Nodes/ComfyUI-GGUF-Loader/LTX-2.3 Img/Audio to Video ⚡
ComfyUI Node

LTX-2.3 Img/Audio to Video ⚡

Prompts, init latent and noise masks for LTX-2.3 T2V/I2V/A2V/IA2V. Feed into the LTX-2.3 KSampler.

By ChrisColeTech·Created 13 days ago·Updated about 3 hours ago· 6
LTX-2.3 Img/Audio to Video ⚡
  • clip
  • vae
  • audio_vae
  • image
  • reference_audio
  • positive
  • negative
  • latent
prompt
negative_prompt
width768
height512
length121
frame_rate24.00
batch_size1
image_strength0.70
length_from_audiotrue
Category🤖 CCTech/LTX-2.3

Inputs (14)

NameTypeDefaultDescription
clipCLIP
vaeVAEThe loader's video_vae output.
audio_vaeVAEThe loader's audio_vae output.
promptSTRINGDescribe the scene and its motion. A caption, not an instruction.
negative_promptSTRING
widthINT76864–16384
heightINT51264–16384
lengthINT1219–16384Frames; 8k+1 tiles exactly (9, 97, 121...). Ignored when length_from_audio is on.
frame_rateFLOAT24.001–12024 is the LTX-2 convention. Match this in CreateVideo or playback drifts.
batch_sizeINT11–4096
imageoptIMAGEFirst frame. Resized and CENTER-CROPPED to width x height here - do not scale it upstream.
reference_audiooptAUDIO
image_strengthoptFLOAT0.700–1i2v only. How much of the init image to keep. 0.7 is the official value; 1.0 locks the first frames hard.
length_from_audiooptBOOLEANtrueWith reference_audio: size the video to the clip.

Outputs (3)

NameTypeDescription
positiveCONDITIONING
negativeCONDITIONING
latentLATENT