TAS.
New TAS Standalone, a desktop app for Windows

Enhance anime.
Frame by frame.

An open-source AI video toolkit built for anime. Interpolation, upscaling, depth, segmentation and restoration in one pipeline, as a desktop app, an After Effects panel or a command line.

Download TAS Standalone Source on GitHub
  • v2.10.0
  • Windows · macOS · Linux
  • CUDA · TensorRT · ROCm · DirectML · OpenVINO · MPS
The same frame after TAS upscaled it with the adore model: crisp spires, defined branches, legible window lights
A soft, low-quality 1280×720 master of the same frame, with smeared detail
Before · 1280×720 master After · adore 2×
A soft 1280×720 master, upscaled 2× with --upscale_method adore. Drag the handle.

Capabilities

One toolkit. Every step of the post-production chain.

Frame interpolation

Multiply frames between keyframes with RIFE 4.22-lite, RIFE 4.25-heavy and GMFSS for fluid in-betweens. Scene-change detection built in.

RIFE · GMFSS · Scene cut

AI upscaling

2× resolution with anime-tuned models. ShuffleCugan, SPAN, Adore, Fallin Strong and the ArtCNN family all supported.

ShuffleCugan · SPAN · Adore · Cyte · ArtCNN

Depth maps

Monocular depth estimation via Depth Anything V2 and V3, temporally-stable Video variants and the anime-tuned Limbo models, for After Effects 2.5D parallax and shader work.

DA V2 / V3 · Video · Limbo

BG / FG segmentation

Alpha-channel mattes for character isolation. Clean edges on hair, armor and line art, ready for compositing in Resolve or AE.

ISNet · BiRefNet · Alpha out

Restoration

SCUNet denoising, anime-specific sharpening and deblock. Rescue old broadcast masters without destroying cel detail.

SCUNet · NAFNet · DeHalo · Anime1080Fixer

Deduplication

Drops redundant or near-identical cels before the GPU touches them. Fewer frames in means faster passes out. Swap detection with --dedup_method.

SSIM · MSE · FlowNetS · VMAF

Apps

Three ways in. One engine.

Click through it on the desktop, render from inside After Effects, or script every pass from a terminal. Same models, same flags, same results.

New Windows 10 / 11 x64

TAS Standalone

The whole TAS pipeline in a desktop app. Drop in a clip, switch steps on, press Run. No Python and no terminal: the app installs the engine itself on first launch.

Download for Windows ~60 MB installer · no admin rights needed

Free with the DirectML and CPU backends. The OpenVINO, CUDA, TensorRT and ROCm backends unlock with a $3+ sponsorship on GitHub Sponsors or Patreon.

  • Every TAS option as a real control. Model lists come straight from TAS's own parser, so nothing is missing.
  • Watch it work. A live preview of the frames being rendered, with frame count, FPS and ETA.
  • Trim, queue, preset. Cut the clip before you render, line up a batch and save the chains you reuse.
  • Picks the right runtime. Detects NVIDIA or AMD hardware for the GPU install, and updates itself in the background.
TAS Standalone: the Chain column with Upscale and Interpolate switched on, the Upscale card expanded to its factor and model settings, and a preview of the loaded anime clip beside a Run button
TAS Standalone 2.10 · Upscale and Interpolate chained on a 720p clip

TAS-AdobeEdition

After Effects · Premiere Pro alpha · Windows · macOS

The TAS panel, docked inside your Adobe workflow. Queue shots, pick a preset and render without leaving your comp. Full After Effects support, with Premiere Pro in alpha.

The TAS-AdobeEdition panel docked inside After Effects

The CUDA, TensorRT and OpenVINO backends are paid in TAS-AdobeEdition (MPS coming).

Python CLI

main.py · Python 3.14 · AGPL-3.0

Every pass is a flag on main.py. Script it, batch it, drop it in a Makefile. It's just a CLI, and it's what the other two run underneath.

$ python main.py --input ep01.mkv \
    --upscale_method span-tensorrt \
    --interpolate_method rife4.25-tensorrt
› stage: interpolate  · rife4.25-tensorrt
› stage: upscale      · span-tensorrt (2×)
› done · ep01-Int2-Up2.mkv

Free and open source. Every model, every backend.

Pipeline

One file in. Six stages of inference out.

Every pass TAS runs shares a single in-memory frame queue, with no redundant disk writes between stages. The steps you switch on decide which stages light up.

  1. Input

    Local file, batch list or YouTube URL.

    mp4 · mkv · mov · webm

  2. Deduplication

    Drops redundant cels before the GPU ever sees them.

    SSIM · MSE · FlowNetS · VMAF

  3. Interpolation

    Synthesizes in-between frames from neighboring keyframes.

    RIFE 4.6 → 4.25-heavy · GMFSS · Elexor

  4. Upscaling

    2× with anime-tuned super-resolution architectures.

    ShuffleCugan · SPAN · Adore · OpenProteus · AniScale2

  5. Restoration

    Denoise, deblock, dejpeg, sharpen and darken line art. Chainable.

    SCUNet · NAFNet · Anime1080Fixer · FastLineDarken

  6. Encoded output

    FFmpeg hand-off with animation-tuned x264/x265 or NVENC.

    x264_animation_10bit · x265 · NVENC · AV1 · ProRes

Models

Every weight that ships with TAS.

74 models across five families in TAS 2.10, before backend variants. Bring your own with --custom_model: Spandrel formats (.pt, .pth, .ckpt, .safetensors) on CUDA, .onnx on TensorRT, DirectML and OpenVINO.

Interpolation 17

RIFE · GMFSS · DistillDRBA

  • rife4.6
  • rife4.15
  • rife4.15-lite
  • rife4.16-lite
  • rife4.17
  • rife4.18
  • rife4.20
  • rife4.21
  • rife4.22
  • rife4.22-lite
  • rife4.25
  • rife4.25-lite
  • rife4.25-heavy
  • rife_elexor
  • distildrba
  • distildrba-lite
  • gmfss

Upscaling 23

SPAN · ShuffleCugan · ArtCNN · Cyte

  • shufflecugan
  • adore
  • span
  • cyte
  • open-proteus
  • aniscale2
  • rtmosr
  • saryn
  • gauss
  • fallin_soft
  • fallin_strong
  • animesr
  • figsr
  • smosr
  • artcnn_c4f16
  • artcnn_c4f16_dn
  • artcnn_c4f16_ds
  • artcnn_c4f32
  • artcnn_c4f32_dn
  • artcnn_c4f32_ds
  • artcnn_r8f64
  • artcnn_r16f96
  • maxine (NVIDIA VSR, 9 modes)

Restoration 18

Denoise · Deblock · Line art

  • anime1080fixer
  • scunet
  • nafnet
  • dpir
  • real-plksr
  • gater3
  • deh264_real
  • deh264_span
  • hurrdeblur
  • dehalo
  • deepdeband-f
  • fastlinedarken
  • linethinner-lite
  • linethinner-medium
  • linethinner-heavy
  • autocas
  • maxine-denoise (4 levels)
  • maxine-deblur (4 levels)

Depth 14

Depth Anything V2 / V3 · Video · Limbo

  • small_v2
  • small_v3
  • base_v3
  • large_v3
  • video_small_v2
  • video_small_v3
  • video_base_v3
  • limbo
  • limbo_v2
  • video_limbo
  • video_limbo_v2
  • og_small_v2
  • og_video_small_v2
  • og_large_v3

Segmentation 2

ISNet · BiRefNet · Alpha matte output

  • anime
  • birefnet

CLI

One invocation. Whole chain.

Every pass is a flag. Chain them. Auto-enable is real: specifying a *_method turns the feature on for you.

main.py · full anime restoration pipeline 
$ python main.py --input anime_episode.mkv \
    --upscale_method shufflecugan-tensorrt \
    --interpolate_method rife4.25-tensorrt --ensemble \
    --restore_method anime1080fixer-tensorrt \
    --dedup_method ssim-cuda \
    --sharpen --sharpen_sens 30 \
    --encode_method x264_animation_10bit --bit_depth 10bit
› resolving backends · tensorrt engines cached
› stage: dedup        · ssim-cuda
› stage: interpolate  · rife4.25-tensorrt (ensemble)
› stage: upscale      · shufflecugan-tensorrt (2×)
› stage: restore      · anime1080fixer-tensorrt + sharpen
› encoder · libx264 · animation · 10-bit

Install

Install once. Run everywhere.

Pick the app on Windows, or grab the prebuilt CLI for Windows x64 and Apple Silicon macOS. Neither needs Python installed. Linux runs from source.

Recommended for Windows TAS Standalone Desktop app. Installs the engine, its dependencies and FFmpeg for you, then keeps itself up to date. Windows 10 / 11 · x64 · v2.10.0 Download installer Not code-signed yet, so Windows SmartScreen may warn on first run. Choose More info, then Run anyway.
PowerShell · CLI one-line install 
> irm tas.nevermindnilas.dev/install.ps1 | iex
Windows CLI x64 · CUDA / TensorRT / DirectML / OpenVINO macOS CLI Apple Silicon · MPS · needs Homebrew Build from source Windows · macOS · Linux · Python 3.14

FAQ

The honest answers.

Standalone, AdobeEdition or the CLI: which one do I want?

TAS Standalone if you're on Windows and want to point, click and render. TAS-AdobeEdition if you live in After Effects and want TAS inside your comp. The CLI if you script, batch on a server, run Linux or want every backend for free. All three drive the same engine, so a model or flag behaves the same everywhere.

Does TAS work with my GPU?

If you have an RTX 20/30/40/50 card, use the CUDA + TensorRT build for the best speed. GTX 16 series works on CUDA. Recent AMD cards can run the ROCm backend, and older AMD cards plus GTX 10 series (Pascal) run on DirectML. Intel iGPUs and dGPUs run on OpenVINO. Apple Silicon runs on MPS. Pick the matching -tensorrt, -rocm, -directml, -openvino or -mps model suffix. TAS Standalone detects your hardware and installs the right runtime for you.

Windows warned me when I ran the Standalone installer. Is it safe?

The installer isn't code-signed yet, so SmartScreen shows "Windows protected your PC" for every new release. Choose More info, then Run anyway. Only download it from the official GitHub releases, which is where every link on this page points. It installs per user, so it never asks for admin rights.

Does it run on macOS or Linux?

macOS: yes, on Apple Silicon, through the CLI and TAS-AdobeEdition. Every release ships a prebuilt macOS-arm64 zip alongside the Windows one, and MPS accelerates interpolation, upscaling, restoration, depth and motion blur. Be aware of the gaps: segmentation, dedup, scene detection and stabilization have no MPS path and fall back to CPU, there is no TensorRT / DirectML / OpenVINO, there is no hardware video encoder, and Intel Macs are not supported. You also need Homebrew, because TAS installs FFmpeg through it on first run rather than bundling it.

Linux: runs from source with the CUDA or lite dependency profile, but there is no prebuilt binary yet. TAS Standalone is Windows only for now.

Can I use my own models?

Yes. The --custom_model flag accepts .pt, .pth, .ckpt and .safetensors for the CUDA compact path via Spandrel, and .onnx for the -directml, -openvino and -tensorrt variants. Just match the backend suffix to the file format. TAS Standalone exposes the same option as a file picker on the Upscale step.

Do I need Python installed?

No. TAS Standalone downloads and sets up the engine on first launch, and the prebuilt Windows and macOS CLI releases bundle everything they need. On first run TAS will fetch FFmpeg automatically if it isn't already present. You only need Python if you're cloning the repo to develop, in which case pip install -r requirements.txt plus one of the extra-requirements-* profiles will get you going.

Is TAS really free and open source?

The CLI is. The source is on GitHub under the AGPL-3.0 license. Fork it, modify it, redistribute it, just keep any network-service derivatives open under the same license.

The two apps are free to download and closed source. TAS Standalone is free with DirectML and CPU, and its OpenVINO, CUDA, TensorRT and ROCm backends need a $3+ sponsorship. In TAS-AdobeEdition the CUDA, TensorRT and OpenVINO backends are paid (MPS coming).

How is this funded?

The CLI is unpaid work. The apps' GPU backends, GitHub Sponsors and Patreon cover model training and hardware. Link your sponsor account inside TAS Standalone to unlock its GPU backends. Sponsors also get a role on the Discord: run /verify_sponsor and follow the link it gives you.

Will there be new features?

Yes. New models, backends and restoration passes land regularly, and TAS Standalone and TAS-AdobeEdition (After Effects, with Premiere Pro support in alpha) are both under active development. Follow releases on GitHub or join the Discord for nightly builds.

Point it at a file.

Desktop app, After Effects panel or free CLI. Every model, one engine.

Download TAS Standalone Get the CLI Join Discord

TAS is mostly unpaid work. If it saves you render hours, support it on GitHub Sponsors or Patreon. Either one unlocks the GPU backends in TAS Standalone and the sponsor role on Discord via /verify_sponsor.