LtxApi25TextToVideo - ComfyUI Built-in Node Documentation - ComfyUI

LTX 2.5 Text To Video is an API node that generates professional-quality videos from a text description using the LTX 2.5 model. You provide a prompt and choose generation settings such as the model tier, duration, resolution, frame rate, and whether to include audio; the node submits the task to the LTX API and returns the resulting video.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	The LTX 2.5 model tier to use for video generation.	STRING	Yes	”LTX-2.5 (Fast)" "LTX-2.5 (Pro)“
`model.duration`	The length of the generated video.	INT	Yes	Integer
`model.resolution`	The output resolution of the video. Available options depend on the selected `model`.	STRING	Yes	With “LTX-2.5 (Fast)”: “1280x720" "720x1280" "1920x1080" "1080x1920" "2560x1440" "1440x2560" "3840x2160" "2160x3840” With “LTX-2.5 (Pro)”: “1280x720" "720x1280" "1920x1080" "1080x1920”
`model.fps`	Frame rate of the generated video (default: 25).	INT	No	Integer
`model.generate_audio`	Whether to generate audio together with the video (default: True).	BOOLEAN	No	True False
`prompt`	The text description of the video to generate. A non-empty prompt of up to 10,000 characters is required (default: "").	STRING	Yes	1 to 10000 characters
`seed`	Seed value used for reproducible generation (default: 42).	INT	No	Integer

Note: The available model.resolution options depend on the selected model. “LTX-2.5 (Fast)” supports resolutions up to 2160x3840, while “LTX-2.5 (Pro)” supports resolutions up to 1920x1080.

Outputs

Output Name	Description	Data Type
`video`	The generated video returned by the LTX API, ready for further use in the workflow. If audio generation was enabled, the video includes synchronized audio.	VIDEO

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 02e131116fb0760cce2cea1e9bc49fa16dd7e4e296903fef5e44b7942b6e84c9