ComfyUI Node
LTX Reference Bind Schedule (Koolook)
Ramp the reference's guide-attention UP at low sigma so identity locks during refinement without disturbing early motion. Works WITHOUT an IC-LoRA: it fabricates the per-guide attention entries for the trailing reference tokens itself (set num_keyframes so it knows the split), so the reference gets the same amplified-attention channel an IC-LoRA would use — inside the Director, no guide-node changes. Mirror of LTX A/V Bind Schedule. One pass, no re-noise.
LTX Reference Bind Schedule (Koolook)
- model
- model
◄num_references1►
◄peak_strength2.00►
◄ramp_start0.50►
◄ramp_end0.90►
◄num_keyframes0►
CategoryKoolook/LTX
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | LTX 2.3 model (the same one feeding the guide pipeline). | |
| num_references | INT | 10–64 | How many trailing guide frames are references (= how many images you fed LTX Director's reference_images). They're appended after the keyframes, so the LAST N guide frames are the references. |
| peak_strength | FLOAT | 2.001–8 | Reference attention multiplier at the end of denoise (low sigma). 1.0 = no boost; 2.0 = double the identity pull during refinement. Try 2-4. |
| ramp_startopt | FLOAT | 0.500–1 | Denoise progress (0=start, 1=end) where the reference boost begins. Keep above where big motion finalizes (~0.5-0.6) so motion forms first. |
| ramp_endopt | FLOAT | 0.900–1 | Denoise progress where the boost reaches peak_strength. |
| num_keyframesopt | INT | 00–256 | No-LoRA path only: how many timeline image keyframes precede the references, so the node knows the keyframe/reference token split. Set this = your number of timeline image segments (e.g. 4). Leave 0 and the WHOLE guide region is treated as reference (also boosts keyframes). Ignored when an IC-LoRA populated real entries. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| model | MODEL | — |