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 WanRTStreamingBeforeDenoiseStep
from .decoders import WanRTDecodeStep
from .encoders import WanRTStreamingTextEncoderStep
from .denoise import WanRTStreamingDenoiseStep

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

TEXT2VIDEO_BLOCKS = InsertableDict(
    [
        ("text_encoder", WanRTStreamingTextEncoderStep),
        ("before_denoise", WanRTStreamingBeforeDenoiseStep),
        ("denoise", WanRTStreamingDenoiseStep),
        ("decode", WanRTDecodeStep),
    ]
)

ALL_BLOCKS = {
    "text2video": TEXT2VIDEO_BLOCKS,
}


class WanStreamingRTBlocks(SequentialPipelineBlocks):
    block_classes = list(TEXT2VIDEO_BLOCKS.copy().values())
    block_names = list(TEXT2VIDEO_BLOCKS.copy().keys())