modular_blocks.py

# Copyright 2025 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from diffusers.utils import logging
from diffusers.modular_pipelines import SequentialPipelineBlocks
from diffusers.modular_pipelines.modular_pipeline_utils import InsertableDict

from .before_denoise import (
    MatrixGameWanActionInputStep,
    MatrixGameWanPrepareImageMaskLatentsStep,
    MatrixGameWanPrepareLatentsStep,
    MatrixGameWanSetTimestepsStep,
)
from .decoders import MatrixGameWanDecodeStep
from .encoders import MatrixGameWanImageEncoderStep
from .denoise import MatrixGameWanDenoiseStep


logger = logging.get_logger(__name__)  # pylint: disable=invalid-name


class MatrixGameWanBeforeDenoiseStep(SequentialPipelineBlocks):
    block_classes = [
        MatrixGameWanActionInputStep,
        MatrixGameWanSetTimestepsStep,
        MatrixGameWanPrepareLatentsStep,
        MatrixGameWanPrepareImageMaskLatentsStep,
    ]
    block_names = ["action_input", "set_timesteps", "prepare_latents", "prepare_mask_latents"]

    @property
    def description(self):
        return (
            "Before denoise step that prepare the inputs for the denoise step.\n"
            + "This is a sequential pipeline blocks:\n"
            + " - `MatrixGameWanInputStep` is used to adjust the batch size of the model inputs\n"
            + " - `MatrixGameWanSetTimestepsStep` is used to set the timesteps\n"
            + " - `MatrixGameWanPrepareLatentsStep` is used to prepare the latents\n"
        )

ACTION2VIDEO_BLOCKS = InsertableDict(
    [
        ("action_input", MatrixGameWanActionInputStep),
        ("image_encoder", MatrixGameWanImageEncoderStep),
        ("set_timesteps", MatrixGameWanSetTimestepsStep),
        ("prepare_latents", MatrixGameWanPrepareLatentsStep),
        ("prepare_masked_latents", MatrixGameWanPrepareImageMaskLatentsStep),
        ("denoise", MatrixGameWanDenoiseStep),
        ("decode", MatrixGameWanDecodeStep),
    ]
)

ALL_BLOCKS = {
    "action2video": ACTION2VIDEO_BLOCKS,
}