colomi
0eb61f3e60
包含： - hair_service_sd: 换发型/换发色算法服务 (端口 8801) - photo_service: LoRA 训练调度服务 (端口 32678) - stable-diffusion-webui: SD WebUI 推理服务 (端口 57860) - kohya_ss_home: 训练环境代码 - meidaojia: 监控测试脚本 - setup.sh: 一键部署脚本 (conda环境恢复 + 配置生成 + 完整性检查) - start_all_services.sh: 启动3个服务 - configure.ini.template: 路径模板化 (BASE_DIR自动推导) - conda_envs/py310.yml: py310 环境定义 大文件 (weights/, models/, data/, conda_envs/*.tar.gz 等) 通过 .gitignore 排除， 由网盘单独上传。
72 lines
2.5 KiB
Python
Executable File
72 lines
2.5 KiB
Python
Executable File
import open_clip.tokenizer
|
|
import torch
|
|
|
|
from modules import sd_hijack_clip, devices
|
|
from modules.shared import opts
|
|
|
|
tokenizer = open_clip.tokenizer._tokenizer
|
|
|
|
|
|
class FrozenOpenCLIPEmbedderWithCustomWords(sd_hijack_clip.FrozenCLIPEmbedderWithCustomWordsBase):
|
|
def __init__(self, wrapped, hijack):
|
|
super().__init__(wrapped, hijack)
|
|
|
|
self.comma_token = [v for k, v in tokenizer.encoder.items() if k == ',</w>'][0]
|
|
self.id_start = tokenizer.encoder["<start_of_text>"]
|
|
self.id_end = tokenizer.encoder["<end_of_text>"]
|
|
self.id_pad = 0
|
|
|
|
def tokenize(self, texts):
|
|
assert not opts.use_old_emphasis_implementation, 'Old emphasis implementation not supported for Open Clip'
|
|
|
|
tokenized = [tokenizer.encode(text) for text in texts]
|
|
|
|
return tokenized
|
|
|
|
def encode_with_transformers(self, tokens):
|
|
# set self.wrapped.layer_idx here according to opts.CLIP_stop_at_last_layers
|
|
z = self.wrapped.encode_with_transformer(tokens)
|
|
|
|
return z
|
|
|
|
def encode_embedding_init_text(self, init_text, nvpt):
|
|
ids = tokenizer.encode(init_text)
|
|
ids = torch.asarray([ids], device=devices.device, dtype=torch.int)
|
|
embedded = self.wrapped.model.token_embedding.wrapped(ids).squeeze(0)
|
|
|
|
return embedded
|
|
|
|
|
|
class FrozenOpenCLIPEmbedder2WithCustomWords(sd_hijack_clip.FrozenCLIPEmbedderWithCustomWordsBase):
|
|
def __init__(self, wrapped, hijack):
|
|
super().__init__(wrapped, hijack)
|
|
|
|
self.comma_token = [v for k, v in tokenizer.encoder.items() if k == ',</w>'][0]
|
|
self.id_start = tokenizer.encoder["<start_of_text>"]
|
|
self.id_end = tokenizer.encoder["<end_of_text>"]
|
|
self.id_pad = 0
|
|
|
|
def tokenize(self, texts):
|
|
assert not opts.use_old_emphasis_implementation, 'Old emphasis implementation not supported for Open Clip'
|
|
|
|
tokenized = [tokenizer.encode(text) for text in texts]
|
|
|
|
return tokenized
|
|
|
|
def encode_with_transformers(self, tokens):
|
|
d = self.wrapped.encode_with_transformer(tokens)
|
|
z = d[self.wrapped.layer]
|
|
|
|
pooled = d.get("pooled")
|
|
if pooled is not None:
|
|
z.pooled = pooled
|
|
|
|
return z
|
|
|
|
def encode_embedding_init_text(self, init_text, nvpt):
|
|
ids = tokenizer.encode(init_text)
|
|
ids = torch.asarray([ids], device=devices.device, dtype=torch.int)
|
|
embedded = self.wrapped.model.token_embedding.wrapped(ids.to(self.wrapped.model.token_embedding.wrapped.weight.device)).squeeze(0)
|
|
|
|
return embedded
|