Nodes/CRT-Nodes/LTX 2.3 Unified Sampler (CRT)
ComfyUI Node

LTX 2.3 Unified Sampler (CRT)

A ComfyUI node in CRT/LTX2.3 with 27 inputs and 2 outputs.

By PGCRT·Created 2 years ago·Updated 7 days ago· 129
LTX 2.3 Unified Sampler (CRT)
  • models_pipe
  • config_pipe
  • images
  • audio
workflow_modeI2V
hqfalse
live_previewfalse
frame_count_from_audiofalse
vae_decode_tiledfalse
unload_model_before_vae_decodetrue
low_vramtrue
megapixels_target1.0
aspect_ratio16:9 (Landscape)
frame_count161
v2v_modeDepth Control
v2v_guide_strength0.60
depth_megapixels0.30
v2v_aspect_ratio16:9 (Landscape)
sampler_maineuler
sampler_refineeuler
steps9
generated_audio_gain_db-12.0
firstframe_strength1.00
depth_mouth_maskfalse
mouth_detect_megapixels0.25
mouth_single_itemtrue
mouth_detect_chunk_size10
mouth_mask_expand8
mouth_mask_blur8.0
CategoryCRT/LTX2.3

Inputs (27)

NameTypeDefaultDescription
models_pipeLTX23_US_MODELS_PIPE
config_pipeLTX23_US_CONFIG_PIPE
workflow_modeCOMBOI2V3 options: I2V, T2V, V2V
hqBOOLEANfalse
live_previewBOOLEANfalse
frame_count_from_audioBOOLEANfalse
vae_decode_tiledBOOLEANfalse
unload_model_before_vae_decodeBOOLEANtrue
low_vramBOOLEANtrueWhen enabled, unloads the text encoder after conditioning and the VAE before sampling to reduce VRAM usage. The VAE is reloaded before decoding.
megapixels_targetFLOAT1.00.1–16
aspect_ratioCOMBO16:9 (Landscape)20 options: 1:1 (Square), 2:3 (Portrait), 3:4 (Portrait), 4:5 (Portrait), 5:7 (Portrait), 5:8 (Portrait), +14
frame_countINT1611–4096
v2v_modeCOMBODepth Control3 options: Depth Control, Outpaint, Upscale
v2v_guide_strengthFLOAT0.600–1
depth_megapixelsFLOAT0.300.05–8
v2v_aspect_ratioCOMBO16:9 (Landscape)20 options: 1:1 (Square), 2:3 (Portrait), 3:4 (Portrait), 4:5 (Portrait), 5:7 (Portrait), 5:8 (Portrait), +14
sampler_mainCOMBOeuler44 options: euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, heunpp2, +38
sampler_refineCOMBOeuler44 options: euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, heunpp2, +38
stepsINT94–128
generated_audio_gain_dbFLOAT-12.0-60–24
firstframe_strengthFLOAT1.000–1
depth_mouth_maskBOOLEANfalse
mouth_detect_megapixelsFLOAT0.250–8Deprecated compatibility input. Ignored; mouth detection uses hardcoded fast mode.
mouth_single_itemBOOLEANtrueDeprecated compatibility input. Ignored; hardcoded internally.
mouth_detect_chunk_sizeINT100–4096Deprecated compatibility input. Ignored; hardcoded internally.
mouth_mask_expandINT80–100Expands the mouth mask before applying it to the depth guide so lip motion influence covers a larger area.
mouth_mask_blurFLOAT8.00–100Softens the mouth mask edges to avoid harsh transitions in the depth guide.

Outputs (2)

NameTypeDescription
imagesIMAGE
audioAUDIO