li-lizhe
2176b74083
Several nodes only exposed a 'cuda'/'cpu' device dropdown, forcing users on any other ComfyUI-supported accelerator (Ascend NPU, XPU, MPS) to run on CPU even when their device is available. Add a shared DEVICE_LIST_OPTIONS constant and get_device() helper in imagefunc.py that resolve 'auto' to ComfyUI's default device, and use them in the VITMatte-based matting nodes and the VQA model loader so non-CUDA devices can be selected from the UI.
84 lines
3.5 KiB
Python
84 lines
3.5 KiB
Python
import torch
|
|
from PIL import Image
|
|
from .imagefunc import log, tensor2pil, pil2tensor, image2mask, mask2image, RMBG, RGB2RGBA, mask_edge_detail
|
|
from .imagefunc import guided_filter_alpha, histogram_remap, generate_VITMatte, generate_VITMatte_trimap
|
|
from .imagefunc import DEVICE_LIST_OPTIONS
|
|
|
|
|
|
|
|
class RmBgUltraV2:
|
|
def __init__(self):
|
|
self.NODE_NAME = 'RmBgUltra V2'
|
|
|
|
@classmethod
|
|
def INPUT_TYPES(cls):
|
|
|
|
method_list = ['VITMatte', 'VITMatte(local)', 'vitmatte-base-composition-1k', 'PyMatting', 'GuidedFilter', ]
|
|
device_list = DEVICE_LIST_OPTIONS
|
|
return {
|
|
"required": {
|
|
"image": ("IMAGE",),
|
|
"detail_method": (method_list,),
|
|
"detail_erode": ("INT", {"default": 6, "min": 1, "max": 255, "step": 1}),
|
|
"detail_dilate": ("INT", {"default": 6, "min": 1, "max": 255, "step": 1}),
|
|
"black_point": ("FLOAT", {"default": 0.01, "min": 0.01, "max": 0.98, "step": 0.01, "display": "slider"}),
|
|
"white_point": ("FLOAT", {"default": 0.99, "min": 0.02, "max": 0.99, "step": 0.01, "display": "slider"}),
|
|
"process_detail": ("BOOLEAN", {"default": True}),
|
|
"device": (device_list,),
|
|
"max_megapixels": ("FLOAT", {"default": 2.0, "min": 1, "max": 999, "step": 0.1}),
|
|
},
|
|
"optional": {
|
|
}
|
|
}
|
|
|
|
RETURN_TYPES = ("IMAGE", "MASK", )
|
|
RETURN_NAMES = ("image", "mask", )
|
|
FUNCTION = "rmbg_ultra_v2"
|
|
CATEGORY = '😺dzNodes/LayerMask'
|
|
|
|
def rmbg_ultra_v2(self, image, detail_method, detail_erode, detail_dilate,
|
|
black_point, white_point, process_detail, device, max_megapixels):
|
|
ret_images = []
|
|
ret_masks = []
|
|
|
|
if detail_method == 'VITMatte(local)':
|
|
local_files_only = True
|
|
else:
|
|
local_files_only = False
|
|
|
|
for i in image:
|
|
i = torch.unsqueeze(i, 0)
|
|
i = pil2tensor(tensor2pil(i).convert('RGB'))
|
|
orig_image = tensor2pil(i).convert('RGB')
|
|
_mask = RMBG(orig_image)
|
|
_mask = pil2tensor(_mask)
|
|
|
|
detail_range = detail_erode + detail_dilate
|
|
if process_detail:
|
|
if detail_method == 'GuidedFilter':
|
|
_mask = guided_filter_alpha(i, _mask, detail_range // 6 + 1)
|
|
_mask = tensor2pil(histogram_remap(_mask, black_point, white_point))
|
|
elif detail_method == 'PyMatting':
|
|
_mask = tensor2pil(mask_edge_detail(i, _mask, detail_range // 8 + 1, black_point, white_point))
|
|
else:
|
|
_trimap = generate_VITMatte_trimap(_mask, detail_erode, detail_dilate)
|
|
_mask = generate_VITMatte(orig_image, _trimap, local_files_only=local_files_only, device=device, max_megapixels=max_megapixels, method=detail_method)
|
|
_mask = tensor2pil(histogram_remap(pil2tensor(_mask), black_point, white_point))
|
|
else:
|
|
_mask = mask2image(_mask)
|
|
|
|
ret_image = RGB2RGBA(orig_image, _mask.convert('L'))
|
|
ret_images.append(pil2tensor(ret_image))
|
|
ret_masks.append(image2mask(_mask))
|
|
|
|
log(f"{self.NODE_NAME} Processed {len(ret_images)} image(s).", message_type='finish')
|
|
return (torch.cat(ret_images, dim=0), torch.cat(ret_masks, dim=0),)
|
|
|
|
NODE_CLASS_MAPPINGS = {
|
|
"LayerMask: RmBgUltra V2": RmBgUltraV2,
|
|
}
|
|
|
|
NODE_DISPLAY_NAME_MAPPINGS = {
|
|
"LayerMask: RmBgUltra V2": "LayerMask: RmBgUltra V2",
|
|
}
|