SunderAli17 commited on
Commit
512dfd4
1 Parent(s): c244c09

Delete toonmage/fluxpipeline.py

Browse files
Files changed (1) hide show
  1. toonmage/fluxpipeline.py +0 -188
toonmage/fluxpipeline.py DELETED
@@ -1,188 +0,0 @@
1
- import gc
2
-
3
- import cv2
4
- import insightface
5
- import torch
6
- import torch.nn as nn
7
- from basicsr.utils import img2tensor, tensor2img
8
- from facexlib.parsing import init_parsing_model
9
- from facexlib.utils.face_restoration_helper import FaceRestoreHelper
10
- from huggingface_hub import hf_hub_download, snapshot_download
11
- from insightface.app import FaceAnalysis
12
- from safetensors.torch import load_file
13
- from torchvision.transforms import InterpolationMode
14
- from torchvision.transforms.functional import normalize, resize
15
-
16
- from eva_clip import create_model_and_transforms
17
- from eva_clip.constants import OPENAI_DATASET_MEAN, OPENAI_DATASET_STD
18
- from toonmage.fluxencoders import IDFormer, PerceiverAttentionCA
19
-
20
-
21
- class ToonMagePipeline(nn.Module):
22
- def __init__(self, dit, device, weight_dtype=torch.bfloat16, *args, **kwargs):
23
- super().__init__()
24
- self.device = device
25
- self.weight_dtype = weight_dtype
26
- double_interval = 2
27
- single_interval = 4
28
-
29
- # init encoder
30
- self.pulid_encoder = IDFormer().to(self.device, self.weight_dtype)
31
-
32
- num_ca = 19 // double_interval + 38 // single_interval
33
- if 19 % double_interval != 0:
34
- num_ca += 1
35
- if 38 % single_interval != 0:
36
- num_ca += 1
37
- self.pulid_ca = nn.ModuleList([
38
- PerceiverAttentionCA().to(self.device, self.weight_dtype) for _ in range(num_ca)
39
- ])
40
-
41
- dit.pulid_ca = self.pulid_ca
42
- dit.toonmage_double_interval = double_interval
43
- dit.toonmage_single_interval = single_interval
44
-
45
- # preprocessors
46
- # face align and parsing
47
- self.face_helper = FaceRestoreHelper(
48
- upscale_factor=1,
49
- face_size=512,
50
- crop_ratio=(1, 1),
51
- det_model='retinaface_resnet50',
52
- save_ext='png',
53
- device=self.device,
54
- )
55
- self.face_helper.face_parse = None
56
- self.face_helper.face_parse = init_parsing_model(model_name='bisenet', device=self.device)
57
- # clip-vit backbone
58
- model, _, _ = create_model_and_transforms('EVA02-CLIP-L-14-336', 'eva_clip', force_custom_clip=True)
59
- model = model.visual
60
- self.clip_vision_model = model.to(self.device, dtype=self.weight_dtype)
61
- eva_transform_mean = getattr(self.clip_vision_model, 'image_mean', OPENAI_DATASET_MEAN)
62
- eva_transform_std = getattr(self.clip_vision_model, 'image_std', OPENAI_DATASET_STD)
63
- if not isinstance(eva_transform_mean, (list, tuple)):
64
- eva_transform_mean = (eva_transform_mean,) * 3
65
- if not isinstance(eva_transform_std, (list, tuple)):
66
- eva_transform_std = (eva_transform_std,) * 3
67
- self.eva_transform_mean = eva_transform_mean
68
- self.eva_transform_std = eva_transform_std
69
- # antelopev2
70
- snapshot_download('DIAMONIK7777/antelopev2', local_dir='models/antelopev2')
71
- self.app = FaceAnalysis(
72
- name='antelopev2', root='.', providers=['CPUExecutionProvider']
73
- )
74
- self.app.prepare(ctx_id=0, det_size=(640, 640))
75
- self.handler_ante = insightface.model_zoo.get_model('models/antelopev2/glintr100.onnx', providers=['CPUExecutionProvider'])
76
- self.handler_ante.prepare(ctx_id=0)
77
-
78
- gc.collect()
79
- torch.cuda.empty_cache()
80
-
81
- # self.load_pretrain()
82
-
83
- # other configs
84
- self.debug_img_list = []
85
-
86
- def load_pretrain(self, pretrain_path=None):
87
- hf_hub_download('SunderAli17/SAK', 'toonmage_flux_v2.safetensors', local_dir ='models')
88
- ckpt_path = 'models/toonmage_flux_v2.safetensors'
89
- if pretrain_path is not None:
90
- ckpt_path = pretrain_path
91
- state_dict = load_file(ckpt_path)
92
- state_dict_dict = {}
93
- for k, v in state_dict.items():
94
- module = k.split('.')[0]
95
- state_dict_dict.setdefault(module, {})
96
- new_k = k[len(module) + 1:]
97
- state_dict_dict[module][new_k] = v
98
-
99
- for module in state_dict_dict:
100
- print(f'loading from {module}')
101
- getattr(self, module).load_state_dict(state_dict_dict[module], strict=True)
102
-
103
- del state_dict
104
- del state_dict_dict
105
-
106
- def to_gray(self, img):
107
- x = 0.299 * img[:, 0:1] + 0.587 * img[:, 1:2] + 0.114 * img[:, 2:3]
108
- x = x.repeat(1, 3, 1, 1)
109
- return x
110
-
111
- def get_id_embedding(self, image, cal_uncond=False):
112
- """
113
- Args:
114
- image: numpy rgb image, range [0, 255]
115
- """
116
- self.face_helper.clean_all()
117
- self.debug_img_list = []
118
- image_bgr = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
119
- # get antelopev2 embedding
120
- # for k in self.app.models.keys():
121
- # self.app.models[k].session.set_providers(['CUDAExecutionProvider'])
122
- face_info = self.app.get(image_bgr)
123
- if len(face_info) > 0:
124
- face_info = sorted(face_info, key=lambda x: (x['bbox'][2] - x['bbox'][0]) * (x['bbox'][3] - x['bbox'][1]))[
125
- -1
126
- ] # only use the maximum face
127
- id_ante_embedding = face_info['embedding']
128
- self.debug_img_list.append(
129
- image[
130
- int(face_info['bbox'][1]) : int(face_info['bbox'][3]),
131
- int(face_info['bbox'][0]) : int(face_info['bbox'][2]),
132
- ]
133
- )
134
- else:
135
- id_ante_embedding = None
136
-
137
- # using facexlib to detect and align face
138
- self.face_helper.read_image(image_bgr)
139
- self.face_helper.get_face_landmarks_5(only_center_face=True)
140
- self.face_helper.align_warp_face()
141
- if len(self.face_helper.cropped_faces) == 0:
142
- raise RuntimeError('facexlib align face fail')
143
- align_face = self.face_helper.cropped_faces[0]
144
- # incase insightface didn't detect face
145
- if id_ante_embedding is None:
146
- print('fail to detect face using insightface, extract embedding on align face')
147
- # self.handler_ante.session.set_providers(['CUDAExecutionProvider'])
148
- id_ante_embedding = self.handler_ante.get_feat(align_face)
149
-
150
- id_ante_embedding = torch.from_numpy(id_ante_embedding).to(self.device, self.weight_dtype)
151
- if id_ante_embedding.ndim == 1:
152
- id_ante_embedding = id_ante_embedding.unsqueeze(0)
153
-
154
- # parsing
155
- input = img2tensor(align_face, bgr2rgb=True).unsqueeze(0) / 255.0
156
- input = input.to(self.device)
157
- parsing_out = self.face_helper.face_parse(normalize(input, [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]))[0]
158
- parsing_out = parsing_out.argmax(dim=1, keepdim=True)
159
- bg_label = [0, 16, 18, 7, 8, 9, 14, 15]
160
- bg = sum(parsing_out == i for i in bg_label).bool()
161
- white_image = torch.ones_like(input)
162
- # only keep the face features
163
- face_features_image = torch.where(bg, white_image, self.to_gray(input))
164
- self.debug_img_list.append(tensor2img(face_features_image, rgb2bgr=False))
165
-
166
- # transform img before sending to eva-clip-vit
167
- face_features_image = resize(face_features_image, self.clip_vision_model.image_size, InterpolationMode.BICUBIC)
168
- face_features_image = normalize(face_features_image, self.eva_transform_mean, self.eva_transform_std)
169
- id_cond_vit, id_vit_hidden = self.clip_vision_model(
170
- face_features_image.to(self.weight_dtype), return_all_features=False, return_hidden=True, shuffle=False
171
- )
172
- id_cond_vit_norm = torch.norm(id_cond_vit, 2, 1, True)
173
- id_cond_vit = torch.div(id_cond_vit, id_cond_vit_norm)
174
-
175
- id_cond = torch.cat([id_ante_embedding, id_cond_vit], dim=-1)
176
-
177
- id_embedding = self.pulid_encoder(id_cond, id_vit_hidden)
178
-
179
- if not cal_uncond:
180
- return id_embedding, None
181
-
182
- id_uncond = torch.zeros_like(id_cond)
183
- id_vit_hidden_uncond = []
184
- for layer_idx in range(0, len(id_vit_hidden)):
185
- id_vit_hidden_uncond.append(torch.zeros_like(id_vit_hidden[layer_idx]))
186
- uncond_id_embedding = self.pulid_encoder(id_uncond, id_vit_hidden_uncond)
187
-
188
- return id_embedding, uncond_id_embedding