## Basic model info

Model name: lightricks/ltx-2.5-fast
Model description: Fast video generation with text-to-video and image-to-video, portrait and landscape support, synchronized audio, and frame interpolation. Up to 20 seconds at 1080p, and 4K resolution.


## Model inputs

- prompt (required): Text prompt describing the video to generate (string)
- image (optional): First frame image for image-to-video generation (string)
- last_frame_image (optional): Last frame image for image-to-video generation. When provided, the video interpolates between the first frame and this last frame. (string)
- resolution (optional): Resolution quality of the generated video. Higher resolutions cap the maximum duration. (string)
- duration (optional): Duration of the video in seconds. Durations longer than 10 seconds are only available at 720p or 1080p resolution with 24 or 25 FPS. 48/50 FPS caps at 10 seconds. (integer)
- aspect_ratio (optional): Aspect ratio of the generated video (string)
- fps (optional): Frame rate in frames per second (integer)
- generate_audio (optional): Generate audio for the video. Used for text_to_video and image_to_video tasks. (boolean)


## Model output schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}

If the input or output schema includes a format of URI, it is referring to a file.


## Example inputs and outputs

Use these example outputs to better understand the types of inputs the model accepts, and the types of outputs the model returns:

### Example (https://replicate.com/p/mn3dc735thrmy0czy9jrbe0cgc)

#### Input

```json
{
  "fps": 25,
  "image": "https://replicate.delivery/pbxt/PblPHd56Zo9AD9mXKnMv3StmbLYpcGXQxpvJuv63BDXbIjEe/tmpxkkpppu3.png",
  "prompt": "the giant looks down at the people and the people look up at him.  \"LTX-2.5\" text stays on the screen the whole time. birds chirping in background loudly and dense jungle noises",
  "duration": 6,
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "generate_audio": true
}
```

#### Output

```json
"https://replicate.delivery/xezq/LIjU3whDDLLqNJfp3EAfqtfp03Muj4ICqDSi8y2c1POhDmEuA/tmpp_vjvbr9.mp4"
```


## Model readme

> # LTX 2.5 Fast
> 
> LTX 2.5 Fast is the speed-optimized variant of Lightricks' LTX-2.5 video generation model. It generates videos with synchronized audio quickly — good for rapid prototyping, mobile workflows, and high-volume production.
> 
> It supports both text-to-video and image-to-video, including start-and-end frame interpolation.
> 
> ## Inputs
> 
> | Input | Description | Default |
> |---|---|---|
> | `prompt` | Text description of the video to generate | (required) |
> | `image` | First frame image for image-to-video | None |
> | `last_frame_image` | End frame for interpolation (requires `image`) | None |
> | `resolution` | Video resolution: `720p`, `1080p`, `2k`, or `4k` | `1080p` |
> | `duration` | Length in seconds: 2, 3, 4, 5, 6, 8, 10, 12, 14, 16, 18, or 20 | `6` |
> | `aspect_ratio` | `16:9` (landscape) or `9:16` (portrait) | `16:9` |
> | `fps` | Frame rate: 24, 25, 48, or 50 | `25` |
> | `generate_audio` | Generate synchronized audio | `true` |
> 
> Durations longer than 10 seconds are only available at 720p or 1080p with 24 or 25 FPS. At 48 or 50 FPS the maximum duration is 10 seconds.
> 
> ## Output
> 
> MP4 video file with synchronized audio (when `generate_audio` is enabled).
> 
> ## Prompting tips
> 
> - Write one continuous paragraph in present tense
> - Be specific about camera angles, lighting, and movement
> - Include atmospheric details: lighting quality, weather, textures
> - Describe actions with active verbs: "walks", "pans slowly", "zooms in"
> - Longer, more detailed prompts produce better results
> 
> ## Image-to-video
> 
> Pass a first frame with `image`. To generate a video that transitions between two frames, also pass `last_frame_image`. The `last_frame_image` input requires `image` to be set.

