theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-23 17:38:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

[NPU]:Replace 'cuda' in the project with abstract interfaces

Browse Source
This commit is contained in:
feng0w0
2026-01-15 20:33:01 +08:00
parent f4d06ce3fc
commit 209a350c0f
18 changed files with 86 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
diffsynth/pipelines/wan_video.py
View File

@@ -11,6 +11,7 @@ from typing import Optional
from typing_extensions import Literal
from transformers import Wav2Vec2Processor
from ..core.device.npu_compatible_device import get_device_type
from ..diffusion import FlowMatchScheduler
from ..core import ModelConfig, gradient_checkpoint_forward
from ..diffusion.base_pipeline import BasePipeline, PipelineUnit
@@ -30,7 +31,7 @@ from ..models.longcat_video_dit import LongCatVideoTransformer3DModel
class WanVideoPipeline(BasePipeline):
def __init__(self, device="cuda", torch_dtype=torch.bfloat16):
def __init__(self, device=get_device_type(), torch_dtype=torch.bfloat16):
super().__init__(
device=device, torch_dtype=torch_dtype,
height_division_factor=16, width_division_factor=16, time_division_factor=4, time_division_remainder=1
@@ -98,7 +99,7 @@ class WanVideoPipeline(BasePipeline):
@staticmethod
def from_pretrained(
torch_dtype: torch.dtype = torch.bfloat16,
device: Union[str, torch.device] = "cuda",
device: Union[str, torch.device] = get_device_type(),
model_configs: list[ModelConfig] = [],
tokenizer_config: ModelConfig = ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="google/umt5-xxl/"),
audio_processor_config: ModelConfig = None,
@@ -960,7 +961,7 @@ class WanVideoUnit_AnimateInpaint(PipelineUnit):
onload_model_names=("vae",)
)
def get_i2v_mask(self, lat_t, lat_h, lat_w, mask_len=1, mask_pixel_values=None, device="cuda"):
def get_i2v_mask(self, lat_t, lat_h, lat_w, mask_len=1, mask_pixel_values=None, device=get_device_type()):
if mask_pixel_values is None:
msk = torch.zeros(1, (lat_t-1) * 4 + 1, lat_h, lat_w, device=device)
else: