Nodes/muse-ltx-timeline/LTX Infinite Director Sampler V7 (Ref-Frame Lock)
ComfyUI Node

LTX Infinite Director Sampler V7 (Ref-Frame Lock)

Reference-frame latent extension for LTX 2.3. The last carry_frames pixel frames from chunk N are VAE-encoded and locked (noise_mask=0) at the start of chunk N+1's latent. The model generates only the new region in a single pass, anchored to real prior content — same architecture as Kijai NativeLooping and LTX extend workflows.

By muse-collective-26·Created 2 months ago·Updated 23 days ago· 5
LTX Infinite Director Sampler V7 (Ref-Frame Lock)
  • model
  • clip
  • audio_vae
  • vae
  • spatial_upscaler
  • bg_audio
  • last_chunk_frames
  • audio
  • stage1_frames
start_second0.00
end_second85.00
duration_seconds85.00
start_frame0
end_frame2040
duration_frames2040
timeline_data{}
local_prompts
segment_lengths
global_prompt
guide_strength
epsilon0.0010
frame_rate24.00
display_modeseconds
custom_width720
custom_height1280
resize_methodmaintain aspect ratio
divisible_by32
img_compression0
generate_audiotrue
custom_audio_onfalse
motion_guide_ontrue
chunk_duration_seconds17.0
auto_chunk_threshold20.0
carry_frames73
carry_strength1.00
crossfade_frames0
ic_lora_nameNone
ic_lora_strength1.00
stage1_steps8
stage2_steps4
stage2_denoise0.42
cfg1.0
seed1000
filename_prefixmuse
bg_volume1.00
CategoryLTXInfiniteDirector

Inputs (42)

NameTypeDefaultDescription
modelMODEL
clipCLIP
audio_vaeVAE
start_secondFLOAT0.000–3600
end_secondFLOAT85.000–3600Total video length in seconds.
duration_secondsFLOAT85.000–3600
start_frameINT00–86400
end_frameINT20400–86400
duration_framesINT20400–86400
timeline_dataSTRING{}
local_promptsSTRING
segment_lengthsSTRING
global_promptSTRING
guide_strengthSTRING
epsilonFLOAT0.00100–1
frame_rateFLOAT24.001–120
display_modeCOMBOseconds2 options: seconds, frames
custom_widthINT72064–4096
custom_heightINT128064–4096
resize_methodCOMBOmaintain aspect ratio4 options: maintain aspect ratio, stretch to fit, crop, pad
divisible_byINT321–256
img_compressionINT00–51
generate_audioBOOLEANtrueLTX generates audio from [SOUNDS] prompts. Can be combined with BG Audio.
custom_audio_onBOOLEANfalseUse audio file from the timeline AUDIO track. Can be combined with Generate Audio.
motion_guide_onBOOLEANtrueUse motion guide segments from the timeline.
vaeVAE
spatial_upscalerLATENT_UPSCALE_MODEL
chunk_duration_secondsFLOAT17.02–120
auto_chunk_thresholdFLOAT20.00–3600
carry_framesINT731–240Reference frames from previous chunk to lock at the start of each new chunk. More = stronger continuity, bigger latent. 73 ≈ 3s at 24fps.
carry_strengthFLOAT1.000–1Unused in V4 (kept for workflow compatibility).
crossfade_framesINT00–120
ic_lora_nameCOMBONone1 options: None
ic_lora_strengthFLOAT1.00-10–10
stage1_stepsINT81–50
stage2_stepsINT41–50
stage2_denoiseFLOAT0.420–1
cfgFLOAT1.00–20
seedINT10000–18446744073709550000
filename_prefixSTRINGmuse
bg_volumeFLOAT1.000–2
bg_audiooptAUDIO

Outputs (3)

NameTypeDescription
last_chunk_framesIMAGE
audioAUDIO
stage1_framesIMAGE