ComfyUI Node
Muse Collective LTX Timeline V4
Muse Collective LTX Timeline V4 — fully standalone LTX 2.3 AV Director + Infinite Sampler, with Seed Hunt scouting, Face ID, and Ghost Mask character-sheet references (reference_mode). Reference-frame latent extension for seamless multi-chunk generation. No WhatDreamsCost dependency.
Muse Collective LTX Timeline V4
- model
- clip
- audio_vae
- vae
- spatial_upscaler
- bg_audio
- base_model
- face_reference_image
- last_chunk_frames
- audio
- stage1_frames
- seed_hunt_preview_1
- seed_hunt_preview_2
- seed_hunt_preview_3
- seed_hunt_preview_4
- seed_hunt_audio_1
- seed_hunt_audio_2
- seed_hunt_audio_3
- seed_hunt_audio_4
◄start_second0.00►
◄end_second10.00►
◄duration_seconds10.00►
◄start_frame0►
◄end_frame240►
◄duration_frames240►
◄timeline_data{}►
◄local_prompts►
◄segment_lengths►
◄global_prompt►
◄guide_strength►
◄epsilon0.0010►
◄frame_rate24.00►
◄display_modeseconds►
◄custom_width960►
◄custom_height544►
◄resize_methodmaintain aspect ratio►
◄divisible_by32►
◄img_compression18►
◄generate_audiotrue►
◄custom_audio_onfalse►
◄lipsynctrue►
◄motion_guide_ontrue►
◄chunk_duration_seconds10.0►
◄auto_chunk_threshold10.0►
◄carry_frames73►
◄carry_strength1.00►
◄crossfade_frames0►
◄ic_lora_nameNone►
◄ic_lora_strength1.00►
◄stage1_steps8►
◄stage2_steps4►
◄stage2_denoise0.42►
◄cfg1.0►
◄seed42►
◄filename_prefixmuse►
◄bg_volume1.00►
◄guide_scale_by0.50►
◄guide_scale_by_s21.00►
◄guide_upscale_methodbicubic►
◄guide_image_attn_strength1.00►
◄guide_cropcenter►
◄guide_auto_snap_ic_gridtrue►
◄guide_use_tiled_encodefalse►
◄guide_tile_size256►
◄guide_tile_overlap64►
◄timeline_ui►
◄seed_huntfalse►
◄seed_hunt_steps6►
◄seed_hunt_scale0.25►
◄seed_hunt_11►
◄seed_hunt_22►
◄seed_hunt_33►
◄seed_hunt_44►
◄use_seed_hunt_1false►
◄use_seed_hunt_2false►
◄use_seed_hunt_3false►
◄use_seed_hunt_4false►
◄face_id_enabledfalse►
◄identity_projectorNone►
◄source_id2►
◄phase_scale1.0►
◄id_strength1.0►
◄arcface_modeauto_adjust►
◄reference_modeOFF►
◄reference_strength1.00►
◄char1_description►
◄char2_description►
◄char3_description►
CategoryMuse Collective
Inputs (77)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| clip | CLIP | — | |
| audio_vae | VAE | — | |
| vae | VAE | — | |
| spatial_upscaler | LATENT_UPSCALE_MODEL | — | |
| start_second | FLOAT | 0.000–3600 | — |
| end_second | FLOAT | 10.000–3600 | — |
| duration_seconds | FLOAT | 10.000–3600 | — |
| start_frame | INT | 00–86400 | — |
| end_frame | INT | 2400–86400 | — |
| duration_frames | INT | 2401–86400 | — |
| timeline_data | STRING | {} | — |
| local_prompts | STRING | — | |
| segment_lengths | STRING | — | |
| global_prompt | STRING | — | |
| guide_strength | STRING | — | |
| epsilon | FLOAT | 0.00100–1 | — |
| frame_rate | FLOAT | 24.001–120 | — |
| display_mode | COMBO | seconds | 2 options: seconds, frames |
| custom_width | INT | 96064–4096 | — |
| custom_height | INT | 54464–4096 | — |
| resize_method | COMBO | maintain aspect ratio | 4 options: maintain aspect ratio, stretch to fit, crop, pad |
| divisible_by | INT | 321–256 | — |
| img_compression | INT | 180–51 | — |
| generate_audio | BOOLEAN | true | LTX generates ambient/sfx audio from [SOUNDS] prompts. |
| custom_audio_on | BOOLEAN | false | Use audio file(s) from the AUDIO timeline track. |
| lipsync | BOOLEAN | true | Sync mouth movements to custom audio. Requires Custom Audio ON and talking head LoRA. |
| motion_guide_on | BOOLEAN | true | Use motion guide segments from the timeline. |
| chunk_duration_seconds | FLOAT | 10.02–120 | — |
| auto_chunk_threshold | FLOAT | 10.00–3600 | — |
| carry_frames | INT | 731–240 | Reference frames from previous chunk locked at chunk start. 73 ≈ 3s at 24fps. |
| carry_strength | FLOAT | 1.000–1 | — |
| crossfade_frames | INT | 00–120 | — |
| ic_lora_name | COMBO | None | 1 options: None |
| ic_lora_strength | FLOAT | 1.00-10–10 | — |
| stage1_steps | INT | 81–50 | — |
| stage2_steps | INT | 41–50 | — |
| stage2_denoise | FLOAT | 0.420–1 | — |
| cfg | FLOAT | 1.00–20 | — |
| seed | INT | 420–18446744073709550000 | — |
| filename_prefix | STRING | muse | — |
| bg_volume | FLOAT | 1.000–2 | — |
| guide_scale_by | FLOAT | 0.500.01–8 | — |
| guide_scale_by_s2 | FLOAT | 1.000.01–8 | — |
| guide_upscale_method | COMBO | bicubic | 5 options: bicubic, bilinear, nearest-exact, area, bislerp |
| guide_image_attn_strength | FLOAT | 1.000–1 | — |
| guide_crop | COMBO | center | 2 options: center, disabled |
| guide_auto_snap_ic_grid | BOOLEAN | true | — |
| guide_use_tiled_encode | BOOLEAN | false | — |
| guide_tile_size | INT | 25664–512 | — |
| guide_tile_overlap | INT | 6416–256 | — |
| timeline_ui | STRING | — | |
| seed_hunt | BOOLEAN | false | ON + no candidate chosen: run a 4-seed Stage-1-resolution preview instead of the full pipeline. ON + one use_seed_hunt_N chosen: commit to that candidate — Stage 2 refines its actual cached latent instead of regenerating Stage 1 from scratch. |
| seed_hunt_steps | INT | 61–50 | — |
| seed_hunt_scale | FLOAT | 0.250.05–1 | Unused as of 1.0.4 — Seed Hunt now scouts at Stage 1's real resolution automatically (so the picked candidate's actual latent can carry forward into Stage 2). Kept as a widget only so older saved workflows still load correctly. |
| seed_hunt_1 | INT | 10–18446744073709550000 | Unused as of 1.0.4 — scouting now draws a fresh random seed for each candidate every run instead of reusing these fixed values (the actual latent carries forward on commit, so the seed number no longer needs to be fixed or reproducible). |
| seed_hunt_2 | INT | 20–18446744073709550000 | — |
| seed_hunt_3 | INT | 30–18446744073709550000 | — |
| seed_hunt_4 | INT | 40–18446744073709550000 | — |
| use_seed_hunt_1 | BOOLEAN | false | — |
| use_seed_hunt_2 | BOOLEAN | false | — |
| use_seed_hunt_3 | BOOLEAN | false | — |
| use_seed_hunt_4 | BOOLEAN | false | — |
| face_id_enabled | BOOLEAN | false | Patches the model at every Stage 1/Stage 2/per-chunk build point so the sampled face is pulled toward face_reference_image. Requires the matching Best-Face-ID LoRA already loaded onto the model input, and ComfyUI-BFSNodes installed. Off = identical to V2. |
| identity_projector | STRING | None | ArcFace projector .safetensors filename from models/loras, or 'None' for overlap-only (recommended default — the projector is a weak channel; the overlap latent carries the bulk of identity). |
| source_id | FLOAT | 20–8 | — |
| phase_scale | FLOAT | 1.00–4 | — |
| id_strength | FLOAT | 1.00–50 | — |
| arcface_mode | COMBO | auto_adjust | 3 options: auto_adjust, as_is, disable |
| reference_mode | COMBO | OFF | Ghost Mask hides each loaded character's reference image as an extra latent frame past the end of chunk 1's clean region — never decoded into the visible output, but the sampler can attend to it as an identity anchor. Applied to chunk 1 only; later chunks inherit identity via the normal carry-frame continuity. |
| reference_strength | FLOAT | 1.000–5 | Guide strength applied to the character reference frames (Ghost Mask only). |
| char1_description | STRING | Text swapped in for @char1/@character1 in your prompts. | |
| char2_description | STRING | Text swapped in for @char2/@character2 in your prompts. | |
| char3_description | STRING | Text swapped in for @char3/@character3 in your prompts. | |
| bg_audioopt | AUDIO | — | |
| base_modelopt | MODEL | Base model without talking-head LoRA. Connect the UNETLoader output directly here so the ambient audio pass generates sounds without speech. | |
| face_reference_imageopt | IMAGE | Reference face for Face ID (see face_id_enabled). Feed it a close-up face crop — Muse Face Lock can produce one from any reference image automatically. |
Outputs (11)
| Name | Type | Description |
|---|---|---|
| last_chunk_frames | IMAGE | — |
| audio | AUDIO | — |
| stage1_frames | IMAGE | — |
| seed_hunt_preview_1 | IMAGE | — |
| seed_hunt_preview_2 | IMAGE | — |
| seed_hunt_preview_3 | IMAGE | — |
| seed_hunt_preview_4 | IMAGE | — |
| seed_hunt_audio_1 | AUDIO | — |
| seed_hunt_audio_2 | AUDIO | — |
| seed_hunt_audio_3 | AUDIO | — |
| seed_hunt_audio_4 | AUDIO | — |