Learned latent super-resolution for MiniMax-H3 video latents.
The released upscaler is a pure-3D convolutional resizer trained on H3's 24-channel VAE latents: it lifts a latent to a target spatial size without a decode/encode round trip through the ~5B-parameter H3 VAE. Weights come from LBH-123-AI/Minimax_h3_latent_Upscaler and are a plain state_dict, so the module layout below reproduces the checkpoint's parameter names exactly.
The network works in a space one normalization below the pipeline latent. A vLLM-Omni H3 latent is already normalized -- :class:MiniMaxH3VideoVAE denormalizes at decode time -- and the reference ComfyUI node applies the VAE's latents_mean / latents_std on top of a latent in that same convention, so the upscaler was trained on the doubly-normalized tensor. Feeding it the pipeline latent directly inflates the output by roughly 5x (measured: output std 5.4 against an input std of 1.0), which decodes as a magenta grid at one tile per latent cell. :meth:MiniMaxH3LatentUpscaler.upscale therefore normalizes in and denormalizes out, exactly as the reference node does.
dataclass ¶
How much of the sigma schedule a second denoise pass re-runs.
Bases: Module
The released pure-3D latent resizer.
in_blocks run at the source resolution, a trilinear interpolation moves the feature volume to the target size, and out_blocks refine it there. The requested scale enters every residual block through a two-layer embedding of scale - 1.
instance-attribute ¶
dataclass ¶
Bases: Module
Serving wrapper around :class:MiniMaxH3LatentResizer3D.
Owns the temporal chunking that keeps long clips inside VRAM and the residency policy that keeps the extra ~700MB off the device between requests.
instance-attribute ¶
upscale(
latent: Tensor, target: MiniMaxH3LatentUpscaleTarget
) -> Tensor
Upscale a normalized [B, 24, T, H, W] H3 latent to target.
dataclass ¶
Shape of a released latent upscaler, recovered from its state_dict.
Bases: ValueError
A latent upscaler artifact that cannot be served.
detect_minimax_h3_upscaler_arch(
state_dict: Mapping[str, Tensor],
) -> MiniMaxH3LatentUpscalerArch
Recover the block layout of a released upscaler from its tensors.
load_minimax_h3_latent_upscaler(
path: str | Path,
*,
device: device,
dtype: dtype,
latents_mean: Sequence[float],
latents_std: Sequence[float],
chunk_frames: int = 0,
chunk_overlap: int | None = None,
resident: bool = False,
) -> MiniMaxH3LatentUpscaler
Build a serving-ready upscaler from a released checkpoint.
parse_minimax_h3_latent_refine_request(
value,
) -> MiniMaxH3LatentRefineSpec | None
Normalize extra_args['latent_refine'] into a refine spec.
Accepts a bare strength (0.4), false/null to opt out of a server-side default, or {"strength": 0.4}.
Normalize extra_args['latent_upscale'] into resolver keywords.
Accepts a bare multiplier (2.0), false/null to opt out of a server-side default, or an object naming one sizing mode: {"scale": 2}, {"width": 2688, "height": 1536} or {"megapixels": 4}, each optionally with align.
resolve_minimax_h3_latent_upscale_target(
*,
latent_height: int,
latent_width: int,
scale: float | None = None,
height: int | None = None,
width: int | None = None,
megapixels: float | None = None,
align: int = 32,
) -> MiniMaxH3LatentUpscaleTarget
Resolve one of the three sizing modes into latent dimensions.
scale multiplies the source size; height/width name the target in pixels; megapixels names a total pixel budget and keeps the aspect ratio. For the two size-based modes the network still needs a single scale hint, which is the mean of the per-axis ratios -- what the reference node feeds the same weights. Targets snap to align pixels and then to the VAE's 16px cell.
resolve_minimax_h3_latent_upscaler(
od_config,
*,
device: device,
latent_stats: Callable[
[], tuple[Sequence[float], Sequence[float]]
],
) -> MiniMaxH3LatentUpscaler | None
Build the upscaler declared by --additional-config, if any.
latent_stats yields the VAE's per-channel latents_mean / latents_std and is called only once a checkpoint is configured, so a deployment without this stage never reaches for them.
Recognized keys: latent_upscaler_path (required to enable the stage), latent_upscaler_dtype, latent_upscaler_chunk_frames (0 disables temporal chunking) and latent_upscaler_resident (keep the weights on the device between requests instead of parking them in host memory).