happyz
/
Fooocus
mirror of https://github.com/lllyasviel/Fooocus.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge 59466e3068 into ae05379cc9

This commit is contained in:
monster29000 2025-09-11 20:43:01 +05:30 committed by GitHub
parent ae05379cc9 59466e3068
commit 3fffb37c03
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
18 changed files with 72 additions and 72 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
experiments_mask_generation.py
View File

@ -6,7 +6,7 @@ from PIL import Image
from extras.inpaint_mask import SAMOptions, generate_mask_from_image
original_image = Image.open('cat.webp')
image = np.array(original_image, dtype=np.uint8)
image = np.asarray(original_image, dtype=np.uint8)
sam_options = SAMOptions(
dino_prompt='eye',

24
extras/facexlib/detection/align_trans.py
View File

@ -49,12 +49,12 @@ def get_reference_facial_points(output_size=None, inner_padding_factor=0.0, oute
inner_padding_factor))
Returns:
----------
@reference_5point: 5x2 np.array
@reference_5point: 5x2 np.asarray
each row is a pair of transformed coordinates (x, y)
"""
tmp_5pts = np.array(REFERENCE_FACIAL_POINTS)
tmp_crop_size = np.array(DEFAULT_CROP_SIZE)
tmp_5pts = np.asarray(REFERENCE_FACIAL_POINTS)
tmp_crop_size = np.asarray(DEFAULT_CROP_SIZE)
# 0) make the inner region a square
if default_square:
@ -79,7 +79,7 @@ def get_reference_facial_points(output_size=None, inner_padding_factor=0.0, oute
if ((inner_padding_factor > 0 or outer_padding[0] > 0 or outer_padding[1] > 0) and output_size is None):
output_size = tmp_crop_size * \
(1 + inner_padding_factor * 2).astype(np.int32)
output_size += np.array(outer_padding)
output_size += np.asarray(outer_padding)
if not (outer_padding[0] < output_size[0] and outer_padding[1] < output_size[1]):
raise FaceWarpException('Not (outer_padding[0] < output_size[0] and outer_padding[1] < output_size[1])')
@ -90,7 +90,7 @@ def get_reference_facial_points(output_size=None, inner_padding_factor=0.0, oute
tmp_crop_size += np.round(size_diff).astype(np.int32)
# 2) resize the padded inner region
size_bf_outer_pad = np.array(output_size) - np.array(outer_padding) * 2
size_bf_outer_pad = np.asarray(output_size) - np.asarray(outer_padding) * 2
if size_bf_outer_pad[0] * tmp_crop_size[1] != size_bf_outer_pad[1] * tmp_crop_size[0]:
raise FaceWarpException('Must have (output_size - outer_padding)'
@ -103,7 +103,7 @@ def get_reference_facial_points(output_size=None, inner_padding_factor=0.0, oute
tmp_crop_size = size_bf_outer_pad
# 3) add outer_padding to make output_size
reference_5point = tmp_5pts + np.array(outer_padding)
reference_5point = tmp_5pts + np.asarray(outer_padding)
tmp_crop_size = output_size
return reference_5point
@ -116,13 +116,13 @@ def get_affine_transform_matrix(src_pts, dst_pts):
get affine transform matrix 'tfm' from src_pts to dst_pts
Parameters:
----------
@src_pts: Kx2 np.array
@src_pts: Kx2 np.asarray
source points matrix, each row is a pair of coordinates (x, y)
@dst_pts: Kx2 np.array
@dst_pts: Kx2 np.asarray
destination points matrix, each row is a pair of coordinates (x, y)
Returns:
----------
@tfm: 2x3 np.array
@tfm: 2x3 np.asarray
transform matrix from src_pts to dst_pts
"""
@ -149,17 +149,17 @@ def warp_and_crop_face(src_img, facial_pts, reference_pts=None, crop_size=(96, 1
apply affine transform 'trans' to uv
Parameters:
----------
@src_img: 3x3 np.array
@src_img: 3x3 np.asarray
input image
@facial_pts: could be
1)a list of K coordinates (x,y)
or
2) Kx2 or 2xK np.array
2) Kx2 or 2xK np.asarray
each row or col is a pair of coordinates (x, y)
@reference_pts: could be
1) a list of K coordinates (x,y)
or
2) Kx2 or 2xK np.array
2) Kx2 or 2xK np.asarray
each row or col is a pair of coordinates (x, y)
or
3) None

44
extras/facexlib/detection/matlab_cp2tform.py
View File

@ -18,14 +18,14 @@ def tformfwd(trans, uv):
Parameters:
----------
@trans: 3x3 np.array
@trans: 3x3 np.asarray
transform matrix
@uv: Kx2 np.array
@uv: Kx2 np.asarray
each row is a pair of coordinates (x, y)
Returns:
----------
@xy: Kx2 np.array
@xy: Kx2 np.asarray
each row is a pair of transformed coordinates (x, y)
"""
uv = np.hstack((uv, np.ones((uv.shape[0], 1))))
@ -42,14 +42,14 @@ def tforminv(trans, uv):
Parameters:
----------
@trans: 3x3 np.array
@trans: 3x3 np.asarray
transform matrix
@uv: Kx2 np.array
@uv: Kx2 np.asarray
each row is a pair of coordinates (x, y)
Returns:
----------
@xy: Kx2 np.array
@xy: Kx2 np.asarray
each row is a pair of inverse-transformed coordinates (x, y)
"""
Tinv = inv(trans)
@ -84,9 +84,9 @@ def findNonreflectiveSimilarity(uv, xy, options=None):
tx = r[2]
ty = r[3]
Tinv = np.array([[sc, -ss, 0], [ss, sc, 0], [tx, ty, 1]])
Tinv = np.asarray([[sc, -ss, 0], [ss, sc, 0], [tx, ty, 1]])
T = inv(Tinv)
T[:, 2] = np.array([0, 0, 1])
T[:, 2] = np.asarray([0, 0, 1])
return T, Tinv
@ -94,8 +94,8 @@ def findNonreflectiveSimilarity(uv, xy, options=None):
def findSimilarity(uv, xy, options=None):
options = {'K': 2}
# uv = np.array(uv)
# xy = np.array(xy)
# uv = np.asarray(uv)
# xy = np.asarray(xy)
# Solve for trans1
trans1, trans1_inv = findNonreflectiveSimilarity(uv, xy, options)
@ -109,7 +109,7 @@ def findSimilarity(uv, xy, options=None):
trans2r, trans2r_inv = findNonreflectiveSimilarity(uv, xyR, options)
# manually reflect the tform to undo the reflection done on xyR
TreflectY = np.array([[-1, 0, 0], [0, 1, 0], [0, 0, 1]])
TreflectY = np.asarray([[-1, 0, 0], [0, 1, 0], [0, 0, 1]])
trans2 = np.dot(trans2r, TreflectY)
@ -140,9 +140,9 @@ def get_similarity_transform(src_pts, dst_pts, reflective=True):
Parameters:
----------
@src_pts: Kx2 np.array
@src_pts: Kx2 np.asarray
source points, each row is a pair of coordinates (x, y)
@dst_pts: Kx2 np.array
@dst_pts: Kx2 np.asarray
destination points, each row is a pair of transformed
coordinates (x, y)
@reflective: True or False
@ -153,9 +153,9 @@ def get_similarity_transform(src_pts, dst_pts, reflective=True):
Returns:
----------
@trans: 3x3 np.array
@trans: 3x3 np.asarray
transform matrix from uv to xy
trans_inv: 3x3 np.array
trans_inv: 3x3 np.asarray
inverse of trans, transform matrix from xy to uv
"""
@ -181,12 +181,12 @@ def cvt_tform_mat_for_cv2(trans):
Parameters:
----------
@trans: 3x3 np.array
@trans: 3x3 np.asarray
transform matrix from uv to xy
Returns:
----------
@cv2_trans: 2x3 np.array
@cv2_trans: 2x3 np.asarray
transform matrix from src_pts to dst_pts, could be directly used
for cv2.warpAffine()
"""
@ -209,9 +209,9 @@ def get_similarity_transform_for_cv2(src_pts, dst_pts, reflective=True):
Parameters:
----------
@src_pts: Kx2 np.array
@src_pts: Kx2 np.asarray
source points, each row is a pair of coordinates (x, y)
@dst_pts: Kx2 np.array
@dst_pts: Kx2 np.asarray
destination points, each row is a pair of transformed
coordinates (x, y)
reflective: True or False
@ -222,7 +222,7 @@ def get_similarity_transform_for_cv2(src_pts, dst_pts, reflective=True):
Returns:
----------
@cv2_trans: 2x3 np.array
@cv2_trans: 2x3 np.asarray
transform matrix from src_pts to dst_pts, could be directly used
for cv2.warpAffine()
"""
@ -276,8 +276,8 @@ if __name__ == '__main__':
x = [-1, 0, 4]
y = [-1, -10, 4]
uv = np.array((u, v)).T
xy = np.array((x, y)).T
uv = np.asarray((u, v)).T
xy = np.asarray((x, y)).T
print('\n--->uv:')
print(uv)

12
extras/facexlib/detection/retinaface.py
View File

@ -245,7 +245,7 @@ class RetinaFace(nn.Module):
for landmark in landmarks:
facial5points = [[landmark[2 * j], landmark[2 * j + 1]] for j in range(5)]
warped_face = warp_and_crop_face(np.array(image), facial5points, self.reference, crop_size=(112, 112))
warped_face = warp_and_crop_face(np.asarray(image), facial5points, self.reference, crop_size=(112, 112))
faces.append(warped_face)
return np.concatenate((boxes, landmarks), axis=1), faces
@ -304,15 +304,15 @@ class RetinaFace(nn.Module):
def batched_detect_faces(self, frames, conf_threshold=0.8, nms_threshold=0.4, use_origin_size=True):
"""
Arguments:
frames: a list of PIL.Image, or np.array(shape=[n, h, w, c],
frames: a list of PIL.Image, or np.asarray(shape=[n, h, w, c],
type=np.uint8, BGR format).
conf_threshold: confidence threshold.
nms_threshold: nms threshold.
use_origin_size: whether to use origin size.
Returns:
final_bounding_boxes: list of np.array ([n_boxes, 5],
final_bounding_boxes: list of np.asarray ([n_boxes, 5],
type=np.float32).
final_landmarks: list of np.array ([n_boxes, 10], type=np.float32).
final_landmarks: list of np.asarray ([n_boxes, 10], type=np.float32).
"""
# self.t['forward_pass'].tic()
frames, self.resize = self.batched_transform(frames, use_origin_size)
@ -340,8 +340,8 @@ class RetinaFace(nn.Module):
# ignore low scores
pred, landm = pred[inds, :], landm[inds, :]
if pred.shape[0] == 0:
final_bounding_boxes.append(np.array([], dtype=np.float32))
final_landmarks.append(np.array([], dtype=np.float32))
final_bounding_boxes.append(np.asarray([], dtype=np.float32))
final_landmarks.append(np.asarray([], dtype=np.float32))
continue
# sort

14
extras/facexlib/utils/face_restoration_helper.py
View File

@ -33,12 +33,12 @@ def get_largest_face(det_faces, h, w):
def get_center_face(det_faces, h=0, w=0, center=None):
if center is not None:
center = np.array(center)
center = np.asarray(center)
else:
center = np.array([w / 2, h / 2])
center = np.asarray([w / 2, h / 2])
center_dist = []
for det_face in det_faces:
face_center = np.array([(det_face[0] + det_face[2]) / 2, (det_face[1] + det_face[3]) / 2])
face_center = np.asarray([(det_face[0] + det_face[2]) / 2, (det_face[1] + det_face[3]) / 2])
dist = np.linalg.norm(face_center - center)
center_dist.append(dist)
center_idx = center_dist.index(min(center_dist))
@ -67,10 +67,10 @@ class FaceRestoreHelper(object):
self.face_size = (int(face_size * self.crop_ratio[1]), int(face_size * self.crop_ratio[0]))
if self.template_3points:
self.face_template = np.array([[192, 240], [319, 240], [257, 371]])
self.face_template = np.asarray([[192, 240], [319, 240], [257, 371]])
else:
# standard 5 landmarks for FFHQ faces with 512 x 512
self.face_template = np.array([[192.98138, 239.94708], [318.90277, 240.1936], [256.63416, 314.01935],
self.face_template = np.asarray([[192.98138, 239.94708], [318.90277, 240.1936], [256.63416, 314.01935],
[201.26117, 371.41043], [313.08905, 371.15118]])
self.face_template = self.face_template * (face_size / 512.0)
if self.crop_ratio[0] > 1:
@ -144,9 +144,9 @@ class FaceRestoreHelper(object):
continue
if self.template_3points:
landmark = np.array([[bbox[i], bbox[i + 1]] for i in range(5, 11, 2)])
landmark = np.asarray([[bbox[i], bbox[i + 1]] for i in range(5, 11, 2)])
else:
landmark = np.array([[bbox[i], bbox[i + 1]] for i in range(5, 15, 2)])
landmark = np.asarray([[bbox[i], bbox[i + 1]] for i in range(5, 15, 2)])
self.all_landmarks_5.append(landmark)
self.det_faces.append(bbox[0:5])
if len(self.det_faces) == 0:

10
extras/facexlib/utils/face_utils.py
View File

@ -64,7 +64,7 @@ def align_crop_face_landmarks(img,
transform_size = output_size * 4
# Parse landmarks
lm = np.array(landmarks)
lm = np.asarray(landmarks)
if lm.shape[0] == 5 and lm_type == 'retinaface_5':
eye_left = lm[0]
eye_right = lm[1]
@ -163,7 +163,7 @@ def align_crop_face_landmarks(img,
# Transform use cv2
h_ratio = shrink_ratio[0] / shrink_ratio[1]
dst_h, dst_w = int(transform_size * h_ratio), transform_size
template = np.array([[0, 0], [0, dst_h], [dst_w, dst_h], [dst_w, 0]])
template = np.asarray([[0, 0], [0, dst_h], [dst_w, dst_h], [dst_w, 0]])
# use cv2.LMEDS method for the equivalence to skimage transform
# ref: https://blog.csdn.net/yichxi/article/details/115827338
affine_matrix = cv2.estimateAffinePartial2D(quad, template, method=cv2.LMEDS)[0]
@ -176,11 +176,11 @@ def align_crop_face_landmarks(img,
if return_inverse_affine:
dst_h, dst_w = int(output_size * h_ratio), output_size
template = np.array([[0, 0], [0, dst_h], [dst_w, dst_h], [dst_w, 0]])
template = np.asarray([[0, 0], [0, dst_h], [dst_w, dst_h], [dst_w, 0]])
# use cv2.LMEDS method for the equivalence to skimage transform
# ref: https://blog.csdn.net/yichxi/article/details/115827338
affine_matrix = cv2.estimateAffinePartial2D(
quad_ori, np.array([[0, 0], [0, output_size], [dst_w, dst_h], [dst_w, 0]]), method=cv2.LMEDS)[0]
quad_ori, np.asarray([[0, 0], [0, output_size], [dst_w, dst_h], [dst_w, 0]]), method=cv2.LMEDS)[0]
inverse_affine = cv2.invertAffineTransform(affine_matrix)
else:
inverse_affine = None
@ -234,7 +234,7 @@ if __name__ == '__main__':
bboxes = get_largest_face(bboxes, h, w)[0]
visualize_detection(img_ori, [bboxes], f'tmp/{img_name}_det.png')
landmarks = np.array([[bboxes[i], bboxes[i + 1]] for i in range(5, 15, 2)])
landmarks = np.asarray([[bboxes[i], bboxes[i + 1]] for i in range(5, 15, 2)])
cropped_face, inverse_affine = align_crop_face_landmarks(
img_ori,

4
extras/inpaint_mask.py
View File

@ -104,7 +104,7 @@ def generate_mask_from_image(image: np.ndarray, mask_model: str = 'sam', extras=
draw = ImageDraw.Draw(debug_dino_image)
for box in boxes.numpy():
draw.rectangle(box.tolist(), fill="white")
return np.array(debug_dino_image), dino_detection_count, sam_detection_count, sam_detection_on_mask_count
return np.asarray(debug_dino_image), dino_detection_count, sam_detection_count, sam_detection_on_mask_count
transformed_boxes = sam_predictor.transform.apply_boxes_torch(boxes, image.shape[:2])
masks, _, _ = sam_predictor.predict_torch(
@ -126,5 +126,5 @@ def generate_mask_from_image(image: np.ndarray, mask_model: str = 'sam', extras=
final_mask_tensor = (final_mask_tensor > 0).to('cpu').numpy()
mask_image = np.dstack((final_mask_tensor, final_mask_tensor, final_mask_tensor)) * 255
mask_image = np.array(mask_image, dtype=np.uint8)
mask_image = np.asarray(mask_image, dtype=np.uint8)
return mask_image, dino_detection_count, sam_detection_count, sam_detection_on_mask_count

2
extras/wd14tagger.py
View File

@ -57,7 +57,7 @@ def default_interrogator(image_rgb, threshold=0.35, character_threshold=0.85, ex
square = Image.new("RGB", (height, height), (255, 255, 255))
square.paste(image, ((height-new_size[0])//2, (height-new_size[1])//2))
image = np.array(square).astype(np.float32)
image = np.asarray(square).astype(np.float32)
image = image[:, :, ::-1] # RGB -> BGR
image = np.expand_dims(image, 0)

6
ldm_patched/contrib/external.py
View File

@ -1476,10 +1476,10 @@ class LoadImage:
if i.mode == 'I':
i = i.point(lambda i: i * (1 / 255))
image = i.convert("RGB")
image = np.array(image).astype(np.float32) / 255.0
image = np.asarray(image).astype(np.float32) / 255.0
image = torch.from_numpy(image)[None,]
if 'A' in i.getbands():
mask = np.array(i.getchannel('A')).astype(np.float32) / 255.0
mask = np.asarray(i.getchannel('A')).astype(np.float32) / 255.0
mask = 1. - torch.from_numpy(mask)
else:
mask = torch.zeros((64,64), dtype=torch.float32, device="cpu")
@ -1536,7 +1536,7 @@ class LoadImageMask:
mask = None
c = channel[0].upper()
if c in i.getbands():
mask = np.array(i.getchannel(c)).astype(np.float32) / 255.0
mask = np.asarray(i.getchannel(c)).astype(np.float32) / 255.0
mask = torch.from_numpy(mask)
if c == 'A':
mask = 1. - mask

2
ldm_patched/contrib/external_mask.py
View File

@ -327,7 +327,7 @@ class GrowMask:
def expand_mask(self, mask, expand, tapered_corners):
c = 0 if tapered_corners else 1
kernel = np.array([[c, 1, c],
kernel = np.asarray([[c, 1, c],
[1, 1, 1],
[c, 1, c]])
mask = mask.reshape((-1, mask.shape[-2], mask.shape[-1]))

4
ldm_patched/contrib/external_post_processing.py
View File

@ -154,7 +154,7 @@ class Quantize:
bayer_n = int(math.log2(order))
bayer_matrix = torch.from_numpy(spread * normalized_bayer_matrix(bayer_n) + 0.5)
result = torch.from_numpy(np.array(im).astype(np.float32))
result = torch.from_numpy(np.asarray(im).astype(np.float32))
tw = math.ceil(result.shape[0] / bayer_matrix.shape[0])
th = math.ceil(result.shape[1] / bayer_matrix.shape[1])
tiled_matrix = bayer_matrix.tile(tw, th).unsqueeze(-1)
@ -182,7 +182,7 @@ class Quantize:
order = int(dither.split('-')[-1])
quantized_image = Quantize.bayer(im, pal_im, order)
quantized_array = torch.tensor(np.array(quantized_image.convert("RGB"))).float() / 255
quantized_array = torch.tensor(np.asarray(quantized_image.convert("RGB"))).float() / 255
result[b] = quantized_array
return (result,)

2
ldm_patched/ldm/modules/diffusionmodules/util.py
View File

@ -163,7 +163,7 @@ def betas_for_alpha_bar(num_diffusion_timesteps, alpha_bar, max_beta=0.999):
t1 = i / num_diffusion_timesteps
t2 = (i + 1) / num_diffusion_timesteps
betas.append(min(1 - alpha_bar(t2) / alpha_bar(t1), max_beta))
return np.array(betas)
return np.asarray(betas)
def extract_into_tensor(a, t, x_shape):

2
ldm_patched/ldm/util.py
View File

@ -25,7 +25,7 @@ def log_txt_as_img(wh, xc, size=10):
except UnicodeEncodeError:
print("Cant encode string for logging. Skipping.")
txt = np.array(txt).transpose(2, 0, 1) / 127.5 - 1.0
txt = np.asarray(txt).transpose(2, 0, 1) / 127.5 - 1.0
txts.append(txt)
txts = np.stack(txts)
txts = torch.tensor(txts)

2
ldm_patched/modules/utils.py
View File

@ -374,7 +374,7 @@ def bislerp(samples, width, height):
def lanczos(samples, width, height):
images = [Image.fromarray(np.clip(255. * image.movedim(0, -1).cpu().numpy(), 0, 255).astype(np.uint8)) for image in samples]
images = [image.resize((width, height), resample=Image.Resampling.LANCZOS) for image in images]
images = [torch.from_numpy(np.array(image).astype(np.float32) / 255.0).movedim(-1, 0) for image in images]
images = [torch.from_numpy(np.asarray(image).astype(np.float32) / 255.0).movedim(-1, 0) for image in images]
result = torch.stack(images)
return result.to(samples.device, samples.dtype)

2
ldm_patched/pfn/architecture/SCUNet.py
View File

@ -149,7 +149,7 @@ class WMSA(nn.Module):
def relative_embedding(self):
cord = torch.tensor(
np.array(
np.asarray(
[
[i, j]
for i in range(self.window_size)

6
modules/gradio_hijack.py
View File

@ -242,7 +242,7 @@ class Image(
if self.type == "pil":
return im
elif self.type == "numpy":
return np.array(im)
return np.asarray(im)
elif self.type == "filepath":
path = self.pil_to_temp_file(
im, dir=self.DEFAULT_TEMP_DIR, format=fmt or "png"
@ -349,7 +349,7 @@ class Image(
x = processing_utils.decode_base64_to_image(x)
if self.shape is not None:
x = processing_utils.resize_and_crop(x, self.shape)
resized_and_cropped_image = np.array(x)
resized_and_cropped_image = np.asarray(x)
try:
from skimage.segmentation import slic
except (ImportError, ModuleNotFoundError) as err:
@ -418,7 +418,7 @@ class Image(
x = processing_utils.decode_base64_to_image(x)
if self.shape is not None:
x = processing_utils.resize_and_crop(x, self.shape)
x = np.array(x)
x = np.asarray(x)
output_scores = np.zeros((x.shape[0], x.shape[1]))
for score, mask in zip(scores, masks):

2
modules/inpaint_worker.py
View File

@ -26,7 +26,7 @@ current_task = None
def box_blur(x, k):
x = Image.fromarray(x)
x = x.filter(ImageFilter.BoxBlur(k))
return np.array(x)
return np.asarray(x)
def max_filter_opencv(x, ksize=3):

4
modules/util.py
View File

@ -40,7 +40,7 @@ def erode_or_dilate(x, k):
def resample_image(im, width, height):
im = Image.fromarray(im)
im = im.resize((int(width), int(height)), resample=LANCZOS)
return np.array(im)
return np.asarray(im)
def resize_image(im, width, height, resize_mode=1):
@ -98,7 +98,7 @@ def resize_image(im, width, height, resize_mode=1):
res.paste(resized.resize((fill_width, height), box=(0, 0, 0, height)), box=(0, 0))
res.paste(resized.resize((fill_width, height), box=(resized.width, 0, resized.width, height)), box=(fill_width + src_w, 0))
return np.array(res)
return np.asarray(res)
def get_shape_ceil(h, w):