Kruk2 / jasna
本文为原文前 6,000 字符的节选翻译,完整内容请查看原文。
The only places to get a genuine License code for the supporter models are Buy Me a Coffee, Unifans, and for China the seller in the Chinese README.
支持者模型的正版许可证码只能通过 Buy Me a Coffee、Unifans 或 闲鱼 获取。
English | 日本語 | 中文 Jasna Jasna restores mosaics in videos and images. It is free, has a simple app and a command line, and runs on your GPU.
English | 日本語 | 中文 Jasna Jasna 可以修复视频和图像中的马赛克。它是免费的,拥有简单的应用程序和命令行界面,并在您的 GPU 上运行。
Contents Start here What Jasna does What you need Quick start Help and community Supporting the project (supporter models) Advanced How Jasna works Command line All guides Benchmarks Licensing Acknowledgments
目录:从这里开始、Jasna 的功能、系统需求、快速入门、帮助与社区、支持项目(支持者模型)、进阶、Jasna 的工作原理、命令行、所有指南、基准测试、许可、致谢。
What Jasna does Finds mosaics in a video and restores them. The rest of the picture is not touched. Two restoration models: fast BasicVSR++ (free) and slow but more detailed LTX (for supporters, NVIDIA only). Restores only the parts you choose, with a preview, in the Segment Editor. Works with VR180 videos and still images (SD 1.5, for supporters). Lets you watch a video restored live in the Video Player, without making a file.
Jasna 的功能:查找视频中的马赛克并进行修复,画面的其余部分不受影响。提供两种修复模型:快速的 BasicVSR++(免费)和缓慢但细节更丰富的 LTX(仅限支持者,仅限 NVIDIA)。在分段编辑器中,您可以选择仅修复特定部分并进行预览。支持 VR180 视频和静态图像(SD 1.5,仅限支持者)。允许您在视频播放器中实时观看修复后的视频,无需生成文件。
What you need NVIDIA GTX 16-series / RTX 20-series or newer, with a recent driver (610+ on Windows, 580+ on Linux). GTX 10-series and older don’t work. Or AMD Radeon RX 7000/9000 (experimental). A folder on a local disk, with no Chinese, Japanese, accented or other non-English characters in its path.
系统需求:NVIDIA GTX 16 系列 / RTX 20 系列或更新型号,并配备较新的驱动程序(Windows 为 610+,Linux 为 580+)。GTX 10 系列及更旧型号无法使用。或者 AMD Radeon RX 7000/9000(实验性支持)。需要一个位于本地磁盘的文件夹,且路径中不能包含中文、日文、重音符号或其他非英文字符。
More details NVIDIA: your GPU needs compute capability 7.5 or higher in NVIDIA’s GPU table. AMD: a GPU supported by ROCm (Radeon RX 7000/9000, Radeon 780M/760M/740M, Ryzen AI). On Windows, AMD Adrenalin driver 26.8.1 or newer. Secondary restoration and LTX are NVIDIA only. Disk format: NTFS on Windows; ext4, Btrfs, XFS or ZFS on Linux. Network disks are not supported. Use an SSD; on a hard disk (HDD) Jasna starts and loads models slowly. LTX needs an NVIDIA RTX GPU, at least 8 GB VRAM and 16 GB RAM. See What LTX needs.
更多详情:NVIDIA GPU 需要在 NVIDIA GPU 表中具备 7.5 或更高的计算能力。AMD GPU 需要支持 ROCm(Radeon RX 7000/9000、Radeon 780M/760M/740M、Ryzen AI)。在 Windows 上,需要 AMD Adrenalin 驱动程序 26.8.1 或更新版本。二次修复和 LTX 仅限 NVIDIA。磁盘格式:Windows 上为 NTFS;Linux 上为 ext4、Btrfs、XFS 或 ZFS。不支持网络磁盘。请使用 SSD;在机械硬盘 (HDD) 上,Jasna 的启动和模型加载速度会很慢。LTX 需要 NVIDIA RTX GPU、至少 8 GB 显存和 16 GB 内存。请参阅“LTX 的需求”。
Quick start Download the release for your system and GPU. Unpack it into a folder with no Chinese, Japanese, accented or other non-English characters in the path. Start the app: Windows: double-click jasna.exe. Linux NVIDIA: run the jasna file. Linux AMD: run run_jasna_amd.sh. Add a video, choose settings and click the ▶ button at the bottom. Your first job is slow. On NVIDIA, Jasna first prepares the models for your exact GPU. This takes about 15–60 minutes, only once. Close other apps and don’t use the PC during this time. When you update Jasna, copy the model_weights folder to the new version, so you don’t wait again. Every setting has a tooltip: move the mouse over the ⓘ icon. Out of GPU memory (VRAM)? Lower Max Clip Size, for example from 90 to 60. See Tuning.
快速入门:下载适用于您系统和 GPU 的版本。将其解压到路径中不含中文、日文、重音符号或其他非英文字符的文件夹中。启动应用程序:Windows 双击 jasna.exe;Linux NVIDIA 运行 jasna 文件;Linux AMD 运行 run_jasna_amd.sh。添加视频,选择设置,然后点击底部的 ▶ 按钮。您的第一次任务会很慢。在 NVIDIA 上,Jasna 会首先为您的特定 GPU 准备模型。这大约需要 15-60 分钟,仅需一次。在此期间请关闭其他应用程序,不要使用电脑。更新 Jasna 时,请将 model_weights 文件夹复制到新版本中,这样就不必再次等待。每个设置都有工具提示:将鼠标悬停在 ⓘ 图标上即可查看。显存 (VRAM) 不足?请降低“最大剪辑大小”(Max Clip Size),例如从 90 降至 60。请参阅“调整”。
Help and community App guide: the queue, presets, output names, the Video Player and activation. SLS Discord: examples, help and settings. Jasna has a new channel; older posts stay in the old channel (archived). Please don’t be too weird. Problem? Click Logs at the bottom of the app, then Export to save a log file. Attach it when you ask for help.
帮助与社区:应用程序指南涵盖队列、预设、输出名称、视频播放器和激活。SLS Discord 提供示例、帮助和设置。Jasna 有一个新频道;旧帖子保留在旧频道(已归档)中。请保持正常交流。遇到问题?点击应用程序底部的“日志”(Logs),然后点击“导出”(Export) 保存日志文件。在寻求帮助时请附上该文件。
Supporting the project Jasna is free. Your support pays for training new models, mostly GPU rental. Supporters get a License code for the supporter models: Support Models $15 USD or more in total UNet 4x: makes restored areas sharper. SD 1.5: experimental model for still images. $25 USD UNet 4x and SD 1.5, plus LTX: much slower than BasicVSR++, but more detail. NVIDIA only. Includes future updates of this LTX model. Supporters who gave $15 USD or more on or before 14 October 2026 get LTX for free.
支持项目:Jasna 是免费的。您的支持用于支付训练新模型的费用,主要是 GPU 租赁。支持者将获得用于支持者模型的许可证码:支持者模型总额 15 美元或以上可获得 UNet 4x(使修复区域更清晰)和 SD 1.5(用于静态图像的实验性模型)。25 美元可获得 UNet 4x、SD 1.5 以及 LTX(比 BasicVSR++ 慢得多,但细节更丰富,仅限 NVIDIA)。包含此 LTX 模型的未来更新。在 2026 年 10 月 14 日或之前捐赠 15 美元或以上的支持者可免费获得 LTX。
Before you choose LTX: Look at these LTX samples: 1, 2, 3, 4, 5, 6, 7, 8. Explore the new channel and the old channel (archived) on SLS Discord for more samples. Run LTX in Trial mode (speed test) on your PC. It is free and shows if your GPU can run LTX and how long it takes. The video is not restored. See What LTX needs. More examples: UNet 4x, SD 1.5, more SD 1.5.
在选择 LTX 之前:查看这些 LTX 示例:1, 2, 3, 4, 5, 6, 7, 8。在 SLS Discord 上探索新频道和旧频道(已归档)以获取更多示例。在您的电脑上以试用模式(速度测试)运行 LTX。它是免费的,可以显示您的 GPU 是否能运行 LTX 以及所需时间。视频不会被修复。请参阅“LTX 的需求”。更多示例:UNet 4x, SD 1.5, 更多 SD 1.5。
Where to support License codes come only from here: Buy Me a Coffee (crypto works too) Unifans For China: see the Chinese README Anyone else selling Jasna, codes or modified files is a scam: their keys don’t work, and their files can run hidden code on your PC. Download Jasna only from GitHub.
支持渠道:许可证码仅来自以下渠道:Buy Me a Coffee(也支持加密货币)、Unifans。中国用户请参阅中文 README。任何其他人出售 Jasna、许可证码或修改过的文件都是诈骗:他们的密钥无效,且他们的文件可能在您的电脑上运行隐藏代码。请仅从 GitHub 下载 Jasna。
How to activate Support on one of the pages above. You get a License code. In Jasna, open Activate Jasna, enter the License code and press Activate online. No internet on that PC, or it fails? Choose Manual, see Activate supporter models. One License code works on 3 PCs or cloud workspaces. After activation, Jasna works offline. Rented GPUs: see Cloud GPUs. What counts as a new PC: on Windows, a new motherboard; on Linux, a fresh Linux install. Each uses one of your 3 slots. Reinstalling Windows or changing the GPU, disk or RAM does not: just activate again with the same License code. A few Windows PCs have no real motherboard ID; on those, a new system disk also counts as a new PC. Have an email and key from Jasna 0.10? They no longer work. Get a new License code from where you bought it.
如何激活:在上述页面之一进行支持,您将获得一个许可证码。在 Jasna 中,打开“激活 Jasna”(Activate Jasna),输入许可证码并点击“在线激活”(Activate online)。如果该电脑没有网络或激活失败?请选择“手动”(Manual),参阅“激活支持者模型”。一个许可证码可在 3 台电脑或云工作区上使用。激活后,Jasna 可离线工作。租赁的 GPU 请参阅“云 GPU”。什么算作新电脑:在 Windows 上,更换主板;在 Linux 上,全新安装 Linux。每种情况都会占用您 3 个名额中的一个。重装 Windows 或更换 GPU、磁盘或内存不会占用名额:只需使用相同的许可证码再次激活即可。少数 Windows 电脑没有真实的主板 ID;在这些电脑上,更换系统盘也会被视为新电脑。如果您有来自 Jasna 0.10 的电子邮件和密钥?它们已不再有效。请从您购买的地方获取新的许可证码。
Advanced How Jasna works Almost everything runs on the GPU, from reading the video to saving it. Decode the video on the GPU (NVDEC on NVIDIA, AMF on AMD). Detect mosaics in each frame (default model rfdetr-v6). Track each mosaic over time and group its frames into clips (up to Max Clip Size frames). Clips end at scene cuts, so two different shots are never mixed. Restore each clip as a 256x256 picture with BasicVSR++. Clips overlap a little, so there are no visible jumps between them. Optional secondary restoration (UNet 4x, RTX Super Res or Topaz TVAI) makes the restored picture bigger and sharper. Blend the restored picture back into the original frame. Only the mosaic area changes. Encode with the GPU encoder (NVENC on NVIDIA, AMF on AMD). Audio is copied (encoded again only if the output format can’t hold it). The first job is slow because the models for steps 2 and 4 (and UNet 4x, if used) are prepared for your exact GPU (NVIDIA only). The result is saved in model_weights and used again later. You can copy it to a newer Jasna version. LTX works differently. It goes over the vid
进阶:Jasna 的工作原理。几乎所有操作都在 GPU 上运行,从读取视频到保存视频。在 GPU 上解码视频(NVIDIA 使用 NVDEC,AMD 使用 AMF)。检测每一帧中的马赛克(默认模型 rfdetr-v6)。随时间跟踪每个马赛克,并将其帧分组为剪辑(最多为“最大剪辑大小”帧)。剪辑在场景切换处结束,因此永远不会混合两个不同的镜头。使用 BasicVSR++ 将每个剪辑修复为 256x256 的图像。剪辑之间有少量重叠,因此不会出现明显的跳跃。可选的二次修复(UNet 4x、RTX Super Res 或 Topaz TVAI)使修复后的图像更大、更清晰。将修复后的图像混合回原始帧中,仅马赛克区域发生变化。使用 GPU 编码器进行编码(NVIDIA 使用 NVENC,AMD 使用 AMF)。音频会被复制(仅当输出格式不支持时才会重新编码)。第一次任务很慢,因为步骤 2 和 4(以及如果使用了 UNet 4x)的模型是为您特定的 GPU(仅限 NVIDIA)准备的。结果保存在 model_weights 中,以后会再次使用。您可以将其复制到较新的 Jasna 版本中。LTX 的工作方式不同,它会遍历视频。