LTXVAddGuide - ComfyUI Built-in Node Documentation

The LTXVAddGuide node encodes input images or videos through a VAE encoder and adds them as guide keyframes to a latent video sequence. It updates both positive and negative conditioning and returns the modified latent, with options to set the starting frame, conditioning strength, an optional attention mask, and optional IC-LoRA parameters.

Inputs

Parameter	Description	Data Type	Required	Range
`positive`	Positive conditioning input to be modified with keyframe guidance.	CONDITIONING	Yes	-
`negative`	Negative conditioning input to be modified with keyframe guidance.	CONDITIONING	Yes	-
`vae`	VAE model used for encoding the input image/video frames.	VAE	Yes	-
`latent`	Input latent sequence that will receive the conditioning frames.	LATENT	Yes	-
`image`	Image or video to condition the latent video on. Must be 8n + 1 frames. If the video is not 8n + 1 frames, it will be cropped to the nearest 8*n + 1 frames.	IMAGE	Yes	-
`frame_idx`	Frame index to start the conditioning at. For single-frame images or videos with 1-8 frames, any frame_idx value is acceptable. For videos with 9+ frames, frame_idx must be divisible by 8, otherwise it will be rounded down to the nearest multiple of 8. Negative values are counted from the end of the video. Default: 0.	INT	Yes	-9999 to 9999
`strength`	Strength of the conditioning influence, where 1.0 applies full conditioning and 0.0 applies no conditioning. Default: 1.0.	FLOAT	Yes	0.0 to 10.0
`attention_mask`	Optional pixel-space spatial mask. Controls per-region conditioning influence via self-attention, multiplied by strength.	MASK	No	-
`iclora_parameters`	Optional IC-LoRA parameters from a Get IC-LoRA Parameters node. Used for adjusting guide processing as required by certain IC-LoRAs (e.g., those with a reference_downscale_factor > 1). When chained, each LTXVAddGuide uses only the parameters connected to it.	IC_LORA_PARAMETERS	No	-

Note: The input image/video must have a frame count following the 8*n + 1 pattern (e.g., 1, 9, 17, 25 frames). If the input exceeds this pattern, it will be automatically cropped to the nearest valid frame count. Note on iclora_parameters: When using IC-LoRA parameters with a reference_downscale_factor greater than 1, the latent spatial dimensions (width and height) must be divisible by that factor. The node will raise an error if this condition is not met. Note: The encoded guide frames must fit within the latent sequence at the selected frame position. If the conditioned frames exceed the length of the latent sequence, the node raises an error. Note: Adding a guide to a latent that combines audio and video channels is not supported and will raise an error.

Outputs

Output Name	Description	Data Type
`positive`	Positive conditioning updated with keyframe guidance information.	CONDITIONING
`negative`	Negative conditioning updated with keyframe guidance information.	CONDITIONING
`latent`	Latent sequence with incorporated conditioning frames and updated noise mask.	LATENT

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): 031bc9030dafed85b5ff1cbceae36234e9d5f77f7f4b040267067ecd16a27929

​Inputs

​Outputs

Inputs

Outputs