimation during denoising. Set to 0 to disable. |
| distill_lora_first_pass_scale | number | The scale of the distill LoRA to use for the first pass. Set to 0 to disable. |
| distill_lora_second_pass_scale | number | The scale of the distill LoRA to use for the second and subsequent passes. |
| image_url | string | The URL of the image to generate the video from. |
| end_image_url | — | The URL of the image to use as the end of the video. |
| image_strength | number | The strength of the image to use for the video generation. |
| end_image_strength | number | The strength of the end image to use for the video generation. |
| interpolation_direction | stringenum: forward, backward | The direction to interpolate the image sequence in. 'Forward' goes from the start image to the end image, 'Backward' goes from the end image to the start image. |
| audio_url | string | The URL of the audio to generate the video from. |
| audio_strength | number | 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. |
| preprocess_audio | boolean | Whether to preprocess the audio before using it as conditioning. |
| match_audio_length | boolean | When enabled, the number of frames will be calculated based on the audio duration and FPS. When disabled, use the specified num_frames. |
| video_url | string | The URL of the video to generate the video from. |
| video_strength | number | Video conditioning strength. Lower values represent more freedom given to the model to change the video content. |
| match_input_fps | boolean | When true, match the output FPS to the input video's FPS instead of using the default target FPS. |
| match_video_length | boolean | When enabled, the number of frames will be calculated based on the video duration and FPS. When disabled, use the specified num_frames. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | The seed used for the random number generator. |
| video | — | The generated video. |
| prompt | string | The prompt used for the generation. |