Vapoursynth AnimeSR: Difference between revisions
New filter page (via create-page on MediaWiki MCP Server) |
Update to current Hybrid behaviour; code as <pre> (via update-page on MediaWiki MCP Server) |
||
| Line 23: | Line 23: | ||
| Tensor RT || trt || on/off || off || Uses TensorRT; the engine is built on the first run and cached. | | Tensor RT || trt || on/off || off || Uses TensorRT; the engine is built on the first run and cached. | ||
|- | |- | ||
| FP16 || – || on/off || off || | | FP16 || – || on/off || off || Half precision (16-bit float clip), with and without Tensor RT. | ||
|- | |- | ||
| max WSS || trt_workspace_size || 0 – 1073741824 || 0 || TensorRT workspace size; 0 = not set. | | max WSS || trt_workspace_size || 0 – 1073741824 || 0 || TensorRT workspace size; 0 = not set. | ||
| Line 32: | Line 32: | ||
== Example == | == Example == | ||
Default settings on a 10-bit YUV 4:2:0 source (640x356), resized to 1280x712: | Default settings on a 10-bit YUV 4:2:0 source (640x356), resized to 1280x712: | ||
< | <pre> | ||
from vsanimesr import animesr as AnimeSR | from vsanimesr import animesr as AnimeSR | ||
# adjusting color space from YUV420P10 to RGBS for vsAnimeSR | # adjusting color space from YUV420P10 to RGBS for vsAnimeSR | ||
| Line 40: | Line 40: | ||
# resizing 2560x1424 to 1280x712 | # resizing 2560x1424 to 1280x712 | ||
clip = core.fmtc.resample(clip, w=1280, h=712, kernel="spline64", interlaced=False, interlacedd=False) | clip = core.fmtc.resample(clip, w=1280, h=712, kernel="spline64", interlaced=False, interlacedd=False) | ||
</ | </pre> | ||
== How Hybrid calls it == | == How Hybrid calls it == | ||
* Selected with Resize enabled and Resizer set to AnimeSR (see [[Vapoursynth Resizer]]). | * Selected with Resize enabled and Resizer set to AnimeSR (see [[Vapoursynth Resizer]]). | ||
* The clip is converted to 32-bit float RGB (16-bit float with | * The clip is converted to 32-bit float RGB (16-bit float with FP16) and padded to mod 4. | ||
* The output is always 4× the input. If that differs from the target, fmtconv resizes it with the ''Resizer'' kernel to the exact size. With separately filtered fields the target height is halved. | * The output is always 4× the input. If that differs from the target, fmtconv resizes it with the ''Resizer'' kernel to the exact size. With separately filtered fields the target height is halved. | ||
* Model and GPU ID are always written (the plugin's own default model is v2); max WSS only when it is not 0. | * Model and GPU ID are always written (the plugin's own default model is v2); max WSS only when it is not 0. | ||
Latest revision as of 09:47, 16 November 2026
AnimeSR (TencentARC) is a real-world super-resolution network for animation videos that always upscales by 4. It is one of the resizers of Vapoursynth Resizer and runs on an NVIDIA GPU through PyTorch.
Filtering → Vapoursynth → Frame → Resize

What it does
The network is recurrent: each output frame and an internal state are passed on to the next frame. It therefore works best when the clip is rendered from start to end; jumping around in a preview can give different results. Hybrid resizes the 4× result to the exact output size afterwards.
Requirements
- Windows, Hybrid's torch add-on and an NVIDIA GPU with CUDA.
- Tensor RT additionally needs Torch-TensorRT from the add-on; it cannot be combined with TensorRT in vs-mlrt filters in the same script.
Settings
| Control | Parameter | Range / values | Hybrid default | Meaning |
|---|---|---|---|---|
| Model | model | AnimeSR_v1, AnimeSR_v2 | AnimeSR_v1 | v1 is the model of the paper; v2 looks more natural with fewer artifacts. Both 4×. |
| GPU ID | device_index | 0 – 4 | 0 | CUDA device. |
| Tensor RT | trt | on/off | off | Uses TensorRT; the engine is built on the first run and cached. |
| FP16 | – | on/off | off | Half precision (16-bit float clip), with and without Tensor RT. |
| max WSS | trt_workspace_size | 0 – 1073741824 | 0 | TensorRT workspace size; 0 = not set. |
| Resizer | – | point, rect, linear, cubic, lanczos, blackman, blackmanminlobe, spline36, spline64, spline144, spline, gauss, sinc | spline64 | Kernel that brings the 4× result to the exact output size. |
Example
Default settings on a 10-bit YUV 4:2:0 source (640x356), resized to 1280x712:
from vsanimesr import animesr as AnimeSR # adjusting color space from YUV420P10 to RGBS for vsAnimeSR clip = core.resize.Bicubic(clip=clip, format=vs.RGBS, matrix_in_s="470bg", range_in_s="limited", range_s="full") # resizing using AnimeSR clip = AnimeSR(clip, model=0, device_index=0) # 2560x1424 # resizing 2560x1424 to 1280x712 clip = core.fmtc.resample(clip, w=1280, h=712, kernel="spline64", interlaced=False, interlacedd=False)
How Hybrid calls it
- Selected with Resize enabled and Resizer set to AnimeSR (see Vapoursynth Resizer).
- The clip is converted to 32-bit float RGB (16-bit float with FP16) and padded to mod 4.
- The output is always 4× the input. If that differs from the target, fmtconv resizes it with the Resizer kernel to the exact size. With separately filtered fields the target height is halved.
- Model and GPU ID are always written (the plugin's own default model is v2); max WSS only when it is not 0.
- With Tensor RT the engines are cached in the engine path from Hybrid's path settings (or the temp folder). For clips larger than 1280×720 Hybrid raises the engine's maximum size to the clip size.
Background
AnimeSR
AnimeSR (Wu et al., NeurIPS 2022) learns the degradations of real animation videos from a set of basic operators instead of only synthetic ones. With it the authors published the AVC dataset of animation clips.
vs-animesr
HolyWu's vs-animesr runs AnimeSR in VapourSynth with PyTorch, optionally with TensorRT. It accepts 16- or 32-bit float RGB; the precision follows the input format. Its TensorRT engines are built for input sizes from 128×128 up to 1280×720 by default.
Sources
- vs-animesr
- AnimeSR
- Hybrid's tooltips