更新 .gitea/workflows/prod_build_manual.yaml

.gitea/workflows/prod_build_manual.yaml

@@ -0,0 +1,40 @@
+name: 手动 LC python main 分支构建部署
+on:
+  workflow_dispatch:
+
+jobs:
+  scheduled_deploy:
+    runs-on: ubuntu-latest
+
+    env:
+      REMOTE_DEPLOY_PATH: /workspace/LC_Workspace/LitServe_Server_Workspace/LC_NeoRefacer
+
+    steps:
+      - name: 1.检出代码
+        uses: actions/checkout@v4
+        with:
+          ref: 'main'
+
+      - name: 2.复制文件到服务器
+        uses: appleboy/scp-action@v0.1.7
+        with:
+          host: ${{ secrets.SERVER_HOST }}
+          username: ${{ secrets.SERVER_USER }}
+          password: ${{ secrets.SERVER_PASSWORD }}
+          source: "."
+          target: ${{ env.REMOTE_DEPLOY_PATH }}
+
+      - name: 3.重启docker-compose
+        uses: appleboy/ssh-action@v0.1.10
+        with:
+          host: ${{ secrets.SERVER_HOST }}
+          username: ${{ secrets.SERVER_USER }}
+          password: ${{ secrets.SERVER_PASSWORD }}
+          script: |
+            # 进入项目目录
+            cd ${{ env.REMOTE_DEPLOY_PATH }}
+            
+            docker-compose down 2>&1
+            docker-compose up -d  2>&1
+            
+            docker image prune -f 2>&1

.gitignore

@@ -170,4 +170,10 @@ aaa.md
 *_test.py
 img.jpg
 test_data
-testsrc.mp4
+testsrc.mp4
+
+*.jpg
+*.png
+*.pth
+.idea
+*.jpeg

Dockerfile

@@ -0,0 +1,37 @@
+FROM ghcr.io/astral-sh/uv:latest AS uv_bin
+FROM nvidia/cuda:12.4.1-base-ubuntu22.04
+
+# 1. 基础环境配置
+ENV UV_LINK_MODE=copy \
+    UV_COMPILE_BYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    # 核心：强制 uv 把虚拟环境建在 /app/.venv
+    UV_PROJECT_ENVIRONMENT=/app/.venv
+
+COPY --from=uv_bin /uv /uvx /bin/
+
+# 2. 安装系统依赖
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    ffmpeg libsm6 libxext6 build-essential g++ \
+    && apt-get clean && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# 3. 安装依赖 (不加 --system，让 uv 创建受管的虚拟环境)
+# 这里会根据 pyproject.toml 自动下载并安装 Python 3.11
+COPY pyproject.toml uv.lock ./
+RUN uv sync --frozen --no-dev --no-install-project --python 3.11
+
+# 4. 拷贝项目文件并安装项目本身
+COPY . .
+RUN uv sync --frozen --no-dev --python 3.11
+
+# 5. 【最关键】将虚拟环境的 bin 目录提到最前面
+# 注意：uv sync 创建的 python 就在这个目录下
+ENV PATH="/app/.venv/bin:$PATH"
+
+EXPOSE 8000
+
+# 验证路径并运行
+# 此时运行 python 实际上是运行 /app/.venv/bin/python
+CMD ["uv", "run","litserver_main.py"]

README-AIDA-LC.md

@@ -0,0 +1,8 @@
+创建Docker file：
+litserve dockerize server.py --port 8000 --gpu
+
+构建镜像：
+docker build -t litserve-model .
+
+运行容器：
+docker run -p 8000:8000 litserve-model

README.md

@@ -93,9 +93,9 @@ Follow these steps to install Refacer and its dependencies:
     
     # Create the environment
     # Windows:
-    conda create -n neorefacer-env python=3.11 nomkl conda-forge::vs2015_runtime
+    conda create -n neorefacer-env python=3.11 conda-forge::vs2015_runtime
     # Linux:
-    conda create -n neorefacer-env python=3.11 nomkl
+    conda create -n neorefacer-env python=3.11
     # MacOS:
     conda create -n neorefacer-env python=3.11
     
@@ -107,6 +107,12 @@ Follow these steps to install Refacer and its dependencies:
     pip install -r requirements-CPU.txt
     
     # For NVIDIA RTX GPU only (compatible with Windows and Linux only, requires a NVIDIA GPU with CUDA and its libraries)
+    # Install Torch with CUDA enabled:
+    conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia
+    # This should install torch 2.5.1, torchaudio 2.5.1 and torchvision 0.20.1
+    # Make sure that CUDA is returning True:
+    python -c "import torch; print('CUDA:', torch.cuda.is_available()); print(torch.version.cuda); print(torch.cuda.get_device_name(0))"
+    # Now install the rest of the dependencies
     pip install -r requirements-GPU.txt
     
     # For CoreML only (compatible with MacOSX, requires Silicon architecture):

basicsr/archs/vqgan_arch.py

@@ -1,65 +1,64 @@
-'''
-VQGAN code, adapted from the original created by the Unleashing Transformers authors:
-https://github.com/samb-t/unleashing-transformers/blob/master/models/vqgan.py
-
-'''
 import numpy as np
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
 import copy
+import os
 from basicsr.utils import get_root_logger
 from basicsr.utils.registry import ARCH_REGISTRY
 
+# Select Device
+def select_device(prefer_coreml=False):
+    if torch.backends.mps.is_available() and prefer_coreml:
+        print("BasicSR Archs: Using CoreML backend (MPS).")
+        return torch.device("mps")
+    elif torch.cuda.is_available():
+        print("BasicSR Archs: Using CUDA backend.")
+        return torch.device("cuda")
+    else:
+        print("BasicSR Archs: Using CPU backend.")
+        return torch.device("cpu")
+
+# Set device globally
+DEVICE = select_device(prefer_coreml=True)
+
 def normalize(in_channels):
     return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)
-    
 
 @torch.jit.script
 def swish(x):
-    return x*torch.sigmoid(x)
+    return x * torch.sigmoid(x)
 
-
-#  Define VQVAE classes
 class VectorQuantizer(nn.Module):
     def __init__(self, codebook_size, emb_dim, beta):
         super(VectorQuantizer, self).__init__()
-        self.codebook_size = codebook_size  # number of embeddings
-        self.emb_dim = emb_dim  # dimension of embedding
-        self.beta = beta  # commitment cost used in loss term, beta * ||z_e(x)-sg[e]||^2
+        self.codebook_size = codebook_size
+        self.emb_dim = emb_dim
+        self.beta = beta
         self.embedding = nn.Embedding(self.codebook_size, self.emb_dim)
         self.embedding.weight.data.uniform_(-1.0 / self.codebook_size, 1.0 / self.codebook_size)
 
     def forward(self, z):
-        # reshape z -> (batch, height, width, channel) and flatten
         z = z.permute(0, 2, 3, 1).contiguous()
         z_flattened = z.view(-1, self.emb_dim)
 
-        # distances from z to embeddings e_j (z - e)^2 = z^2 + e^2 - 2 e * z
-        d = (z_flattened ** 2).sum(dim=1, keepdim=True) + (self.embedding.weight**2).sum(1) - \
+        d = (z_flattened ** 2).sum(dim=1, keepdim=True) + \
+            (self.embedding.weight ** 2).sum(1) - \
             2 * torch.matmul(z_flattened, self.embedding.weight.t())
 
         mean_distance = torch.mean(d)
-        # find closest encodings
-        # min_encoding_indices = torch.argmin(d, dim=1).unsqueeze(1)
         min_encoding_scores, min_encoding_indices = torch.topk(d, 1, dim=1, largest=False)
-        # [0-1], higher score, higher confidence
-        min_encoding_scores = torch.exp(-min_encoding_scores/10)
+        min_encoding_scores = torch.exp(-min_encoding_scores / 10)
 
-        min_encodings = torch.zeros(min_encoding_indices.shape[0], self.codebook_size).to(z)
+        min_encodings = torch.zeros(min_encoding_indices.shape[0], self.codebook_size, device=z.device)
         min_encodings.scatter_(1, min_encoding_indices, 1)
 
-        # get quantized latent vectors
         z_q = torch.matmul(min_encodings, self.embedding.weight).view(z.shape)
-        # compute loss for embedding
-        loss = torch.mean((z_q.detach()-z)**2) + self.beta * torch.mean((z_q - z.detach()) ** 2)
-        # preserve gradients
+        loss = torch.mean((z_q.detach() - z) ** 2) + self.beta * torch.mean((z_q - z.detach()) ** 2)
         z_q = z + (z_q - z).detach()
 
-        # perplexity
         e_mean = torch.mean(min_encodings, dim=0)
         perplexity = torch.exp(-torch.sum(e_mean * torch.log(e_mean + 1e-10)))
-        # reshape back to match original input shape
         z_q = z_q.permute(0, 3, 1, 2).contiguous()
 
         return z_q, loss, {
@@ -68,18 +67,15 @@ class VectorQuantizer(nn.Module):
             "min_encoding_indices": min_encoding_indices,
             "min_encoding_scores": min_encoding_scores,
             "mean_distance": mean_distance
-            }
+        }
 
     def get_codebook_feat(self, indices, shape):
-        # input indices: batch*token_num -> (batch*token_num)*1
-        # shape: batch, height, width, channel
-        indices = indices.view(-1,1)
-        min_encodings = torch.zeros(indices.shape[0], self.codebook_size).to(indices)
+        indices = indices.view(-1, 1)
+        min_encodings = torch.zeros(indices.shape[0], self.codebook_size, device=indices.device)
         min_encodings.scatter_(1, indices, 1)
-        # get quantized latent vectors
         z_q = torch.matmul(min_encodings.float(), self.embedding.weight)
 
-        if shape is not None:  # reshape back to match original input shape
+        if shape is not None:
             z_q = z_q.view(shape).permute(0, 3, 1, 2).contiguous()
 
         return z_q
@@ -324,112 +320,87 @@ class Generator(nn.Module):
         return x
 
   
+# Autoencoder with device transfer
 @ARCH_REGISTRY.register()
 class VQAutoEncoder(nn.Module):
-    def __init__(self, img_size, nf, ch_mult, quantizer="nearest", res_blocks=2, attn_resolutions=[16], codebook_size=1024, emb_dim=256,
-                beta=0.25, gumbel_straight_through=False, gumbel_kl_weight=1e-8, model_path=None):
+    def __init__(self, img_size, nf, ch_mult, quantizer="nearest", res_blocks=2,
+                 attn_resolutions=[16], codebook_size=1024, emb_dim=256,
+                 beta=0.25, gumbel_straight_through=False, gumbel_kl_weight=1e-8, model_path=None):
         super().__init__()
         logger = get_root_logger()
-        self.in_channels = 3 
-        self.nf = nf 
-        self.n_blocks = res_blocks 
+        self.in_channels = 3
+        self.nf = nf
         self.codebook_size = codebook_size
         self.embed_dim = emb_dim
         self.ch_mult = ch_mult
         self.resolution = img_size
         self.attn_resolutions = attn_resolutions
         self.quantizer_type = quantizer
+
         self.encoder = Encoder(
-            self.in_channels,
-            self.nf,
-            self.embed_dim,
-            self.ch_mult,
-            self.n_blocks,
-            self.resolution,
-            self.attn_resolutions
-        )
+            self.in_channels, self.nf, self.embed_dim, self.ch_mult,
+            res_blocks, self.resolution, self.attn_resolutions
+        ).to(DEVICE)
+
         if self.quantizer_type == "nearest":
-            self.beta = beta #0.25
-            self.quantize = VectorQuantizer(self.codebook_size, self.embed_dim, self.beta)
-        elif self.quantizer_type == "gumbel":
-            self.gumbel_num_hiddens = emb_dim
-            self.straight_through = gumbel_straight_through
-            self.kl_weight = gumbel_kl_weight
+            self.quantize = VectorQuantizer(self.codebook_size, self.embed_dim, beta).to(DEVICE)
+        else:
             self.quantize = GumbelQuantizer(
-                self.codebook_size,
-                self.embed_dim,
-                self.gumbel_num_hiddens,
-                self.straight_through,
-                self.kl_weight
-            )
+                self.codebook_size, self.embed_dim, emb_dim,
+                gumbel_straight_through, gumbel_kl_weight
+            ).to(DEVICE)
+
         self.generator = Generator(
-            self.nf, 
-            self.embed_dim,
-            self.ch_mult, 
-            self.n_blocks, 
-            self.resolution, 
-            self.attn_resolutions
-        )
+            self.nf, self.embed_dim, self.ch_mult, res_blocks,
+            self.resolution, self.attn_resolutions
+        ).to(DEVICE)
 
         if model_path is not None:
             chkpt = torch.load(model_path, map_location='cpu')
             if 'params_ema' in chkpt:
-                self.load_state_dict(torch.load(model_path, map_location='cpu')['params_ema'])
-                logger.info(f'vqgan is loaded from: {model_path} [params_ema]')
+                self.load_state_dict(chkpt['params_ema'])
+                logger.info(f'Loaded VQGAN from: {model_path} [params_ema]')
             elif 'params' in chkpt:
-                self.load_state_dict(torch.load(model_path, map_location='cpu')['params'])
-                logger.info(f'vqgan is loaded from: {model_path} [params]')
+                self.load_state_dict(chkpt['params'])
+                logger.info(f'Loaded VQGAN from: {model_path} [params]')
             else:
-                raise ValueError(f'Wrong params!')
-
+                raise ValueError("Invalid model format!")
 
     def forward(self, x):
+        x = x.to(DEVICE)
         x = self.encoder(x)
         quant, codebook_loss, quant_stats = self.quantize(x)
         x = self.generator(quant)
         return x, codebook_loss, quant_stats
 
-
-
-# patch based discriminator
 @ARCH_REGISTRY.register()
 class VQGANDiscriminator(nn.Module):
     def __init__(self, nc=3, ndf=64, n_layers=4, model_path=None):
         super().__init__()
-
-        layers = [nn.Conv2d(nc, ndf, kernel_size=4, stride=2, padding=1), nn.LeakyReLU(0.2, True)]
-        ndf_mult = 1
-        ndf_mult_prev = 1
-        for n in range(1, n_layers):  # gradually increase the number of filters
-            ndf_mult_prev = ndf_mult
-            ndf_mult = min(2 ** n, 8)
-            layers += [
-                nn.Conv2d(ndf * ndf_mult_prev, ndf * ndf_mult, kernel_size=4, stride=2, padding=1, bias=False),
-                nn.BatchNorm2d(ndf * ndf_mult),
-                nn.LeakyReLU(0.2, True)
-            ]
-
-        ndf_mult_prev = ndf_mult
-        ndf_mult = min(2 ** n_layers, 8)
-
-        layers += [
-            nn.Conv2d(ndf * ndf_mult_prev, ndf * ndf_mult, kernel_size=4, stride=1, padding=1, bias=False),
-            nn.BatchNorm2d(ndf * ndf_mult),
+        layers = [
+            nn.Conv2d(nc, ndf, kernel_size=4, stride=2, padding=1),
             nn.LeakyReLU(0.2, True)
         ]
-
+        nf_mult = 1
+        for n in range(1, n_layers):
+            prev = nf_mult
+            nf_mult = min(2 ** n, 8)
+            layers += [
+                nn.Conv2d(ndf * prev, ndf * nf_mult, 4, 2, 1, bias=False),
+                nn.BatchNorm2d(ndf * nf_mult),
+                nn.LeakyReLU(0.2, True)
+            ]
         layers += [
-            nn.Conv2d(ndf * ndf_mult, 1, kernel_size=4, stride=1, padding=1)]  # output 1 channel prediction map
-        self.main = nn.Sequential(*layers)
+            nn.Conv2d(ndf * nf_mult, 1, 4, 1, 1)
+        ]
+        self.main = nn.Sequential(*layers).to(DEVICE)
 
-        if model_path is not None:
+        if model_path:
             chkpt = torch.load(model_path, map_location='cpu')
             if 'params_d' in chkpt:
-                self.load_state_dict(torch.load(model_path, map_location='cpu')['params_d'])
+                self.load_state_dict(chkpt['params_d'])
             elif 'params' in chkpt:
-                self.load_state_dict(torch.load(model_path, map_location='cpu')['params'])
-            else:
-                raise ValueError(f'Wrong params!')
+                self.load_state_dict(chkpt['params'])
 
     def forward(self, x):
-        return self.main(x)
+        return self.main(x.to(DEVICE))

basicsr/data/prefetch_dataloader.py

@@ -82,12 +82,9 @@ class CPUPrefetcher():
 
 
 class CUDAPrefetcher():
-    """CUDA prefetcher.
+    """CUDA (or MPS/CPU) prefetcher.
 
-    Ref:
-    https://github.com/NVIDIA/apex/issues/304#
-
-    It may consums more GPU memory.
+    It may consume more GPU memory.
 
     Args:
         loader: Dataloader.
@@ -98,8 +95,18 @@ class CUDAPrefetcher():
         self.ori_loader = loader
         self.loader = iter(loader)
         self.opt = opt
-        self.stream = torch.cuda.Stream()
-        self.device = torch.device('cuda' if opt['num_gpu'] != 0 else 'cpu')
+
+        # Cross-platform device detection
+        if opt['num_gpu'] != 0 and torch.cuda.is_available():
+            self.device = torch.device('cuda')
+            self.stream = torch.cuda.Stream()
+        elif torch.backends.mps.is_available():
+            self.device = torch.device('mps')
+            self.stream = None
+        else:
+            self.device = torch.device('cpu')
+            self.stream = None
+
         self.preload()
 
     def preload(self):
@@ -108,18 +115,24 @@ class CUDAPrefetcher():
         except StopIteration:
             self.batch = None
             return None
-        # put tensors to gpu
-        with torch.cuda.stream(self.stream):
+
+        if self.stream is not None:
+            with torch.cuda.stream(self.stream):
+                for k, v in self.batch.items():
+                    if torch.is_tensor(v):
+                        self.batch[k] = self.batch[k].to(device=self.device, non_blocking=True)
+        else:
             for k, v in self.batch.items():
                 if torch.is_tensor(v):
-                    self.batch[k] = self.batch[k].to(device=self.device, non_blocking=True)
+                    self.batch[k] = self.batch[k].to(device=self.device)
 
     def next(self):
-        torch.cuda.current_stream().wait_stream(self.stream)
+        if self.stream is not None:
+            torch.cuda.current_stream().wait_stream(self.stream)
         batch = self.batch
         self.preload()
         return batch
 
     def reset(self):
         self.loader = iter(self.ori_loader)
-        self.preload()
+        self.preload()

basicsr/train.py

@@ -2,22 +2,38 @@ import argparse
 import datetime
 import logging
 import math
-import copy
 import random
 import time
 import torch
+import platform
 from os import path as osp
+import warnings
 
 from basicsr.data import build_dataloader, build_dataset
 from basicsr.data.data_sampler import EnlargedSampler
 from basicsr.data.prefetch_dataloader import CPUPrefetcher, CUDAPrefetcher
 from basicsr.models import build_model
-from basicsr.utils import (MessageLogger, check_resume, get_env_info, get_root_logger, init_tb_logger,
-                           init_wandb_logger, make_exp_dirs, mkdir_and_rename, set_random_seed)
+from basicsr.utils import (
+    MessageLogger, check_resume, get_env_info, get_root_logger, init_tb_logger,
+    init_wandb_logger, make_exp_dirs, mkdir_and_rename, set_random_seed
+)
 from basicsr.utils.dist_util import get_dist_info, init_dist
 from basicsr.utils.options import dict2str, parse
 
-import warnings
+# ----------- DEVICE SELECTION ----------
+def select_device(prefer_coreml=True):
+    if torch.backends.mps.is_available() and prefer_coreml and platform.system() == "Darwin":
+        print("BasicSR: Using CoreML backend (MPS).")
+        return torch.device("mps")
+    elif torch.cuda.is_available():
+        print("BasicSR: Using CUDA backend.")
+        return torch.device("cuda")
+    else:
+        print("BasicSR: Using CPU backend.")
+        return torch.device("cpu")
+
+DEVICE = select_device(prefer_coreml=True)
+
 # ignore UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`.
 warnings.filterwarnings("ignore", category=UserWarning)
 
@@ -30,9 +46,9 @@ def parse_options(root_path, is_train=True):
     opt = parse(args.opt, root_path, is_train=is_train)
 
     # distributed settings
-    if args.launcher == 'none':
+    if args.launcher == 'none' or DEVICE.type != 'cuda':
         opt['dist'] = False
-        print('Disable distributed.', flush=True)
+        print('Distributed training disabled.', flush=True)
     else:
         opt['dist'] = True
         if args.launcher == 'slurm' and 'dist_params' in opt:
@@ -51,122 +67,96 @@ def parse_options(root_path, is_train=True):
 
     return opt
 
-
 def init_loggers(opt):
     log_file = osp.join(opt['path']['log'], f"train_{opt['name']}.log")
     logger = get_root_logger(logger_name='basicsr', log_level=logging.INFO, log_file=log_file)
     logger.info(get_env_info())
     logger.info(dict2str(opt))
 
-    # initialize wandb logger before tensorboard logger to allow proper sync:
     if (opt['logger'].get('wandb') is not None) and (opt['logger']['wandb'].get('project') is not None):
-        assert opt['logger'].get('use_tb_logger') is True, ('should turn on tensorboard when using wandb')
+        assert opt['logger'].get('use_tb_logger') is True
         init_wandb_logger(opt)
+
     tb_logger = None
     if opt['logger'].get('use_tb_logger'):
         tb_logger = init_tb_logger(log_dir=osp.join('tb_logger', opt['name']))
     return logger, tb_logger
 
-
 def create_train_val_dataloader(opt, logger):
-    # create train and val dataloaders
     train_loader, val_loader = None, None
     for phase, dataset_opt in opt['datasets'].items():
         if phase == 'train':
             dataset_enlarge_ratio = dataset_opt.get('dataset_enlarge_ratio', 1)
             train_set = build_dataset(dataset_opt)
             train_sampler = EnlargedSampler(train_set, opt['world_size'], opt['rank'], dataset_enlarge_ratio)
-            train_loader = build_dataloader(
-                train_set,
-                dataset_opt,
-                num_gpu=opt['num_gpu'],
-                dist=opt['dist'],
-                sampler=train_sampler,
-                seed=opt['manual_seed'])
-
-            num_iter_per_epoch = math.ceil(
-                len(train_set) * dataset_enlarge_ratio / (dataset_opt['batch_size_per_gpu'] * opt['world_size']))
+            train_loader = build_dataloader(train_set, dataset_opt, num_gpu=opt['num_gpu'], dist=opt['dist'], sampler=train_sampler, seed=opt['manual_seed'])
+            num_iter_per_epoch = math.ceil(len(train_set) * dataset_enlarge_ratio / (dataset_opt['batch_size_per_gpu'] * opt['world_size']))
             total_iters = int(opt['train']['total_iter'])
-            total_epochs = math.ceil(total_iters / (num_iter_per_epoch))
-            logger.info('Training statistics:'
-                        f'\n\tNumber of train images: {len(train_set)}'
-                        f'\n\tDataset enlarge ratio: {dataset_enlarge_ratio}'
-                        f'\n\tBatch size per gpu: {dataset_opt["batch_size_per_gpu"]}'
-                        f'\n\tWorld size (gpu number): {opt["world_size"]}'
-                        f'\n\tRequire iter number per epoch: {num_iter_per_epoch}'
-                        f'\n\tTotal epochs: {total_epochs}; iters: {total_iters}.')
+            total_epochs = math.ceil(total_iters / num_iter_per_epoch)
+            logger.info(f'Training stats:\n\tTrain images: {len(train_set)}\n\tEnlarge ratio: {dataset_enlarge_ratio}\n\tBatch/GPU: {dataset_opt["batch_size_per_gpu"]}\n\tGPUs: {opt["world_size"]}\n\tIters/epoch: {num_iter_per_epoch}\n\tTotal epochs: {total_epochs}, Iters: {total_iters}')
 
         elif phase == 'val':
             val_set = build_dataset(dataset_opt)
-            val_loader = build_dataloader(
-                val_set, dataset_opt, num_gpu=opt['num_gpu'], dist=opt['dist'], sampler=None, seed=opt['manual_seed'])
-            logger.info(f'Number of val images/folders in {dataset_opt["name"]}: ' f'{len(val_set)}')
+            val_loader = build_dataloader(val_set, dataset_opt, num_gpu=opt['num_gpu'], dist=opt['dist'], sampler=None, seed=opt['manual_seed'])
+            logger.info(f'Validation items in {dataset_opt["name"]}: {len(val_set)}')
         else:
-            raise ValueError(f'Dataset phase {phase} is not recognized.')
+            raise ValueError(f'Dataset phase {phase} not recognized.')
 
     return train_loader, train_sampler, val_loader, total_epochs, total_iters
 
-
 def train_pipeline(root_path):
-    # parse options, set distributed setting, set ramdom seed
     opt = parse_options(root_path, is_train=True)
 
-    torch.backends.cudnn.benchmark = True
-    # torch.backends.cudnn.deterministic = True
+    if DEVICE.type == 'cuda':
+        torch.backends.cudnn.benchmark = True
 
-    # load resume states if necessary
     if opt['path'].get('resume_state'):
-        device_id = torch.cuda.current_device()
-        resume_state = torch.load(
-            opt['path']['resume_state'], map_location=lambda storage, loc: storage.cuda(device_id))
+        resume_state = torch.load(opt['path']['resume_state'], map_location=DEVICE)
     else:
         resume_state = None
 
-    # mkdir for experiments and logger
     if resume_state is None:
         make_exp_dirs(opt)
         if opt['logger'].get('use_tb_logger') and opt['rank'] == 0:
             mkdir_and_rename(osp.join('tb_logger', opt['name']))
 
-    # initialize loggers
     logger, tb_logger = init_loggers(opt)
-    
-    # create train and validation dataloaders
-    result = create_train_val_dataloader(opt, logger)
-    train_loader, train_sampler, val_loader, total_epochs, total_iters = result
+    train_loader, train_sampler, val_loader, total_epochs, total_iters = create_train_val_dataloader(opt, logger)
 
-    # create model
-    if resume_state:  # resume training
+    if resume_state:
         check_resume(opt, resume_state['iter'])
-        model = build_model(opt)
-        model.resume_training(resume_state)  # handle optimizers and schedulers
-        logger.info(f"Resuming training from epoch: {resume_state['epoch']}, " f"iter: {resume_state['iter']}.")
+        model = build_model(opt).to(DEVICE)
+        model.resume_training(resume_state)
+        logger.info(f"Resuming from epoch {resume_state['epoch']}, iter {resume_state['iter']}")
         start_epoch = resume_state['epoch']
         current_iter = resume_state['iter']
     else:
-        model = build_model(opt)
+        model = build_model(opt).to(DEVICE)
         start_epoch = 0
         current_iter = 0
 
-    # create message logger (formatted outputs)
     msg_logger = MessageLogger(opt, current_iter, tb_logger)
 
-    # dataloader prefetcher
     prefetch_mode = opt['datasets']['train'].get('prefetch_mode')
-    if prefetch_mode is None or prefetch_mode == 'cpu':
+    if prefetch_mode is None or prefetch_mode == 'cpu' or DEVICE.type in ['cpu', 'mps']:
+        if prefetch_mode == 'cuda' and DEVICE.type == 'mps':
+            logger.warning("CUDA prefetch requested but MPS (CoreML) is in use. Falling back to CPU prefetch.")
         prefetcher = CPUPrefetcher(train_loader)
     elif prefetch_mode == 'cuda':
-        prefetcher = CUDAPrefetcher(train_loader, opt)
-        logger.info(f'Use {prefetch_mode} prefetch dataloader')
-        if opt['datasets']['train'].get('pin_memory') is not True:
-            raise ValueError('Please set pin_memory=True for CUDAPrefetcher.')
+        if DEVICE.type != 'cuda':
+            logger.warning("CUDA prefetch requested but CUDA unavailable. Using CPU prefetch.")
+            prefetcher = CPUPrefetcher(train_loader)
+        else:
+            if opt['datasets']['train'].get('pin_memory') is not True:
+                raise ValueError('Set pin_memory=True for CUDAPrefetcher.')
+            prefetcher = CUDAPrefetcher(train_loader, opt)
+            logger.info(f'Using CUDA prefetcher')
     else:
-        raise ValueError(f'Wrong prefetch_mode {prefetch_mode}.' "Supported ones are: None, 'cuda', 'cpu'.")
+        raise ValueError(f"Invalid prefetch_mode: {prefetch_mode}. Supported: 'cpu', 'cuda', None")
 
-    # training
-    logger.info(f'Start training from epoch: {start_epoch}, iter: {current_iter+1}')
-    data_time, iter_time = time.time(), time.time()
+    logger.info(f'Start training at epoch {start_epoch}, iter {current_iter + 1}')
     start_time = time.time()
+    data_time, iter_time = time.time(), time.time()
 
     for epoch in range(start_epoch, total_epochs + 1):
         train_sampler.set_epoch(epoch)
@@ -175,17 +165,15 @@ def train_pipeline(root_path):
 
         while train_data is not None:
             data_time = time.time() - data_time
-
             current_iter += 1
             if current_iter > total_iters:
                 break
-            # update learning rate
+
             model.update_learning_rate(current_iter, warmup_iter=opt['train'].get('warmup_iter', -1))
-            # training
             model.feed_data(train_data)
             model.optimize_parameters(current_iter)
+
             iter_time = time.time() - iter_time
-            # log
             if current_iter % opt['logger']['print_freq'] == 0:
                 log_vars = {'epoch': epoch, 'iter': current_iter}
                 log_vars.update({'lrs': model.get_current_learning_rate()})
@@ -193,33 +181,27 @@ def train_pipeline(root_path):
                 log_vars.update(model.get_current_log())
                 msg_logger(log_vars)
 
-            # save models and training states
             if current_iter % opt['logger']['save_checkpoint_freq'] == 0:
-                logger.info('Saving models and training states.')
+                logger.info('Saving model and training state.')
                 model.save(epoch, current_iter)
 
-            # validation
-            if opt.get('val') is not None and opt['datasets'].get('val') is not None \
-                and (current_iter % opt['val']['val_freq'] == 0):
+            if opt.get('val') and opt['datasets'].get('val') and (current_iter % opt['val']['val_freq'] == 0):
                 model.validation(val_loader, current_iter, tb_logger, opt['val']['save_img'])
 
             data_time = time.time()
             iter_time = time.time()
             train_data = prefetcher.next()
-        # end of iter
-
-    # end of epoch
 
     consumed_time = str(datetime.timedelta(seconds=int(time.time() - start_time)))
-    logger.info(f'End of training. Time consumed: {consumed_time}')
-    logger.info('Save the latest model.')
-    model.save(epoch=-1, current_iter=-1)  # -1 stands for the latest
-    if opt.get('val') is not None and opt['datasets'].get('val'):
+    logger.info(f'Training complete. Time: {consumed_time}')
+    logger.info('Saving latest model.')
+    model.save(epoch=-1, current_iter=-1)
+
+    if opt.get('val') and opt['datasets'].get('val'):
         model.validation(val_loader, current_iter, tb_logger, opt['val']['save_img'])
     if tb_logger:
         tb_logger.close()
 
-
 if __name__ == '__main__':
     root_path = osp.abspath(osp.join(__file__, osp.pardir, osp.pardir))
-    train_pipeline(root_path)
+    train_pipeline(root_path)

basicsr/utils/realesrgan_utils.py

@@ -44,11 +44,20 @@ class RealESRGANer():
         self.half = half
 
         # initialize model
-        if gpu_id:
-            self.device = torch.device(
-                f'cuda:{gpu_id}' if torch.cuda.is_available() else 'cpu') if device is None else device
+        if device is not None:
+            self.device = device
         else:
-            self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') if device is None else device
+            if torch.cuda.is_available():
+                if gpu_id is not None and gpu_id < torch.cuda.device_count():
+                    self.device = torch.device(f"cuda:{gpu_id}")
+                else:
+                    self.device = torch.device("cuda:0")
+            elif torch.backends.mps.is_available():
+                self.device = torch.device("mps")
+            else:
+                self.device = torch.device("cpu")
+
+
         # if the model_path starts with https, it will first download models to the folder: realesrgan/weights
         if model_path.startswith('https://'):
             model_path = load_file_from_url(

client.py

@@ -0,0 +1,7 @@
+# This file is auto-generated by LitServe.
+# Disable auto-generation by setting `generate_client_file=False` in `LitServer.run()`.
+
+import requests
+
+response = requests.post("http://127.0.0.1:8080/predict", json={"input": 4.0})
+print(f"Status: {response.status_code}\nResponse:\n {response.text}")

codeformer_wrapper.py

@@ -9,8 +9,15 @@ from basicsr.utils.download_util import load_file_from_url
 from facelib.utils.face_restoration_helper import FaceRestoreHelper
 from basicsr.utils.registry import ARCH_REGISTRY
 
-device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+# Cross-platform device selection: CUDA > MPS > CPU
+if torch.cuda.is_available():
+    device = torch.device("cuda")
+elif torch.backends.mps.is_available():
+    device = torch.device("mps")
+else:
+    device = torch.device("cpu")
 
+# Download and load model
 pretrain_model_url = {
     'restoration': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth',
 }
@@ -20,7 +27,7 @@ net = ARCH_REGISTRY.get('CodeFormer')(dim_embd=512, codebook_size=1024, n_head=8
 
 ckpt_path = load_file_from_url(url=pretrain_model_url['restoration'],
                                 model_dir='weights/CodeFormer', progress=True, file_name=None)
-checkpoint = torch.load(ckpt_path)['params_ema']
+checkpoint = torch.load(ckpt_path, map_location=device)['params_ema']
 net.load_state_dict(checkpoint)
 net.eval()
 
@@ -47,9 +54,9 @@ def _enhance_img(img: np.ndarray, w: float = 0.5) -> np.ndarray:
     face_helper.align_warp_face()
 
     for cropped_face in face_helper.cropped_faces:
-        cropped_face_t = img2tensor(cropped_face / 255., bgr2rgb=True, float32=True)
+        cropped_face_t = img2tensor(cropped_face / 255., bgr2rgb=True, float32=True).to(device)
         normalize(cropped_face_t, (0.5, 0.5, 0.5), (0.5, 0.5, 0.5), inplace=True)
-        cropped_face_t = cropped_face_t.unsqueeze(0).to(device)
+        cropped_face_t = cropped_face_t.unsqueeze(0)  # (1, 3, H, W), already on correct device
 
         with torch.no_grad():
             output = net(cropped_face_t, w=w, adain=True)[0]
@@ -84,4 +91,4 @@ def enhance_image_memory(img: np.ndarray, w: float = 0.5) -> np.ndarray:
     """
     Enhances an input image entirely in memory and returns the enhanced image.
     """
-    return _enhance_img(img, w=w)
+    return _enhance_img(img, w=w)

codeformer_wrapper_no_path.py

@@ -0,0 +1,93 @@
+import os
+import torch
+import cv2
+import numpy as np
+from pathlib import Path
+from torchvision.transforms.functional import normalize
+from basicsr.utils import img2tensor, tensor2img
+from basicsr.utils.download_util import load_file_from_url
+from facelib.utils.face_restoration_helper import FaceRestoreHelper
+from basicsr.utils.registry import ARCH_REGISTRY
+
+# Cross-platform device selection: CUDA > MPS > CPU
+if torch.cuda.is_available():
+    device = torch.device("cuda")
+elif torch.backends.mps.is_available():
+    device = torch.device("mps")
+else:
+    device = torch.device("cpu")
+
+# Download and load model
+pretrain_model_url = {
+    'restoration': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth',
+}
+
+net = ARCH_REGISTRY.get('CodeFormer')(dim_embd=512, codebook_size=1024, n_head=8, n_layers=9,
+                                       connect_list=['32', '64', '128', '256']).to(device)
+
+ckpt_path = load_file_from_url(url=pretrain_model_url['restoration'],
+                                model_dir='weights/CodeFormer', progress=True, file_name=None)
+checkpoint = torch.load(ckpt_path, map_location=device)['params_ema']
+net.load_state_dict(checkpoint)
+net.eval()
+
+face_helper = FaceRestoreHelper(
+    upscale_factor=1,
+    face_size=512,
+    crop_ratio=(1, 1),
+    det_model='retinaface_resnet50',
+    save_ext='jpg',
+    use_parse=True,
+    device=device
+)
+
+def _enhance_img(img: np.ndarray, w: float = 0.5) -> np.ndarray:
+    """
+    Internal helper to enhance a numpy image with CodeFormer.
+    """
+    face_helper.clean_all()
+    face_helper.read_image(img)
+    num_faces = face_helper.get_face_landmarks_5(only_center_face=False, resize=640, eye_dist_threshold=5)
+    if num_faces == 0:
+        return img  # Return original if no faces detected
+
+    face_helper.align_warp_face()
+
+    for cropped_face in face_helper.cropped_faces:
+        cropped_face_t = img2tensor(cropped_face / 255., bgr2rgb=True, float32=True).to(device)
+        normalize(cropped_face_t, (0.5, 0.5, 0.5), (0.5, 0.5, 0.5), inplace=True)
+        cropped_face_t = cropped_face_t.unsqueeze(0)  # (1, 3, H, W), already on correct device
+
+        with torch.no_grad():
+            output = net(cropped_face_t, w=w, adain=True)[0]
+            restored_face = tensor2img(output, rgb2bgr=True, min_max=(-1, 1))
+
+        restored_face = restored_face.astype('uint8')
+        face_helper.add_restored_face(restored_face)
+
+    face_helper.get_inverse_affine(None)
+    restored_img = face_helper.paste_faces_to_input_image()
+    return restored_img
+
+def enhance_image(img: str, w: float = 0.5) -> str:
+    """
+    Enhances an input image using CodeFormer and saves it with a '.enhanced.jpg' suffix.
+    """
+    # input_path = Path(input_image_path)
+    # output_path = input_path.with_name(f"{input_path.stem}.enhanced.jpg")
+    # img = cv2.imread(str(input_path), cv2.IMREAD_COLOR)
+    if img is None:
+        raise ValueError(f"Cannot read image")
+
+    restored_img = _enhance_img(img, w=w)
+
+    # os.makedirs(output_path.parent, exist_ok=True)
+    # cv2.imwrite(str(output_path), restored_img)
+    # print(f"Enhanced image saved to: {output_path}")
+    return restored_img
+
+def enhance_image_memory(img: np.ndarray, w: float = 0.5) -> np.ndarray:
+    """
+    Enhances an input image entirely in memory and returns the enhanced image.
+    """
+    return _enhance_img(img, w=w)

docker-compose.yml

@@ -0,0 +1,19 @@
+services:
+  lc_neo_refacer:
+    container_name: LC_Refacer_Server
+    build:
+      context: .
+      dockerfile: Dockerfile
+    working_dir: /app
+    volumes:
+      - .:/app
+    ports:
+      - "10071:8000"
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              device_ids: [ '1' ]
+              capabilities:
+                - gpu

facelib/detection/retinaface/retinaface.py

@@ -11,7 +11,13 @@ from facelib.detection.retinaface.retinaface_net import FPN, SSH, MobileNetV1, m
 from facelib.detection.retinaface.retinaface_utils import (PriorBox, batched_decode, batched_decode_landm, decode, decode_landm,
                                                  py_cpu_nms)
 
-device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+if torch.cuda.is_available():
+    device = torch.device("cuda")
+elif torch.backends.mps.is_available():
+    device = torch.device("mps")
+else:
+    device = torch.device("cpu")
 
 
 def generate_config(network_name):
@@ -367,4 +373,4 @@ class RetinaFace(nn.Module):
         # self.total_frame += len(frames)
         # print(self.batch_time / self.total_frame)
 
-        return final_bounding_boxes, final_landmarks
+        return final_bounding_boxes, final_landmarks

facelib/detection/yolov5face/face_detector.py

@@ -139,4 +139,4 @@ class YoloDetector:
             return None
 
     def __call__(self, *args):
-        return self.predict(*args)
+        return self.predict(*args)

facelib/detection/yolov5face/utils/extract_ckpt.py

@@ -1,5 +1,21 @@
 import torch
 import sys
-sys.path.insert(0,'./facelib/detection/yolov5face')
-model = torch.load('facelib/detection/yolov5face/yolov5n-face.pt', map_location='cpu')['model']
-torch.save(model.state_dict(),'weights/facelib/yolov5n-face.pth')
+import os
+
+# Setup dynamic device selection
+if torch.cuda.is_available():
+    device = torch.device("cuda")
+elif torch.backends.mps.is_available():
+    device = torch.device("mps")
+else:
+    device = torch.device("cpu")
+
+sys.path.insert(0, './facelib/detection/yolov5face')
+
+# Load the model to the selected device
+ckpt = torch.load('facelib/detection/yolov5face/yolov5n-face.pt', map_location=device)
+model = ckpt['model'].to(device)
+
+# Save only the weights
+os.makedirs('weights/facelib', exist_ok=True)
+torch.save(model.state_dict(), 'weights/facelib/yolov5n-face.pth')

litserver_main.py

@@ -0,0 +1,72 @@
+import time
+
+import cv2
+import litserve as ls
+from pydantic import BaseModel
+
+from refacer_no_path import Refacer as NoPathRefacer
+from utils.minio_client import oss_get_image, minio_client, oss_upload_image
+
+
+class PredictRequest(BaseModel):
+    input_image_list: list[str]  # 待换脸图片
+    input_face: str  # 目标脸图片
+    threshold: float = 0.2  # 相似度 max：0.5
+
+
+class InferencePipeline(ls.LitAPI):
+    def setup(self, device):
+        force_cpu = False
+        colab_performance = False
+        self.supported_exts = {'jpg', 'jpeg', 'png', 'bmp', 'webp'}
+        self.refacer = NoPathRefacer(force_cpu=force_cpu, colab_performance=colab_performance)
+
+    def decode_request(self, request: PredictRequest):
+        self.input_image_list = []
+        for path in request.input_image_list:
+            self.input_image_list.append({
+                'img_obj': oss_get_image(oss_client=minio_client, path=path, data_type="cv2"),
+                'img_path': path
+            })
+        dest_img = oss_get_image(oss_client=minio_client, path=request.input_face, data_type="cv2")
+        if dest_img.shape[2] == 4:
+            dest_img = cv2.cvtColor(dest_img, cv2.COLOR_RGBA2RGB)
+        faces_config = [
+            {
+                'origin': None,
+                'destination': dest_img,
+                'destination_path': request.input_face,
+                'threshold': request.threshold,
+            }
+        ]
+        self.refacer.prepare_faces(faces_config)
+        return faces_config
+
+    def predict(self, faces_config):
+        refaced_images_url = []
+        for i, image in enumerate(self.input_image_list):
+            ext = image['img_path'].rsplit(".", 1)[1].lower()
+
+            if ext not in self.supported_exts:
+                print(f"Skipping non-image file: {image['img_path']}")
+                continue
+            print(f"Refacing: {image['img_path']}")
+            try:
+                refaced_image = self.refacer.reface_image(image['img_obj'], faces_config, disable_similarity=True)
+                refaced_image_rgb = cv2.cvtColor(refaced_image, cv2.COLOR_RGB2BGR)
+                image_bytes = cv2.imencode('.jpg', refaced_image_rgb)[1].tobytes()
+                req = oss_upload_image(oss_client=minio_client, bucket="lanecarford", object_name=f"refaced_image/refaced{time.time()}.{ext}", image_bytes=image_bytes)
+                refaced_images_url.append(f"{req.bucket_name}/{req.object_name}")
+                print(f"Saved -> {req.bucket_name}/{req.object_name}")
+            except Exception as e:
+                print(f"Failed to process {image['img_path']}: {e}")
+        return refaced_images_url
+
+    def encode_response(self, output):
+        return {"output": output}
+
+
+if __name__ == '__main__':
+    api = InferencePipeline()
+    server = ls.LitServer(api, accelerator="auto")
+    server.run(port=8000)

pyproject.toml

@@ -0,0 +1,26 @@
+[project]
+name = "lc-neorefacer"
+version = "0.1.0"
+description = "Add your description here"
+requires-python = ">=3.11"
+dependencies = [
+    "ffmpeg-python>=0.2.0",
+    "gdown>=5.2.0",
+    "gradio>=6.2.0",
+    "imageio[ffmpeg]>=2.37.2",
+    "insightface>=0.7.3",
+    "litserve>=0.2.16",
+    "lpips>=0.1.4",
+    "minio>=7.2.20",
+    "ngrok>=1.4.0",
+    "onnx>=1.20.0",
+    "onnxruntime>=1.23.2",
+    "opencv-contrib-python>=4.12.0.88",
+    "pillow>=12.0.0",
+    "pyfiglet>=1.0.4",
+    "requests>=2.32.5",
+    "scikit-image>=0.26.0",
+    "torch>=2.9.1",
+    "torchvision>=0.24.1",
+    "tqdm>=4.67.1",
+]

recognition/scrfd.py

@@ -269,32 +269,45 @@ class SCRFD:
         return det, kpss
 
     def autodetect(self, img, max_num=0, metric='max'):
-        bboxes, kpss = self.detect(img, input_size=(640, 640), thresh=0.5)
-        bboxes2, kpss2 = self.detect(img, input_size=(128, 128), thresh=0.5)
+        if self.session.get_providers()[0] == 'CoreMLExecutionProvider':
+            # Cache the CPU-based detector
+            if not hasattr(self, '_cpu_fallback_detector'):
+                model_path = self.model_file
+                cpu_session = onnxruntime.InferenceSession(model_path, providers=["CPUExecutionProvider"])
+                self._cpu_fallback_detector = SCRFD(model_file=model_path, session=cpu_session)
+                self._cpu_fallback_detector.prepare(0, input_size=(640, 640))
+            
+            detector = self._cpu_fallback_detector
+        else:
+            detector = self  # Use the original GPU/CoreML session
+
+        bboxes, kpss = detector.detect(img, input_size=(640, 640), thresh=0.5)
+        bboxes2, kpss2 = detector.detect(img, input_size=(128, 128), thresh=0.5)
+        
         bboxes_all = np.concatenate([bboxes, bboxes2], axis=0)
         kpss_all = np.concatenate([kpss, kpss2], axis=0)
         keep = self.nms(bboxes_all)
-        det = bboxes_all[keep,:]
-        kpss = kpss_all[keep,:]
+        det = bboxes_all[keep, :]
+        kpss = kpss_all[keep, :]
+
         if max_num > 0 and det.shape[0] > max_num:
-            area = (det[:, 2] - det[:, 0]) * (det[:, 3] -
-                                                    det[:, 1])
+            area = (det[:, 2] - det[:, 0]) * (det[:, 3] - det[:, 1])
             img_center = img.shape[0] // 2, img.shape[1] // 2
             offsets = np.vstack([
                 (det[:, 0] + det[:, 2]) / 2 - img_center[1],
                 (det[:, 1] + det[:, 3]) / 2 - img_center[0]
             ])
             offset_dist_squared = np.sum(np.power(offsets, 2.0), 0)
-            if metric=='max':
+            if metric == 'max':
                 values = area
             else:
-                values = area - offset_dist_squared * 2.0  # some extra weight on the centering
-            bindex = np.argsort(
-                values)[::-1]  # some extra weight on the centering
+                values = area - offset_dist_squared * 2.0
+            bindex = np.argsort(values)[::-1]
             bindex = bindex[0:max_num]
             det = det[bindex, :]
             if kpss is not None:
                 kpss = kpss[bindex, :]
+
         return det, kpss
 
     def nms(self, dets):
@@ -325,5 +338,4 @@ class SCRFD:
             inds = np.where(ovr <= thresh)[0]
             order = order[inds + 1]
 
-        return keep
-
+        return keep

refacer.py

@@ -1,6 +1,9 @@
 import cv2
 import onnxruntime as rt
 import sys
+
+from utils.minio_client import oss_get_image, minio_client
+
 sys.path.insert(1, './recognition')
 from scrfd import SCRFD
 from arcface_onnx import ArcFaceONNX
@@ -40,9 +43,11 @@ if sys.platform in ("win32", "win64"):
     if hasattr(rt, "preload_dlls"):
         rt.preload_dlls()
 
+
 class RefacerMode(Enum):
     CPU, CUDA, COREML, TENSORRT = range(1, 5)
 
+
 class Refacer:
     def __init__(self, force_cpu=False, colab_performance=False):
         self.disable_similarity = False
@@ -55,46 +60,45 @@ class Refacer:
         self.__check_providers()
         self.total_mem = psutil.virtual_memory().total
         self.__init_apps()
-        
+
     def _partial_face_blend(self, original_frame, swapped_frame, face):
         h_frame, w_frame = original_frame.shape[:2]
-    
+
         x1, y1, x2, y2 = map(int, face.bbox)
-        x1 = max(0, min(x1, w_frame-1))
-        y1 = max(0, min(y1, h_frame-1))
+        x1 = max(0, min(x1, w_frame - 1))
+        y1 = max(0, min(y1, h_frame - 1))
         x2 = max(0, min(x2, w_frame))
         y2 = max(0, min(y2, h_frame))
-    
+
         if x2 <= x1 or y2 <= y1:
             print(f"Invalid bbox: {x1},{y1},{x2},{y2}")
             return swapped_frame
-    
+
         w = x2 - x1
         h = y2 - y1
         cutoff = int(h * (1.0 - self.blend_height_ratio))
-    
+
         swap_crop = swapped_frame[y1:y2, x1:x2].copy()
         orig_crop = original_frame[y1:y2, x1:x2].copy()
-    
+
         mask = np.ones((h, w, 3), dtype=np.float32)
         transition = 40
-    
+
         if cutoff < h:
             blend_start = max(cutoff - transition // 2, 0)
             blend_end = min(cutoff + transition // 2, h)
-    
+
             if blend_end > blend_start:
                 alpha = np.linspace(1.0, 0.0, blend_end - blend_start)[:, np.newaxis, np.newaxis]
                 mask[blend_start:blend_end, :, :] = alpha
             mask[blend_end:, :, :] = 0.0
-    
+
         blended_crop = (swap_crop.astype(np.float32) * mask + orig_crop.astype(np.float32) * (1.0 - mask)).astype(np.uint8)
-    
+
         blended_frame = swapped_frame.copy()
         blended_frame[y1:y2, x1:x2] = blended_crop
-    
+
         return blended_frame
-    
 
     def __download_with_progress(self, url, output_path):
         response = requests.get(url, stream=True)
@@ -238,7 +242,7 @@ class Refacer:
         faces = self.__get_faces(frame, max_num=0)
         if not faces:
             return frame
-    
+
         if self.disable_similarity:
             for face in faces:
                 swapped = self.face_swapper.get(frame, face, self.replacement_faces[0][1], paste_back=True)
@@ -253,9 +257,9 @@ class Refacer:
         faces = self.__get_faces(frame, max_num=0)
         if not faces:
             return frame
- 
+
         faces = sorted(faces, key=lambda face: face.bbox[0])
- 
+
         if self.multiple_faces_mode:
             for idx, face in enumerate(faces):
                 if idx >= len(self.replacement_faces):
@@ -309,33 +313,33 @@ class Refacer:
         original_name = osp.splitext(osp.basename(video_path))[0]
         timestamp = str(int(time.time()))
         filename = f"{original_name}_preview.mp4" if preview else f"{original_name}_{timestamp}.mp4"
-    
+
         self.__check_video_has_audio(video_path)
-    
+
         if preview:
             os.makedirs("output/preview", exist_ok=True)
             output_video_path = os.path.join('output', 'preview', filename)
         else:
             os.makedirs("output", exist_ok=True)
             output_video_path = os.path.join('output', filename)
-    
+
         self.prepare_faces(faces, disable_similarity=disable_similarity, multiple_faces_mode=multiple_faces_mode)
         self.first_face = False if multiple_faces_mode else (faces[0].get("origin") is None or disable_similarity)
         self.partial_reface_ratio = partial_reface_ratio
-    
+
         cap = cv2.VideoCapture(video_path, cv2.CAP_FFMPEG)
         total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
         fps = cap.get(cv2.CAP_PROP_FPS)
         frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
         frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-    
+
         fourcc = cv2.VideoWriter_fourcc(*'mp4v')
         output = cv2.VideoWriter(output_video_path, fourcc, fps, (frame_width, frame_height))
-    
+
         frames = []
         frame_index = 0
         skip_rate = 10 if preview else 1
-    
+
         with tqdm(total=total_frames, desc="Extracting frames") as pbar:
             while cap.isOpened():
                 flag, frame = cap.read()
@@ -349,28 +353,24 @@ class Refacer:
                         gc.collect()
                 frame_index += 1
                 pbar.update()
-    
+
         cap.release()
         if frames:
             self.reface_group(faces, frames, output)
         output.release()
-    
+
         converted_path = self.__convert_video(video_path, output_video_path, preview=preview)
-    
+
         if video_path.lower().endswith(".gif"):
             if preview:
                 gif_output_path = os.path.join("output", "preview", os.path.basename(converted_path).replace(".mp4", ".gif"))
             else:
                 gif_output_path = os.path.join("output", "gifs", os.path.basename(converted_path).replace(".mp4", ".gif"))
-    
+
             self.__generate_gif(converted_path, gif_output_path)
             return converted_path, gif_output_path
-    
-        return converted_path, None
-    
-   
-  
 
+        return converted_path, None
 
     def __generate_gif(self, video_path, gif_output_path):
         os.makedirs(os.path.dirname(gif_output_path), exist_ok=True)
@@ -396,60 +396,64 @@ class Refacer:
         return new_path
 
     def reface_image(self, image_path, faces, disable_similarity=False, multiple_faces_mode=False, partial_reface_ratio=0.0):
-         self.prepare_faces(faces, disable_similarity=disable_similarity, multiple_faces_mode=multiple_faces_mode)
-         self.first_face = False if multiple_faces_mode else (faces[0].get("origin") is None or disable_similarity)
-         self.partial_reface_ratio = partial_reface_ratio
- 
-         ext = osp.splitext(image_path)[1].lower()
-         os.makedirs("output", exist_ok=True)
-         original_name = osp.splitext(osp.basename(image_path))[0]
-         timestamp = str(int(time.time()))
- 
-         if ext in ['.tif', '.tiff']:
-             pil_img = Image.open(image_path)
-             frames = []
- 
-             page_count = 0
-             try:
-                 while True:
-                     pil_img.seek(page_count)
-                     page_count += 1
-             except EOFError:
-                 pass
- 
-             pil_img = Image.open(image_path)
- 
-             with tqdm(total=page_count, desc="Processing TIFF pages") as pbar:
-                 for page in range(page_count):
-                     pil_img.seek(page)
-                     bgr_image = cv2.cvtColor(np.array(pil_img.convert('RGB')), cv2.COLOR_RGB2BGR)
-                     refaced_bgr = self.process_first_face(bgr_image.copy()) if self.first_face else self.process_faces(bgr_image.copy())
-                     enhanced_bgr = enhance_image_memory(refaced_bgr)
-                     enhanced_rgb = cv2.cvtColor(enhanced_bgr, cv2.COLOR_BGR2RGB)
-                     enhanced_pil = Image.fromarray(enhanced_rgb)
-                     frames.append(enhanced_pil)
-                     pbar.update(1)
- 
-             output_path = os.path.join("output", f"{original_name}_{timestamp}.tif")
-             frames[0].save(output_path, save_all=True, append_images=frames[1:], compression="tiff_deflate")
-             print(f"Saved multipage refaced TIFF to {output_path}")
-             return output_path
- 
-         else:
-             bgr_image = cv2.imread(image_path)
-             if bgr_image is None:
-                 raise ValueError("Failed to read input image")
- 
-             refaced_bgr = self.process_first_face(bgr_image.copy()) if self.first_face else self.process_faces(bgr_image.copy())
-             refaced_rgb = cv2.cvtColor(refaced_bgr, cv2.COLOR_BGR2RGB)
-             pil_img = Image.fromarray(refaced_rgb)
-             filename = f"{original_name}_{timestamp}.jpg"
-             output_path = os.path.join("output", filename)
-             pil_img.save(output_path, format='JPEG', quality=100, subsampling=0)
-             output_path = enhance_image(output_path)
-             print(f"Saved refaced image to {output_path}")
-             return output_path
+        self.prepare_faces(faces, disable_similarity=disable_similarity, multiple_faces_mode=multiple_faces_mode)
+        self.first_face = False if multiple_faces_mode else (faces[0].get("origin") is None or disable_similarity)
+        self.partial_reface_ratio = partial_reface_ratio
 
+        ext = osp.splitext(image_path)[1].lower()  #
+        # ext = image_path.rsplit('.',1)[1].lower()
+        os.makedirs("output", exist_ok=True)  #
+
+        original_name = osp.splitext(osp.basename(image_path))[0]
+        timestamp = str(int(time.time()))
+
+        if ext in ['.tif', '.tiff']:
+            pil_img = Image.open(image_path)  #
+            # pil_img = oss_get_image(oss_client=minio_client, path=image_path, data_type="PIL")
+            frames = []
+
+            page_count = 0
+            try:
+                while True:
+                    pil_img.seek(page_count)
+                    page_count += 1
+            except EOFError:
+                pass
+
+            pil_img = Image.open(image_path)  #
+            # pil_img = oss_get_image(oss_client=minio_client, path=image_path, data_type="PIL")
+
+            with tqdm(total=page_count, desc="Processing TIFF pages") as pbar:
+                for page in range(page_count):
+                    pil_img.seek(page)
+                    bgr_image = cv2.cvtColor(np.array(pil_img.convert('RGB')), cv2.COLOR_RGB2BGR)
+                    refaced_bgr = self.process_first_face(bgr_image.copy()) if self.first_face else self.process_faces(bgr_image.copy())
+                    enhanced_bgr = enhance_image_memory(refaced_bgr)
+                    enhanced_rgb = cv2.cvtColor(enhanced_bgr, cv2.COLOR_BGR2RGB)
+                    enhanced_pil = Image.fromarray(enhanced_rgb)
+                    frames.append(enhanced_pil)
+                    pbar.update(1)
+
+            output_path = os.path.join("output", f"{original_name}_{timestamp}.tif")
+            frames[0].save(output_path, save_all=True, append_images=frames[1:], compression="tiff_deflate")
+            print(f"Saved multipage refaced TIFF to {output_path}")
+            return output_path
+
+        else:
+            bgr_image = cv2.imread(image_path)  #
+            # bgr_image = oss_get_image(oss_client=minio_client, path=image_path, data_type="cv2")
+            if bgr_image is None:
+                raise ValueError("Failed to read input image")
+
+            refaced_bgr = self.process_first_face(bgr_image.copy()) if self.first_face else self.process_faces(bgr_image.copy())
+            refaced_rgb = cv2.cvtColor(refaced_bgr, cv2.COLOR_BGR2RGB)
+            pil_img = Image.fromarray(refaced_rgb)
+            filename = f"{original_name}_{timestamp}.jpg"
+            output_path = os.path.join("output", filename)
+            pil_img.save(output_path, format='JPEG', quality=100, subsampling=0)
+            output_path = enhance_image(output_path)
+            print(f"Saved refaced image to {output_path}")
+            return output_path
 
     def extract_faces_from_image(self, image_path, max_faces=5):
         frame = cv2.imread(image_path)
@@ -508,4 +512,4 @@ class Refacer:
         'h264_videotoolbox': '0',
         'h264_nvenc': '0',
         'libx264': '0'
-    }
+    }