KJNodes/ltxvgenerated

LTX2 LoRA Loader Advanced(LTX2LoraLoaderAdvanced)

Advanced LoRA loader with per-block strength control for LTX2 models

LTX2 Lora Loader Advanced

model
model
rank
loaded_keys_info
lora_name
COMBO
strength_model
1.00
opt_lora_path
STRING
video
1.00
video_to_audio
1.00
audio
1.00
audio_to_video
1.00
other
1.00
KJNodes

Description

The LTX2 LoRA Loader Advanced node provides per-block strength control for applying LoRAs to LTX2 video diffusion models. Unlike a standard LoRA loader, this node allows you to independently adjust the influence of the LoRA on different types of attention layers within the model: video, video‑to‑audio cross-attention, audio, audio‑to‑video cross-attention, and all other layers not caught by those filters. This gives you fine‑grained control over how the LoRA modifies the model’s behaviour across modalities.

Inputs

InputTypeRequiredDefaultMinMaxStepTooltip / Description
lora_nameCOMBOYesThe name of the LoRA (select from available LoRAs or type a name).
modelMODELYesThe diffusion model the LoRA will be applied to.
strength_modelFLOATYes1.0-100.0100.00.01How strongly to modify the diffusion model. This value can be negative (inverts the effect).
opt_lora_pathSTRINGNo(empty)Absolute path of the LoRA file. If provided, overrides the selected lora_name lookup.
videoFLOATYes1.00.01.00.01Strength for video attention layers.
video_to_audioFLOATYes1.00.01.00.01Strength for video‑to‑audio cross‑attention layers.
audioFLOATYes1.00.01.00.01Strength for audio attention layers.
audio_to_videoFLOATYes1.00.01.00.01Strength for audio‑to‑video cross‑attention layers.
otherFLOATYes1.00.01.00.01Strength for layers not caught by the other layer filters (e.g., shared or residual components).

Outputs

OutputTypeDescription
modelMODELThe diffusion model with the LoRA applied, modulated by the per‑block strengths.
lora_nameSTRINGThe name of the loaded LoRA (useful for logging or passing to other nodes).
lora_pathSTRINGThe absolute path of the loaded LoRA file (or an empty string if only a name was used).

Usage Notes

  • The strength_model parameter controls the overall influence of the LoRA on the model. The per‑block strength parameters (video, video_to_audio, etc.) multiply against this overall strength for their respective blocks. For example, if strength_model = 1.5 and video = 0.5, the effective strength on video attention layers is 1.5 × 0.5 = 0.75.
  • A single per‑block strength of 0 completely disables the LoRA’s effect on that block type, while a value of 1.0 applies the full (scaled) LoRA effect.
  • The overall strength_model can be negative, which inverts the direction of the LoRA’s modification. Per‑block strengths should be kept in [0.0, 1.0]; negative per‑block values are not supported by the interface.
  • The opt_lora_path input allows you to load a LoRA from a specific file path, bypassing the named‑LoRA selection. If both lora_name and opt_lora_path are provided, the path takes precedence.
  • This node is designed specifically for LTX2 models. Using it with other model architectures may produce unexpected results.

Comments

Sign in with GitHub to join the discussion.

Loading comments…
LTX2 LoRA Loader Advanced (LTX2LoraLoaderAdvanced) - ComfyUI-KJNodes | ComfyUI Wiki