ComfyUI Node
MiniMax H3 Ref Tinker (CCN)
Experimental control over MiniMax H3 reference conditioning: reference strength (cond-row noise aug) and reference RoPE geometry (temporal gap to the target streams, spatial offset of image refs). Wraps the diffusion-model call; composes with other model patches.
MiniMax H3 Ref Tinker (CCN)
- model
- MODEL
◄enabledtrue►
◄visual_cond_noise_aug0.999►
◄audio_cond_noise_aug1.000►
◄ref_temporal_gap0.0►
◄ref_spatial_shift_h0.00►
◄ref_spatial_shift_w0.00►
Categorymodel/patch/minimax
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| enabled | BOOLEAN | true | Manual off switch - passes the model through unpatched. |
| visual_cond_noise_aug | FLOAT | 0.9990–1 | Strength of visual condition rows (reference images and fl2va keyframes). 0.999 = stock (rows re-injected ~clean every step). Lower mixes fixed-seed noise into the rows (aug*latent + (1-aug)*noise) and lowers their declared timestep, weakening verbatim copying before identity. Useful band ~0.90-1.00. |
| audio_cond_noise_aug | FLOAT | 1.0000–1 | Same for reference-audio rows. 1.0 = stock (fully clean). |
| ref_temporal_gap | FLOAT | 0.0-1–2000 | Extra RoPE-time distance between reference blocks and the target audio/video streams, in position ticks (1 tick = 1/40 s on the shared AV clock). Stock ref->video gap is 1.0 tick; video frame hops are 1.67/6.67. -1.0 co-locates the last image ref with frame 0 (soft keyframe-anchor mode). 0 = stock. |
| ref_spatial_shift_h | FLOAT | 0.00-64–64 | Offset added to image-reference RoPE h coordinates (frame grids are area-normalized, roughly spanning 0-32). Decorrelates ref<->target pixel alignment without editing the image. 0 = stock. |
| ref_spatial_shift_w | FLOAT | 0.00-64–64 | Offset added to image-reference RoPE w coordinates. 0 = stock. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| MODEL | MODEL | — |