ComfyUI Node
H3MD Sampler (two-pass)
Two-pass MiniMax H3 sampling (low-res pass, latent lift, full-res pass) on the bundled Luna-H3-Sampler engine, with H3MD drift, low-res head, VRAM release between the passes and high-res tiling. Outputs only the final latent.
H3MD Sampler (two-pass)
- low_res_model
- positive
- negative
- vae
- latent_image
- sampler
- sigmas
- high_res_model
- latent
◄seed0►
◄cfg1.0►
◄transition_step6►
◄lowres_scale0.50►
◄rho0.00►
◄w_min0.50►
◄w_max1.00►
◄upscaler_modelnone►
◄highres_tilingtrue►
◄tiling_axisauto►
◄tiling_overlap8►
◄ff_chunk_rows0►
◄release_upscalertrue►
◄unload_idle_modelstrue►
CategoryMiniMax H3/H3MD
Inputs (22)
| Name | Type | Default | Description |
|---|---|---|---|
| low_res_model | MODEL | Model for the low-res pass (and the high-res pass when high_res_model is not connected). | |
| positive | CONDITIONING | — | |
| negative | CONDITIONING | — | |
| vae | VAE | Video VAE (pixel route of the lift when rho > 0). | |
| latent_image | LATENT | Target-size H3 audio+video latent; noise_mask 0 = keep. | |
| sampler | SAMPLER | — | |
| sigmas | SIGMAS | One schedule for both passes; split at transition_step. | |
| seed | INT | 00–18446744073709550000 | — |
| cfg | FLOAT | 1.00–100 | — |
| transition_step | INT | 61–10000 | Steps of the schedule run at low resolution; the rest run at full resolution. |
| lowres_scale | FLOAT | 0.500.25–1 | Size of the low-res pass (0.5 = half width and height). |
| rho | FLOAT | 0.000–1 | Share of the most inconsistent positions corrected toward the pixel-VAE route. 0 = learned upscaler only (no VAE round trip). |
| w_min | FLOAT | 0.500–1 | — |
| w_max | FLOAT | 1.000–1 | — |
| upscaler_model | COMBO | none | Learned H3 3D latent upscaler for the lift (models/latent_upscale_models or upscale_models). none = nearest. |
| high_res_modelopt | MODEL | Model for the high-res pass (default: low_res_model). | |
| highres_tilingopt | BOOLEAN | true | High-res pass: measure the free VRAM and use the fewest strips that fit (full frame when it fits - no cost on large cards). Off = always full frame. |
| tiling_axisopt | COMBO | auto | High-res tiling: split direction. auto = the longer side; width = left/right strips; height = top/bottom strips. Audio and time are never split. |
| tiling_overlapopt | INT | 82–32 | High-res tiling: overlap between neighbouring strips in latent pixels (x16 image pixels); the strip predictions are feather-blended over it. |
| ff_chunk_rowsopt | INT | 00–262144 | Low VRAM: run the DiT feed-forward on this many sequence rows at a time (both passes). Same result, lower peak memory, a little slower. 0 = off (the high-res tiling still switches it on by itself after an out-of-memory retry at the most strips). |
| release_upscaleropt | BOOLEAN | true | Drop the learned upscaler from RAM right after the lift. |
| unload_idle_modelsopt | BOOLEAN | true | Between the passes: unload text encoder / VAEs / other idle models + empty the cache. The diffusion models stay loaded. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| latent | LATENT | — |