1b87a98261
## 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
23 lines
926 B
Python
23 lines
926 B
Python
"""
|
|
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
|