let5see/IOPaint
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

🎨 完整的 IOPaint 项目更新

Browse Source 
## 主要更新
- ✨ 更新所有依赖到最新稳定版本
- 📝 添加详细的项目文档和模型推荐
- 🔧 配置 VSCode Cloud Studio 预览功能
- 🐛 修复 PyTorch API 弃用警告

## 依赖更新
- diffusers: 0.27.2 → 0.35.2
- gradio: 4.21.0 → 5.46.0
- peft: 0.7.1 → 0.18.0
- Pillow: 9.5.0 → 11.3.0
- fastapi: 0.108.0 → 0.116.2

## 新增文件
- CLAUDE.md - 项目架构和开发指南
- UPGRADE_NOTES.md - 详细的升级说明
- .vscode/preview.yml - 预览配置
- .vscode/LAUNCH_GUIDE.md - 启动指南
- .gitignore - 更新的忽略规则

## 代码修复
- 修复 iopaint/model/ldm.py 中的 torch.cuda.amp.autocast() 弃用警告

## 文档更新
- README.md - 添加模型推荐和使用指南
- 完整的项目源码（iopaint/）
- Web 前端源码（web_app/）

🤖 Generated with Claude Code
This commit is contained in:
let5sne
2025-11-28 17:10:24 +00:00
parent 03b999e9ea
commit 1b87a98261
332 changed files with 77453 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

201
iopaint/plugins/basicsr/LICENSE Normal file
View File

@@ -0,0 +1,201 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright 2018-2022 BasicSR Authors
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

22
iopaint/plugins/basicsr/__init__.py Normal file
View File

@@ -0,0 +1,22 @@
"""
Adapted from https://github.com/XPixelGroup/BasicSR
License: Apache-2.0
As of Feb 2024, `basicsr` appears to be unmaintained. It imports a function from `torchvision` that is removed in
`torchvision` 0.17. Here is the deprecation warning:
UserWarning: The torchvision.transforms.functional_tensor module is deprecated in 0.15 and will be **removed in
0.17**. Please don't rely on it. You probably just need to use APIs in torchvision.transforms.functional or in
torchvision.transforms.v2.functional.
As a result, a dependency on `basicsr` means we cannot keep our `torchvision` dependency up to date.
Because we only rely on a single class `RRDBNet` from `basicsr`, we've copied the relevant code here and removed the
dependency on `basicsr`.
The code is almost unchanged, only a few type annotations have been added. The license is also copied.
Copy From InvokeAI
"""
from .rrdbnet_arch import RRDBNet

80
iopaint/plugins/basicsr/arch_util.py Normal file
View File

@@ -0,0 +1,80 @@
from typing import Type, List, Union
import torch
from torch import nn as nn
from torch.nn import init as init
from torch.nn.modules.batchnorm import _BatchNorm
@torch.no_grad()
def default_init_weights(
module_list: Union[List[nn.Module], nn.Module],
scale: float = 1,
bias_fill: float = 0,
**kwargs,
) -> None:
"""Initialize network weights.
Args:
module_list (list[nn.Module] | nn.Module): Modules to be initialized.
scale (float): Scale initialized weights, especially for residual
blocks. Default: 1.
bias_fill (float): The value to fill bias. Default: 0
kwargs (dict): Other arguments for initialization function.
"""
if not isinstance(module_list, list):
module_list = [module_list]
for module in module_list:
for m in module.modules():
if isinstance(m, nn.Conv2d):
init.kaiming_normal_(m.weight, **kwargs)
m.weight.data *= scale
if m.bias is not None:
m.bias.data.fill_(bias_fill)
elif isinstance(m, nn.Linear):
init.kaiming_normal_(m.weight, **kwargs)
m.weight.data *= scale
if m.bias is not None:
m.bias.data.fill_(bias_fill)
elif isinstance(m, _BatchNorm):
init.constant_(m.weight, 1)
if m.bias is not None:
m.bias.data.fill_(bias_fill)
def make_layer(
basic_block: Type[nn.Module], num_basic_block: int, **kwarg
) -> nn.Sequential:
"""Make layers by stacking the same blocks.
Args:
basic_block (Type[nn.Module]): nn.Module class for basic block.
num_basic_block (int): number of blocks.
Returns:
nn.Sequential: Stacked blocks in nn.Sequential.
"""
layers = []
for _ in range(num_basic_block):
layers.append(basic_block(**kwarg))
return nn.Sequential(*layers)
# TODO: may write a cpp file
def pixel_unshuffle(x: torch.Tensor, scale: int) -> torch.Tensor:
"""Pixel unshuffle.
Args:
x (Tensor): Input feature with shape (b, c, hh, hw).
scale (int): Downsample ratio.
Returns:
Tensor: the pixel unshuffled feature.
"""
b, c, hh, hw = x.size()
out_channel = c * (scale**2)
assert hh % scale == 0 and hw % scale == 0
h = hh // scale
w = hw // scale
x_view = x.view(b, c, h, scale, w, scale)
return x_view.permute(0, 1, 3, 5, 2, 4).reshape(b, out_channel, h, w)

172
iopaint/plugins/basicsr/img_util.py Normal file
View File

@@ -0,0 +1,172 @@
import cv2
import math
import numpy as np
import os
import torch
from torchvision.utils import make_grid
def img2tensor(imgs, bgr2rgb=True, float32=True):
"""Numpy array to tensor.
Args:
imgs (list[ndarray] | ndarray): Input images.
bgr2rgb (bool): Whether to change bgr to rgb.
float32 (bool): Whether to change to float32.
Returns:
list[tensor] | tensor: Tensor images. If returned results only have
one element, just return tensor.
"""
def _totensor(img, bgr2rgb, float32):
if img.shape[2] == 3 and bgr2rgb:
if img.dtype == 'float64':
img = img.astype('float32')
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = torch.from_numpy(img.transpose(2, 0, 1))
if float32:
img = img.float()
return img
if isinstance(imgs, list):
return [_totensor(img, bgr2rgb, float32) for img in imgs]
else:
return _totensor(imgs, bgr2rgb, float32)
def tensor2img(tensor, rgb2bgr=True, out_type=np.uint8, min_max=(0, 1)):
"""Convert torch Tensors into image numpy arrays.
After clamping to [min, max], values will be normalized to [0, 1].
Args:
tensor (Tensor or list[Tensor]): Accept shapes:
1) 4D mini-batch Tensor of shape (B x 3/1 x H x W);
2) 3D Tensor of shape (3/1 x H x W);
3) 2D Tensor of shape (H x W).
Tensor channel should be in RGB order.
rgb2bgr (bool): Whether to change rgb to bgr.
out_type (numpy type): output types. If ``np.uint8``, transform outputs
to uint8 type with range [0, 255]; otherwise, float type with
range [0, 1]. Default: ``np.uint8``.
min_max (tuple[int]): min and max values for clamp.
Returns:
(Tensor or list): 3D ndarray of shape (H x W x C) OR 2D ndarray of
shape (H x W). The channel order is BGR.
"""
if not (torch.is_tensor(tensor) or (isinstance(tensor, list) and all(torch.is_tensor(t) for t in tensor))):
raise TypeError(f'tensor or list of tensors expected, got {type(tensor)}')
if torch.is_tensor(tensor):
tensor = [tensor]
result = []
for _tensor in tensor:
_tensor = _tensor.squeeze(0).float().detach().cpu().clamp_(*min_max)
_tensor = (_tensor - min_max[0]) / (min_max[1] - min_max[0])
n_dim = _tensor.dim()
if n_dim == 4:
img_np = make_grid(_tensor, nrow=int(math.sqrt(_tensor.size(0))), normalize=False).numpy()
img_np = img_np.transpose(1, 2, 0)
if rgb2bgr:
img_np = cv2.cvtColor(img_np, cv2.COLOR_RGB2BGR)
elif n_dim == 3:
img_np = _tensor.numpy()
img_np = img_np.transpose(1, 2, 0)
if img_np.shape[2] == 1: # gray image
img_np = np.squeeze(img_np, axis=2)
else:
if rgb2bgr:
img_np = cv2.cvtColor(img_np, cv2.COLOR_RGB2BGR)
elif n_dim == 2:
img_np = _tensor.numpy()
else:
raise TypeError(f'Only support 4D, 3D or 2D tensor. But received with dimension: {n_dim}')
if out_type == np.uint8:
# Unlike MATLAB, numpy.unit8() WILL NOT round by default.
img_np = (img_np * 255.0).round()
img_np = img_np.astype(out_type)
result.append(img_np)
if len(result) == 1:
result = result[0]
return result
def tensor2img_fast(tensor, rgb2bgr=True, min_max=(0, 1)):
"""This implementation is slightly faster than tensor2img.
It now only supports torch tensor with shape (1, c, h, w).
Args:
tensor (Tensor): Now only support torch tensor with (1, c, h, w).
rgb2bgr (bool): Whether to change rgb to bgr. Default: True.
min_max (tuple[int]): min and max values for clamp.
"""
output = tensor.squeeze(0).detach().clamp_(*min_max).permute(1, 2, 0)
output = (output - min_max[0]) / (min_max[1] - min_max[0]) * 255
output = output.type(torch.uint8).cpu().numpy()
if rgb2bgr:
output = cv2.cvtColor(output, cv2.COLOR_RGB2BGR)
return output
def imfrombytes(content, flag='color', float32=False):
"""Read an image from bytes.
Args:
content (bytes): Image bytes got from files or other streams.
flag (str): Flags specifying the color type of a loaded image,
candidates are `color`, `grayscale` and `unchanged`.
float32 (bool): Whether to change to float32., If True, will also norm
to [0, 1]. Default: False.
Returns:
ndarray: Loaded image array.
"""
img_np = np.frombuffer(content, np.uint8)
imread_flags = {'color': cv2.IMREAD_COLOR, 'grayscale': cv2.IMREAD_GRAYSCALE, 'unchanged': cv2.IMREAD_UNCHANGED}
img = cv2.imdecode(img_np, imread_flags[flag])
if float32:
img = img.astype(np.float32) / 255.
return img
def imwrite(img, file_path, params=None, auto_mkdir=True):
"""Write image to file.
Args:
img (ndarray): Image array to be written.
file_path (str): Image file path.
params (None or list): Same as opencv's :func:`imwrite` interface.
auto_mkdir (bool): If the parent folder of `file_path` does not exist,
whether to create it automatically.
Returns:
bool: Successful or not.
"""
if auto_mkdir:
dir_name = os.path.abspath(os.path.dirname(file_path))
os.makedirs(dir_name, exist_ok=True)
ok = cv2.imwrite(file_path, img, params)
if not ok:
raise IOError('Failed in writing images.')
def crop_border(imgs, crop_border):
"""Crop borders of images.
Args:
imgs (list[ndarray] | ndarray): Images with shape (h, w, c).
crop_border (int): Crop border for each end of height and weight.
Returns:
list[ndarray]: Cropped images.
"""
if crop_border == 0:
return imgs
else:
if isinstance(imgs, list):
return [v[crop_border:-crop_border, crop_border:-crop_border, ...] for v in imgs]
else:
return imgs[crop_border:-crop_border, crop_border:-crop_border, ...]

133
iopaint/plugins/basicsr/rrdbnet_arch.py Normal file
View File

@@ -0,0 +1,133 @@
import torch
from torch import nn as nn
from torch.nn import functional as F
from .arch_util import default_init_weights, make_layer, pixel_unshuffle
class ResidualDenseBlock(nn.Module):
"""Residual Dense Block.
Used in RRDB block in ESRGAN.
Args:
num_feat (int): Channel number of intermediate features.
num_grow_ch (int): Channels for each growth.
"""
def __init__(self, num_feat: int = 64, num_grow_ch: int = 32) -> None:
super(ResidualDenseBlock, self).__init__()
self.conv1 = nn.Conv2d(num_feat, num_grow_ch, 3, 1, 1)
self.conv2 = nn.Conv2d(num_feat + num_grow_ch, num_grow_ch, 3, 1, 1)
self.conv3 = nn.Conv2d(num_feat + 2 * num_grow_ch, num_grow_ch, 3, 1, 1)
self.conv4 = nn.Conv2d(num_feat + 3 * num_grow_ch, num_grow_ch, 3, 1, 1)
self.conv5 = nn.Conv2d(num_feat + 4 * num_grow_ch, num_feat, 3, 1, 1)
self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
# initialization
default_init_weights(
[self.conv1, self.conv2, self.conv3, self.conv4, self.conv5], 0.1
)
def forward(self, x: torch.Tensor) -> torch.Tensor:
x1 = self.lrelu(self.conv1(x))
x2 = self.lrelu(self.conv2(torch.cat((x, x1), 1)))
x3 = self.lrelu(self.conv3(torch.cat((x, x1, x2), 1)))
x4 = self.lrelu(self.conv4(torch.cat((x, x1, x2, x3), 1)))
x5 = self.conv5(torch.cat((x, x1, x2, x3, x4), 1))
# Empirically, we use 0.2 to scale the residual for better performance
return x5 * 0.2 + x
class RRDB(nn.Module):
"""Residual in Residual Dense Block.
Used in RRDB-Net in ESRGAN.
Args:
num_feat (int): Channel number of intermediate features.
num_grow_ch (int): Channels for each growth.
"""
def __init__(self, num_feat: int, num_grow_ch: int = 32) -> None:
super(RRDB, self).__init__()
self.rdb1 = ResidualDenseBlock(num_feat, num_grow_ch)
self.rdb2 = ResidualDenseBlock(num_feat, num_grow_ch)
self.rdb3 = ResidualDenseBlock(num_feat, num_grow_ch)
def forward(self, x: torch.Tensor) -> torch.Tensor:
out = self.rdb1(x)
out = self.rdb2(out)
out = self.rdb3(out)
# Empirically, we use 0.2 to scale the residual for better performance
return out * 0.2 + x
class RRDBNet(nn.Module):
"""Networks consisting of Residual in Residual Dense Block, which is used
in ESRGAN.
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks.
We extend ESRGAN for scale x2 and scale x1.
Note: This is one option for scale 1, scale 2 in RRDBNet.
We first employ the pixel-unshuffle (an inverse operation of pixelshuffle to reduce the spatial size
and enlarge the channel size before feeding inputs into the main ESRGAN architecture.
Args:
num_in_ch (int): Channel number of inputs.
num_out_ch (int): Channel number of outputs.
num_feat (int): Channel number of intermediate features.
Default: 64
num_block (int): Block number in the trunk network. Defaults: 23
num_grow_ch (int): Channels for each growth. Default: 32.
"""
def __init__(
self,
num_in_ch: int,
num_out_ch: int,
scale: int = 4,
num_feat: int = 64,
num_block: int = 23,
num_grow_ch: int = 32,
) -> None:
super(RRDBNet, self).__init__()
self.scale = scale
if scale == 2:
num_in_ch = num_in_ch * 4
elif scale == 1:
num_in_ch = num_in_ch * 16
self.conv_first = nn.Conv2d(num_in_ch, num_feat, 3, 1, 1)
self.body = make_layer(
RRDB, num_block, num_feat=num_feat, num_grow_ch=num_grow_ch
)
self.conv_body = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
# upsample
self.conv_up1 = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
self.conv_up2 = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
self.conv_hr = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
def forward(self, x: torch.Tensor) -> torch.Tensor:
if self.scale == 2:
feat = pixel_unshuffle(x, scale=2)
elif self.scale == 1:
feat = pixel_unshuffle(x, scale=4)
else:
feat = x
feat = self.conv_first(feat)
body_feat = self.conv_body(self.body(feat))
feat = feat + body_feat
# upsample
feat = self.lrelu(
self.conv_up1(F.interpolate(feat, scale_factor=2, mode="nearest"))
)
feat = self.lrelu(
self.conv_up2(F.interpolate(feat, scale_factor=2, mode="nearest"))
)
out = self.conv_last(self.lrelu(self.conv_hr(feat)))
return out