v3.3.0 3.3.0 版
Released June 13th, 2023 发布于 2023 年 6 月 13 日
Changes from v3.2.9 与 v3.2.9 相比的变化
Adds a new enhancement model Iris for face enhancement and/or improving low-to-medium quality progressive/interlaced videos
添加了新的增强模型 Iris ,用于面部增强和/或改进中低质量逐行扫描/隔行扫描视频
Adds Recover Original Detail option for Proteus, Iris, and Artemis models
为普罗透斯、Iris和阿尔忒弥斯模型添加 Recover Original Detail 选项
Adds DPX support 添加 DPX 支持
Maps all audio streams with metadata to output
将所有音频流与元数据映射到输出
Fixes issue with estimate not working for certain image sequences
修复了估计不适用于某些图像序列的问题
Misc bug fixes and improvements 杂项错误修复和改进
Known Issues: 已知问题:
Videos with mismatched metadata and streams will display incorrect duration
元数据和流不匹配的视频将显示不正确的时长
Frame number preview length may shorten on app restart
应用重启时帧数预览长度可能会缩短
Enhancement model - Iris 增强模型 - Iris
Primary aim of the model is to improve human faces
该模型的主要目的是改善人脸
This model is also designed to enhance low- to medium-quality video, particularly, with noise and compression artifacts. Note, the model tends to lose details on high-quality videos
该模型还旨在增强中低质量的视频,特别是具有噪点和压缩伪影的视频。请注意,该模型往往会丢失高质量视频的细节
This model is trained to work on all three categories - progressive, interlaced, interlaced progressive
此模型经过训练,可处理所有三个类别 - 逐行扫描、隔行扫描、隔行渐进
Please look at some examples in the roadmap post 109
Recover Original Detail 恢复原始细节
Purpose of this slider is to retain details from original source if the model’s output is overly smoothed
此滑块的目的是在模型的输出过于平滑时保留原始源的细节
It adds the source texture details to the model’s output to bring back the original details
它将源纹理详细信息添加到模型的输出中,以恢复原始细节 |