不得不讲Rope Crystal的更新版本:蓝宝石(11.20)

文章目录

  • (一)关于 Rope - Sapphire
  • (二)主界面
  • (三)变化参数详解
    • (2.1)预览窗口分离
    • (2.2)标记点控制
    • (2.3)画面方向
    • (2.4)处理强度
    • (2.5)视频/图片
  • (四)总结

(一)关于 Rope - Sapphire

官网仓库:地址
之前的介绍:参考这里。基本的安装,依赖,模型什么的步骤都类似。
需要注意的是,每个版本模型可能有变化,需要重新下载。

这个项目每次更新都会带来很大的提升。
上个版本(9月17日)代号:水晶碎片,带来了CodeFormer。
这个版本(11月20日)代号:蓝宝石,更是好些实用的更新。

最大的变化总结如下:

  1. 分离的视频窗口和控制界面窗口——可以全屏实时预览处理的过程了。

  2. 除了视频,也可以换图片了。

  3. 能够设置脸部顺时针旋转方向(0°,90°,180°,270°)

  4. 视频帧可以添加标记点,标记点上记录了参数设置(包括脸部方向),
    便于不同段的视频用不同的参数替换。
    还添加了停止标记点(不用手动停止也不会换到最后一帧了)。

  5. 快捷键操作,AWSD。上一帧,上一秒,下一帧,下一秒。

其它的变化参考官网日志吧:)

(二)主界面

和上个版本布局一致,但是有些小变化。
不得不讲Rope Crystal的更新版本:蓝宝石(11.20)_第1张图片

(三)变化参数详解

大部分参数和实用方式未变,继续参考这里。
变化的部分如下:

(2.1)预览窗口分离

在这里插入图片描述
播放/录制的左边,两个向上的小箭头,点击后,预览界面会变成独立的窗口。
和控制界面窗口分离,这样预览就可以放非常大,便于看清处理后的样子。
不过分离了,似乎不能合并回来……

窗口分离后界面如下:
不得不讲Rope Crystal的更新版本:蓝宝石(11.20)_第2张图片

(2.2)标记点控制

在这里插入图片描述
进度条的最右边,依次为:

  • 增加标记点
  • 删除标记点
  • 跳到上个标记点
  • 跳到下个标记点
  • 增加结束点。

添加的每个标记点都保存了一套参数配置。
有效范围是当前标记点到下个标记点之前一帧。

PS:修改了某个标记点的参数后,需要再点一次添加。

(2.3)画面方向

在这里插入图片描述
左键单击 :开启/关闭。
滚动鼠标滚轮:更改方向(顺时针0°,90°,180°,270°)

虽然insightface非常强大,但是对于角度太大的面部识别不太好,所以这个参数特别有用。
配合上面的设置标记点功能,可以设定不同段视频人脸的方向(以前需要人工剪辑视频,再分段处理呢)。

PS:错误的方向可能导致识别不到面部,或者变成下面这种样子:
不得不讲Rope Crystal的更新版本:蓝宝石(11.20)_第3张图片

(2.4)处理强度

在这里插入图片描述
左键单击 :开启/关闭。
滚动鼠标滚轮:更改强度(默认100%)。

强度越大,越像Src,同时也会越不自然。

(2.5)视频/图片

在这里插入图片描述
在选择dst目录的下面,点击切换。
在这里插入图片描述
以前这个项目只能换视频,不能换图片,现在可以啦,哇哈哈哈。

(四)总结

其它不是特别重要的变化就不列举了,比如显示遮罩,比如每个按钮都有帮助说明,等等。
细节和现存bug请参考作者的更新日志吧:

总之,这个项目现在功能非常完善了⭐️

### (2023-11-17) Changelog for Rope - Sapphire: ###
**Note: Please check the wiki for installation and link to the new models file**
- Images! In addition to videos, use Rope to swap images. Seamlessly integrated into the current interface.
- Timeline markers. Add markers to the timeline that capture the current settings at a specific frame. When playing back or recording, markers control the options when the frame is reached. Add as many markers as you need!
- Iterations. Apply the swapper model multiple times to a face. It seems to increase likeliness if used carefully.
- Orientation. Sometimes faces are at a bad orientation, like laying down or upside-down. The face detector has problems with this, so Rope now has an option to tell the detector which way the face is oriented. It is also markerable, so you can set markers for it per frame!
- Tool tips on (almost) everything. Tips are in the bottom pane.
- Bug fixes and refactoring

### (2023-11-18) Bug Fixes for Sapphire - Shard: ###
- (fixed) saving the same image multiple times in a row overwrites it. the time is appended when the image is loaded, not saved, so the time is always the same
- (fixed) cf is returning weird colors, similar to when the rgm bgr stuff was messed up. try swapping rgp before netering cf
- (fixed) GFPGAN fp16 might be causing too much harm (going back to original)
- (fixed) the orientation feature might not be unorienting
- (fixed) bug (I hope :D) : When clicking on a registered face name (the one of the left) to swap, on the previous version, clicking back to the same face name would delete the choice and unswap the face. Now it's just blocked and I can't "unswap" (unselect) the face. I'm force to select a face or just close and restart the soft.
- (fixed) update text for all the parser features
- (fixed) "Switch from one timeline marker to another doesn't properly show the correct features configured. Switch to the next frame (and back the previous one is working too) will fix it and show the correct configuration actually configured on the frame."
- (fixed) update mask tooltip
- (fixed) Btw accidentially scrolling Strength below 100% crashed Rope now the third time when CF is enabled. Haven't seen this with GFPGAN yet. I can screenshot the console error if that helps...
- (new) Added Mask view button, moved mask blur to button above mask view
- (new) MouthParser scrolls in negative direction to a)only mask the inside of the mouth, and b) grow the inside mouth mask as the amount increases
- (fixed) GFPGAN and Codeformer will give better results now, especially with details around the eyes and mouth. 
- (fixed) in some cases, pixel values will be > 255
- (new) added undock button to image view
- (new) 'Strength' now has an on/off state
- (fixed) intermittent play bug
- (new) Click the mouse on the playback screen to control play/pause
- (new) Keyboard control with wasd and space 
- (new) Stop Marker. Sets a frame that will stop the video playing/recording

### Known Bugs: ###
- Recording starts on the next frame. It's an issue with how the opencv lib is used. In the future, I hope to get around this with another lib or just working directly with ffmpeg.
- Toggling between img/vid leaves a residual frame in the window. I'll clean this up in the future
- Unfortunately recording is bugged with Threads = 1. I need to change some logic.
- When using Markers, the frames before the first marker will use parameters from the the last settings in your options. Not sure if it is a true bug, but best way to deal with this is to create a marker at the first frame.

我很懒,懒得翻译了……

你可能感兴趣的:(Windows,Python,人工智能/机器学习,rope,crystal,Sapphire,insightface,face)