"""The denoising half of a **split** MiniMax-H3 deployment.

MiniMax-H3 is ~196 GiB in bfloat16 and a ZeroGPU Space is evicted at 150 GB of storage, so `MiniMaxH3Blocks` is cut
at its `text_encoder` step: the 62.14 GiB Qwen3-VL conditioner runs in its own Space and everything else — the
distilled transformer and the two autoencoders — runs here. `prompt_embeds` + `text_token_tags` is the whole wire
format between the two halves.

Dropping the `text_encoder` step drops the three components it declares, so `load_components` resolves
`transformer` / `vae` / `audio_vae` / the two schedulers out of the checkpoint's `modular_model_index.json` and never
fetches the conditioner.

`resize` runs on **both** sides: it owns no pretrained component (PIL and arithmetic), and each half needs the canvas
— the conditioner to build its vision blocks, this half to lay out the latents. The caller aligns the frame count to
`17 * n + 5` before the call.

Adapted from `multimodalart/minimax-h3`, trimmed to the `t2va` (text → video + audio) branch this Space serves.
"""

from diffusers.modular_pipelines.minimax_h3.decoders import MiniMaxH3AfterDenoiseStep
from diffusers.modular_pipelines.minimax_h3.modular_blocks_minimax_h3 import (
    MiniMaxH3AutoKeyframeVaeEncoderStep,
    MiniMaxH3AutoResizeStep,
    MiniMaxH3CoreDenoiseStep,
    MiniMaxH3DecodeStep,
    _generation_outputs,
)
from diffusers.modular_pipelines.modular_pipeline import SequentialPipelineBlocks


class MiniMaxH3GeneratorBlocks(SequentialPipelineBlocks):
    """The denoising half of a split MiniMax-H3: `MiniMaxH3Blocks` with its `text_encoder` step removed."""

    model_name = "minimax-h3"
    block_classes = [
        MiniMaxH3AutoResizeStep,
        MiniMaxH3AutoKeyframeVaeEncoderStep,
        MiniMaxH3CoreDenoiseStep,
        MiniMaxH3AfterDenoiseStep,
        MiniMaxH3DecodeStep,
    ]
    block_names = ["resize", "vae_encoder", "denoise", "after_denoise", "decode"]

    @property
    def description(self):
        return (
            "The denoising half of a split MiniMax-H3 deployment: the `t2va` branch of `MiniMaxH3Blocks` without its "
            "text-encoder step, so `prompt_embeds` and `text_token_tags` come in as inputs and the 62.14 GiB Qwen3-VL "
            "conditioner is never loaded here."
        )

    @property
    def outputs(self):
        return _generation_outputs()