The only places to get a genuine License code for the supporter models are Ko-fi, Unifans, and for China the seller in the Chinese README.
Jasna restores mosaics in videos and images. It is free, has a simple app and a command line, and runs on your GPU.
Start here
- What Jasna does
- What you need
- Quick start
- Help and community
- Supporting the project (supporter models)
Advanced
- 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).
- 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.
- 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 5000 or newer (experimental). RX 7000/9000 are tested; RX 5000/6000 are untested.
- A folder on a local disk, with no Chinese, Japanese, accented or other non-English characters in its path.
More details
- NVIDIA: your GPU needs compute capability 7.5 or higher in NVIDIA's GPU table.
- AMD: see the table below. UNet 4x secondary restoration is supported.
- 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 or AMD Radeon RX 7000/9000 GPU, at least 8 GB VRAM and 16 GB RAM. See What LTX needs.
| AMD GPU | Jasna | LTX |
|---|---|---|
| Radeon RX 9060/9070, Radeon AI PRO R9700 | yes | yes (Windows: beta) |
| Radeon RX 7600–7900, Radeon PRO W7000 | yes | yes (Windows: beta) |
| Radeon 740M/760M/780M/880M/890M, Ryzen AI Max (8050S/8060S) | yes, untested | yes, untested |
| Radeon RX 5000/6000, Radeon PRO W5000/W6000 | yes, untested | no |
| Radeon 610M/660M/680M/820M/840M/860M | yes, untested | no |
| Radeon RX Vega, RX 500 and older | no | no |
- 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. On AMD, first install AMD's driver for ROCm 10.1 (26.10.41.05, download .exe) and reboot. You don't need to install ROCm. -
Linux NVIDIA: run the
jasnafile. -
Linux AMD: first install AMD's AMF video runtime once. We tested AMF 26.20:
curl -fLO https://repo.radeon.com/amf/26.20/amf_installer_26.20.zip unzip amf_installer_26.20.zip sudo bash amf_installer_26.20.sh
Accept AMD's license when prompted, then run
run_jasna_amd.sh. If using Distrobox, install AMF inside the same container as Jasna.
-
- 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. LTX may
still ask to download its model again after an update. On AMD, only UNet 4x
needs this preparation, on its first use.
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.
- 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.
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 (Ko-fi: 14 EUR) or more in total | UNet 4x: makes restored areas sharper. SD 1.5: experimental model for still images. |
| $25 USD (Ko-fi: 23 EUR) | UNet 4x and SD 1.5, plus LTX: much slower than BasicVSR++, but more detail. Includes future updates of this LTX model. |
Supporters who gave $15 USD or more on or before 14 October 2026 get LTX for free.
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.
License codes come only from here:
- Ko-fi
- 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.
- Support on one of the pages above. You get a License code.
- In Jasna, open Activate Jasna, enter the License code, choose This is my PC or Rented or shared PC and press Activate.
One License code works on 3 devices at the same time. To see how many are in use, open Activate Jasna again.
- PC with a TPM 2.0 security chip (most Windows 11 PCs): after one online activation, Jasna works offline. The PC keeps one of your 3 slots. Windows may ask for permission once. A new motherboard or a security chip reset counts as a new PC.
- Other PCs, rented GPUs, and Linux in a container (Docker, distrobox) or virtual machine: Jasna needs internet while it uses supporter models. A device counts only while Jasna runs. See Cloud GPUs.
- Linux with a security chip: to use it offline, run
sudo usermod -aG tss $USER, restart the PC and activate again.
Coming from Jasna 0.11? Your activation carries over the first time you use a supporter model, and Jasna 0.11 keeps working on the same PC.
Have an email and key from Jasna 0.10? They no longer work. Get a new License code from where you bought it.
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).
On NVIDIA, the first job prepares the models for steps 2 and 4 (and UNet 4x,
if used) for your exact GPU; on AMD, only UNet 4x. 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 video in 4 passes: find mosaics, prepare, restore with a diffusion model, save. It is slower but can add more real detail. Its quality choices: Basic (about 1.7x faster than Standard), Standard (default), Good (about 1.5x slower), High (about 2.5x slower) and Top (about 5x slower). See Choosing models.
LTX jobs and jobs with ranges can pause and continue. See Pause and continue.
The command line can do most of what the app does (not the Video Player, LTX seed previews, mask suggestions or interactive image mode).
# One video
jasna --input input.mp4 --output output.mkv
# One image
jasna --input photo.png --output restored.png
# A whole folder
jasna --input input_folder --output output_folderjasna --help lists all options. See the CLI reference.
- Using the GUI: queue, presets, output names, Video Player, activation.
- Choosing models: detection models, BasicVSR++ or LTX, secondary restoration, SD 1.5 for images.
- Restoring only parts of a video: Segment Editor, mosaic scan, LTX only for big mosaics.
- VR180 videos: how side-by-side and top/bottom VR are handled.
- Tuning VRAM and GPU usage: clip size, overlap, what to do when VRAM runs out.
- Advanced processing: denoise, 60→30 FPS, color LUT, sharpening, encoder quality, settings saved in the video, actions after the queue.
- Streaming: watch in the browser or in Stash.
- Cloud GPUs: Jasna on a rented GPU (RunPod, Vast).
- CLI reference: all command line options.
- Running from source: for developers. From source you can use the free BasicVSR++; activation and supporter models need the official release.
Time to restore a whole 3:22 video with BasicVSR++ on an RTX 5090 (Linux). Lower is better.
| Input | Lada 0.11.0 | Jasna v0.9.1 |
|---|---|---|
| 720p H.264 | 01:47 | 00:32 (3.4x faster) |
| 1080p H.264 | 02:02 | 00:34 (3.6x faster) |
| 2160p H.264 | 04:56 | 01:03 (4.7x faster) |
GPU memory, older versions and how it was measured
GPU memory used (typical / peak, in GB). — means not measured. Lada uses
less GPU memory than Jasna.
| Input | Lada | v0.4.1 | v0.5.0 | v0.9.0 | v0.9.1 |
|---|---|---|---|---|---|
| 720p H.264 8-bit | 1.8/3.1 | 17.6/19.9 | 8.6/9.0 | 8.6/9.1 | 4.2/4.6 |
| 1080p H.264 8-bit | 2.0/3.3 | 18.9/21.4 | 9.5/10.2 | 9.3/10.1 | 4.8/5.6 |
| 2160p H.264 8-bit | 2.6/4.1 | 26.0/30.5 | 12.9/15.0 | 11.4/15.4 | 7.2/10.9 |
| 8K VR HEVC 60 fps (15 s) | — | — | — | 17.1/18.3 | 5E66 |
Times for older versions (v0.4.1: 01:35 / 01:46 / 03:23; v0.5.0: 00:45 / 00:47 / 01:22; v0.9.0: 00:34 / 00:39 / 01:15 for 720p / 1080p / 2160p; 8K VR: 00:34), the test settings, RAM use and every codec are in the full benchmark report. Older full-length videos: legacy report.
Jasna's public application source is AGPL-3.0. Models and bundled dependencies keep their own terms. See licensing and source availability, model notices and the release source correspondence.
- Lada (Codeberg): Jasna is inspired
by Lada and in some places based on it. The
mosaic_restoration_1.2model used by Jasna was trained by ladaapp, the author of Lada. - ZeLeFans: for the VR detection model and the detailed analysis of mosaic shapes and VR projection.