VeizikNVIDIA and Apple Silicon builds are available now.Release notes →
veiziknative inference engine
Sign inDownload
Product
OverviewWhat the engine isHow it worksWeights in, native execution outPlatformsNVIDIA · Apple SiliconSecurity & licensingDevice-bound, local by designReleasesEvery build, dated
Engineering
How it worksOne researched page per capabilityVideo memory720p that stays under a 24 GB cardA 35B model on one card21 GiB resident on a 24 GB GPUIts own stackNo Python, no framework, no cuBLASResume a renderCrash, resume, same result
Models
NVIDIALanguage and video — available nowApple SiliconQwen2.5 · Qwen3 — availableFull catalogueEvery model and its status
Hardware
All hardwareEvery device × every modelPick your deviceWhat runs on yoursNVIDIAAmpere → Blackwell · CUDAApple SiliconM1 – M4 · Metal
Benchmarks
All resultsMatrix or pick, by buildBuilds & downloadsEvery build, JSON / CSVMethod & notationHow every figure is taken
Docs
QuickstartInstall to first runCommand referenceEvery documented commandActivate a machineDevices and licenceWhat leaves the machineOffline and networkTroubleshootingWhen something fails
ReleasesSign inDownloadGitHub
Releases

veizik WAN (CUDA) v1.2.91 — Wan 2.1 & Wan 2.2 video — cuda-wan-1.2.91

Text-to-video and image-to-video with Wan2.1-T2V-1.3B, Wan2.1-T2V-14B, Wan2.2-T2V-A14B and Wan2.2-I2V-A14B on your own NVIDIA GPU. Veizik runs the models through its own native engine: no Python, no CUDA toolkit. You supply the weights; the frames are written as PNG files to the folder you name. It also runs a resident render server with a host-loop (bin/veizik-resident) that keeps one process and one GPU context across requests, and mid-render preemption. A maintenance cut over 1.2.8: the base text- and image-to-video renders are byte-identical (the engine's non-LoRA code is unchanged), distributed now as a single signed .vzpack.

This page records the state as of 2026-10-30 and is not updated as the catalogue moves. For what runs now, see models.

Highlights

What this build does

  • veizik run <model key> "prompt" --out DIR renders a video and writes its frames as PNG files to DIR/frames/; nothing is written inside the package.
  • Serve: veizik serve <model> runs a resident render server that renders request after request in one process and one GPU context, with results bit-identical to veizik run.
  • Four modes: quality (the reference path and the default), balanced, fast and ultrafast.
  • An interrupted render continues from its last step with --resume, and the result is identical to a render that never stopped.
  • Every file of the package is checked against its sealed manifest before each run.
  • GPU code for sm_80, sm_86, sm_89, sm_90a, sm_100a and sm_120a.
  • Every frame it writes carries the provenance mark described in the Terms: an in-pixel watermark plus XMP DigitalSourceType trainedAlgorithmicMedia.
  • Distributed as a single signed .vzpack: veizik install wan fetches and verifies it (and the shared-core .vzroot once) from its GitHub release and refuses any other file.
  • mid-render preemption — POST /v1/videos/generations with "priority": "urgent" interrupts a running render at a step boundary, is served, then the first render resumes from its checkpoint.
Support

Models in this release

ModelTaskContextStatus
Wan2.1-T2V-1.3BVideo—Available
Wan2.1-T2V-14BVideo—Available
Wan2.2-T2V-A14BVideo—Available
Wan2.2-I2V-A14BVideo—Available
Platform
Linux on x86-64
Verification
`veizik install` checks the download against SHA-256 ec21840bb29e63284743c92b5c19ae4bacef7e4cd07ddc17e78192d1b1b1cadb and refuses any other file. The release is reproducible: SHA256SUMS on the release, a single-file .vzpack with a signed .vzindex. To check veizik-wan-1.2.91-linux-x86_64.vzpack by hand, compare it with sha256sum.
File
veizik-wan-1.2.91-linux-x86_64.vzpack
Size
7,007,814 bytes
SHA-256
ec21840bb29e63284743c92b5c19ae4bacef7e4cd07ddc17e78192d1b1b1cadb
GPU architectures
sm_80, sm_86, sm_89, sm_90a, sm_100a, sm_120a
Run end to end on
GeForce RTX 3090 (sm_86); GeForce RTX 3090 (sm_86); GeForce RTX 3090 (sm_86)
Release
v1.2.91
Installation

Get, install, activate

bash
# the veizik command for Linux x86-64
$ curl -fsSL https://veizik.com/install.sh | sh
# if the installer asks you to put ~/.local/bin on your PATH
$ export PATH="$HOME/.local/bin:$PATH"
# accepted names: wan, wan21, wan22 or a full model key (wan21_t2v_1_3b, wan21_t2v_14b, wan22_t2v_a14b, wan22_i2v_a14b); any case; '.' and '-' work too (wan2.2)
$ veizik install wan22
$ veizik activate

Run `veizik activate` once per device after `veizik install`. Then `veizik pull wan` fetches the Wan weights and prepares the video decoder for you — no manual VAE setup or support request. Activation itself does not need the weights; rendering does. veizik install refuses a download whose SHA-256 differs from this release. The other packages are on the download page.

Fixed

Fixed issues

  • Maintenance cut over 1.2.8: the base text- and image-to-video renders are byte-identical (the engine's non-LoRA code is unchanged); carries the 1.2.5/1.2.6/1.2.8 install-reliability and resume improvements forward.
  • Internal engine preparation for the distilled image-to-video Lightning path; that model is not yet enabled on this site and is not advertised until its render is verified.
Known issues

Known issues in cuda-wan-1.2.91

  • Model weights are not included. veizik pull wan downloads the Wan2.1/2.2 weights (Apache-2.0) and prepares the video decoder automatically — no manual VAE setup; veizik pull --prep-local DIR prepares weights you already have.
  • Speed figures for this package were measured on an NVIDIA RTX 3090 (sm_86) only.
  • The image-to-video model takes its input image as raw RGB bytes, one byte per channel, at exactly the render size (width × height × 3 bytes).
  • balanced, fast and ultrafast are not bit-identical to quality; without --det-vae yes decoded frames may differ slightly from run to run.
  • The distilled image-to-video Lightning model is not yet enabled: its render is being verified before it is advertised.