ComfyUI Node
MiniMax H3 SelfLift Project — Experimental
Experimental SelfLift project switch for the dedicated Chain workflow. Plan width/height are the final size; lowres_scale defaults to half-size spatial latents. Optional pixel/VAE consistency correction is disabled by default (rho=0). Does not patch ComfyUI or change any other workflow.
MiniMax H3 SelfLift Project — Experimental
- plan
- plan
- status
◄enabledfalse►
◄upscaler_model▾►
◄high_resolution_steps2►
◄cleanup_between_stagesfalse►
◄lowres_scale0.50►
◄rho0.00►
◄w_min0.50►
◄w_max1.00►
Categoryconditioning/minimax/context_loop
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| plan | H3_CHAIN_PLAN | — | |
| enabled | BOOLEAN | false | Project-wide switch in the dedicated SelfLift workflow. Off uses ordinary single-stage sampling; saved clips are not regenerated automatically. |
| upscaler_model | COMBO | Select an installed LBH H3 3D checkpoint, tridae (FP32 clean-latent 2x; downloads verified weights on first use), or bilinear (spatial-only, no weights). Tr1dae requires final dimensions divisible by 64. Required only when enabled; generic image/LTX upscalers are not compatible. | |
| high_resolution_steps | INT | 21–10000 | Final steps at the Plan's full resolution. Must be lower than each generated scene's total steps (e.g. 6 low + 2 high out of 8). |
| cleanup_between_stagesopt | BOOLEAN | false | Release the retired checkpoint's DynamicVRAM buffers before lifting, and unload the learned upscaler after use. Tr1dae's small legacy upscaler is specifically offloaded to CPU; other classic/non-dynamic models are skipped. Preserves shared models and saved takes; can slow next-scene reloads. |
| lowres_scaleopt | FLOAT | 0.500.25–1 | First-stage width/height relative to the final Plan size, rounded to H3's even latent grid. 0.5 keeps the existing half-resolution behavior. Tr1dae requires an exact 2x lift: use 0.5 and final dimensions divisible by 64. |
| rhoopt | FLOAT | 0.000–1 | Fraction of the most inconsistent latent locations to correct toward a pixel/VAE anchor. 0 keeps the existing direct lift. Above 0 (with w_max > 0) adds a full video VAE decode, pixel resize and VAE encode; costs time/memory and can change detail/color. Experimental, not a guaranteed artifact fix. |
| w_minopt | FLOAT | 0.500–1 | Minimum pixel/VAE correction strength at selected locations. Inactive when rho=0. Must be <= w_max; 0 keeps the direct lift and 1 uses the pixel/VAE anchor. |
| w_maxopt | FLOAT | 1.000–1 | Maximum pixel/VAE correction strength at the most inconsistent locations. Inactive when rho=0. Must be >= w_min; setting both weights to 0 skips the pixel/VAE pass. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| plan | H3_CHAIN_PLAN | — |
| status | STRING | — |