File size: 2,534 Bytes
5178ef1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
# 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,
}
|