VerifiedHow we measureHead-to-headTimeMachine StatusWho it's forPricingDocsFAQGet a key 한국어로 보기
Technical Preview — benchmarks are public, runtime access opens in verified waves

A 14-billion-parameter video model, in 6.5 GB.

Install opens soon. Reserve your spot — the launch notice goes out automatically to everyone on the list. Reserving is free and collects no payment.

Its own publisher asks for a GPU with 80 GB — and says so with the memory-saving options already switched on. We measured this clip at 6.5 GB on one RTX 3090, against 17.7 GB for the standard fp8 offload path on the same card, and the footprint is not bought by letting the picture fall apart: across the clip veizik loses 8–11% of its sharpness where that path loses 47%.

Free when it opens · reserve to get notified Linux and Windows 11 + WSL2 · NVIDIA GPU (per-model VRAM in the table) Runs on your GPU — nothing is uploaded
seed Qwen-Image-2512 Apache-2.0 motion Wan2.2-I2V-A14B Apache-2.0 832×464 · 81f · 40 steps one RTX 3090 delivered 1280×720 · 24 fps C2PA signed · what that means
6
model families on one engine
Linux
+ NVIDIA · Windows WSL2 experimental
0
media or prompts leave your machine
0
per-render charges — you supply the GPU
In 10 seconds

What this actually is

Six families, one engine

LTX-Video, Wan, HunyuanVideo, CogVideoX, Step-Video and FLUX run on the same runtime. veizik doctor reads your card and tells you what it will run, per family, before you commit to a download.

one install, every family

Every number is checkable

Each figure on this site ships with the config that produced it — model hash, resolution, frame count, steps, seed — and a run manifest you can diff against your own. Run the same fixed config on your card and compare.

method & conditions

Nothing leaves the machine

Your prompts, your inputs and your renders stay local — the engine runs on your GPU, so there is no upload and no per-render charge. What you buy is a runtime licence, not cloud credits.

install free · upgrade later
Reproduce it yourself

One command, one verifiable result

The benchmark harness, metrics, manifest schema and these run records are live today: run the fixed config against the same model hash and diff your run record against ours. The one-line curl wrapper and the veizik bench subcommand are convenience wrappers still in development.

command · planned wrapper
# planned — not live yet:
$ curl -fsSL https://veizik.com/bench.sh | bash   # planned
$ veizik bench --suite ltx-consumer --upload=ask  # planned

# today — real: run the fixed config from
# benchmark-method.md against the same model hash
output · fixed config · 5 runs
GPU      RTX 3090 24GB (sole tenant · 420W verified)
Model    Lightricks/LTX-Video @ 8984fa2
Profile  veizik-native · bf16
Config   768x448 · 49f · 30 steps · seed 42
Peak VRAM 9.55 GB   (spread 0.00, 5 runs)
Wall      18.5 s    (median · ±0.97 · min 17.4 / max 20.4)
Output   sha256 66b560f1…c16c28
Manifest veizik-bench/reports/runs/d605e616….json

Every figure carries its conditions and raw per-run JSONL, and is reproducible on the same card. Method: benchmark-method.md · Reproduce: REPRODUCE.md (LTX/FLUX evidence + lockfile).

Real renders

Made locally with the Veizik engine

Rendered locally on a single NVIDIA GPU, with every number below measured on that run — not estimated. Full conditions travel with each clip so you can judge it the way you'd judge your own hardware.

Wan2.2-I2V · 3 s · click to play

Strawberry splash

C2PA signed
Qwen-Image-2512 still (Apache-2.0) → Wan2.2-I2V-A14B · 1280×720 · 24 fps · 3 s · C2PA signed
Wan2.2-I2V · 3 s · click to play

Coastline aerial

local render
Qwen-Image-2512 still (Apache-2.0) → Wan2.2-I2V-A14B · 1280×720 · 24 fps · 3 s · C2PA signed
Wan2.2-I2V · 3 s · click to play

Neon rain city

C2PA signed
Qwen-Image-2512 still (Apache-2.0) → Wan2.2-I2V-A14B · 1280×720 · 24 fps · 3 s · C2PA signed
Wan2.2-I2V · 3 s · click to play

Aurora over the lake

C2PA signed
Qwen-Image-2512 still (Apache-2.0) → Wan2.2-I2V-A14B · 1280×720 · 24 fps · 3 s · C2PA signed
Wan2.2-I2V · 5 s · click to play

Coastal supercar

C2PA signed
Qwen-Image-2512 still (Apache-2.0) → Wan2.2-I2V-A14B · 1280×720 · 24 fps · 5 s · C2PA signed
Wan2.2-I2V · 3 s · click to play

Coral reef

C2PA signed
Qwen-Image-2512 still (Apache-2.0) → Wan2.2-I2V-A14B · 1280×720 · 24 fps · 3 s · C2PA signed
Wan2.2-I2V · 3 s · click to play

Rainy cafe window

C2PA signed
Qwen-Image-2512 still (Apache-2.0) → Wan2.2-I2V-A14B · 1280×720 · 24 fps · 3 s · C2PA signed

A high-resolution still is generated first, then turned into a 5-second cinematic film with image-to-video — all on one local GPU, and nothing leaves the machine. Test conditions for every figure on this page →

repeated runs · 420W verifiedThe figures we stand behind — reproducible on a fixed config

RTX 3090 · exclusive GPU · 420 W verified · same seed/prompt/scheduler each run:

LTX-Video 768×448 · 49f · 30 steps → 18.5 s median (± 0.97 s, 5 runs · 17.4–20.4) · peak 9.55 GB (spread 0.0)
FLUX.1-dev 1024² · 24 steps → 49.25 s median (± 0.64 s, 4 warm runs · 48.8–50.5) · peak 12.78 GB

Every run ships raw per-run JSONL (conditions · GPU UUID · observed draw) in veizik-bench, so the number is reproducible on the same card.

Receipts

Six model families, measured on a fixed config

Every row below is a real render on a pinned config — model hash, resolution, frame count, steps and seed all published — with wall time, peak VRAM and peak host RAM taken from the run itself. Run the same config on your card and compare.

Model · text-to-videoWorkloadWall (median)Peak VRAMPeak host RAMRuns
LTX-Video768×448 · 49f · 30 steps18.5 s 17.4–20.49.55 GB18.7 GB5 runs
FLUX.1-dev (image)1024² · 24 steps49.25 s 48.8–50.512.78 GB45.2 GB4 runs
CogVideoX-2b720×480 · 49f · 50 steps195.2 s 195–21316.29 GB18.6 GB3 runs
Wan 2.1 · 1.3B832×480 · 49f · 30 steps149.4 s 149–15011.60 GB23.4 GB3 runs
Wan 2.1 · 14B832×480 · 49f · 30 steps · seq offload854.5 s16.68 GB94.9 GB1 run
Step-Video · 30B992×544 · 51f · 30 steps1730 s12.48 GB96.0 GB1 run

Conditions: 420 W verified, sole GPU tenant, seed 42, on 24 GB-class NVIDIA hardware. The 14B/30B rows need ~96 GB of host RAM — read the host-RAM column before you plan a build. Run the same config on your card and open a result PR.

Conditions behind these numbers
  • Raw per-run JSONL (conditions · GPU UUID · observed draw) is published in REPRODUCE.md.
  • The Runs column is the number of runs behind each median; ranges are min–max across those runs.
  • The 14B/30B models hold peak VRAM at 12–17 GB by streaming weights, and pay for it in system memory: a 24 GB GPU plus ~96 GB host RAM.
  • Engine paths match the reference at the block/engine level — rel_L2 1e-6–1e-7 across the five families we publish (Step-Video 2.35e-6 · LTX 1.94e-7 · CogVideoX 8.43e-7 · Wan 2.1 5.53e-7 · FLUX 4.58e-7). That is a component check, not an end-to-end render.
  • HunyuanVideo figures are not published. The engine has a HunyuanVideo path, but the Tencent Hunyuan Community License excludes the EU, UK and South Korea from its Territory — see model licences.
What it does

What's live today, and what's still coming

Technical Preview. The tags below say what the downloadable build does today and what is still planned — see Known Issues for the open ledger, and test conditions for every figure on this page.

Hardware check & profile

veizik doctor scans your machine and prints a runnable support tier per model family, so you know what fits before you render.

live in the download

Low-VRAM execution

The runtime fits large video models on consumer NVIDIA GPUs without manual offload tuning — LTX-Video 2B peaks at 9.55 GB, and doctor prints the per-model fit for your card.

peak VRAM measured

Native engine paths

Engine paths are numerically checked at the block/engine level (rel_L2 ~1e-6–1e-7 vs reference) — a component-level check, not an end-to-end render benchmark. Image and video today; language models and more on the roadmap.

block-level numerical check

Local & licensed

veizik login redeems a free key for a server-signed entitlement. Your media and prompts stay on your machine; only license data is exchanged.

live in the download

TimeMachine Render

Branch from a saved checkpoint: keep the good prefix, re-render only the failing tail. Ships as a Preview build asset — not in the current download yet.

planned · Preview build

ComfyUI integration

Goal: run your existing ComfyUI graph under Veizik with low-VRAM + native engines. Under preview validation — run / serve land in the next release.

upcoming preview
Recovery · Planned · Preview build

Kill it at step 20. Resume. Only the tail re-renders.

Status: TimeMachine ships as a downloadable Preview build asset — it is not in the current public download yet. The diagram below describes the intended behavior.

The biggest waste in AI video is "the first part is good but the rest breaks, so I re-render everything." TimeMachine addresses that — one checkpoint infrastructure serves both crash-resume (same settings) and creative branching (new settings).

base render · denoise steps 5 10 15 ◀ branch 20 30 prefix 0..15 — REUSED (kept) tail 16..30 — new style/cfg real GPU (LTX): re-ran 8/16 steps · 50% saved timeline stored: 807 KB · sparse latents only
  • Keep the good part. Composition, faces, product placement, lighting are preserved — not thrown away.
  • Fix only what's wrong. A clip that collapses after ~6 s regenerates only its tail — a fraction of the work.
  • A/B fanout. Several endings (warm / cyberpunk / luxury) from one branch point, in parallel across the farm.
  • Auto-find "from where" prototype A collapse detector to flag face drift, flicker, and motion jumps and suggest a branch point — prototype, not in the build.
  • Low storage. Sparse latent checkpoints — a branchable timeline is ~kilobytes, not a copy of every frame.
LTX · 40 steps · killed at 20The experiment

Start a 40-step LTX render. SIGKILL it at step 20. Resume from the last checkpoint and compare to an uninterrupted run of the same seed.

8 / 16
tail steps re-run on resume — ≈50% of the denoise work saved vs re-rendering from step 0
807 KB
sparse-latent timeline stored — not a copy of every frame
within tolerance
resume output vs the uninterrupted run — compared on decoded output, not on file hashes

Branch A/B/C: the prefix is computed once; each additional ending (warm / cyberpunk / luxury) costs only its tail. Conditions: one LTX run on an RTX 3090, claim id VZK-TM-LTX-RESUME-3090.

Compatibility

Model families with a native engine path

These families have a native engine path, each numerically checked at the block/engine level (rel_L2 ~1e-6–1e-7 vs reference — a component check, not an end-to-end render benchmark). A universal fallback path for other models is under development.

Native engine

Step-Video 30B

rel 2.35e-6 · single GPU
Native engine

HunyuanVideo

measurements withheld
⚠ Licence restricted in KR / EU / UK — model licences
Native engine

Wan 2.1

rel 5.53e-7
Native engine

LTX-Video

rel 1.94e-7 · measured
Native engine

CogVideoX

rel 8.43e-7
Native engine

FLUX.1-dev

rel 4.58e-7 · image
planned

Llama / Qwen

LLM · OpenAI-compatible endpoint
Planned

Universal fallback

other models · in development
Works with your stack
runs on the tools you already use — no rewrite, no lock-in
upcoming

ComfyUI

integration · next release
runtime

NVIDIA CUDA

sm_80+ · fp16 TC
pipeline

diffusers

T2 fallback path
framework

PyTorch

2.x · bf16 / fp16
OS

WSL2 / Linux

Windows or native
planned

OpenAI-compatible

LLM endpoint · planned
How we measure

What the engine optimises

Performance here is not one leaderboard number. Each axis below is measured on a pinned config — same model hash, prompt, seed, scheduler, steps, resolution and power cap — so a figure means the same thing every time it is published. Test conditions →

Memory

Peak VRAM at equal model and quality. LTX-Video 2B peaked 9.55 GB on a 24 GB card, 5 runs.

Consumer-GPU latency

Wall time on a pinned config, 420 W verified. LTX 18.5 s (5 runs) · FLUX 49.25 s (4 warm runs), each with a run record.

Recovery preview build

Resume and branch savings after a kill — the prefix is kept and only the tail re-renders. TimeMachine ships as a Preview build asset.

Test conditions

How every figure on this page is measured

One pinned config per row — model hash, prompt, seed, scheduler, steps, resolution, frame count and power cap all fixed and recorded — so the same command reproduces the same number on the same card. Full method: benchmark-method.md.

Render · 24 GB card, sole tenantWall timeOOM
LTX image-to-video · 1216×704 · 49f · 30 steps33.5 snone
LTX image-to-video · 1216×704 · 73f · 30 steps71.3 snone
LTX text-to-video · 1216×704 · 49f · 30 steps32.2 snone
Warm runs, fixed seed, one card, sole GPU tenant, power cap recorded per run. The remaining model families are measured in the table further up this page; this block is the LTX resolution/frame sweep only.
Engine pathBlock/engine rel_L2
Step-Video 30B2.35e-6block-level
LTX-Video1.94e-7block-level
CogVideoX8.43e-7block-level
Wan 2.15.53e-7block-level
FLUX.1-dev4.58e-7block-level
Numerical equivalence vs the reference implementation at the block/engine level — not an end-to-end generation benchmark.
VRAM budget · measured on a 24 GB cardLTX-Video 2B working set 9.55 GB
9.55 GB 24 GB
LTX-Video 2B at 768×448 · 49f · 30 steps · seed 42 — spread 0.00 across 5 runs. Ran it on your own card? Post the result.
Head-to-head

Same clip, same card — against the fp8 offload path

The comparison that matters on a desktop card is memory and stability, not a leaderboard second. Below is Wan2.2 image-to-video run two ways on one machine, with the conditions published so you can run the same config yourself.

Wan2.2 i2v · 5 s · 81 f · 848×480Memory and drift, measured on one card
Mode (same clip, same card)Peak GPUTemporal drift (front→back)Wall · step counts differ
Veizik native int86.5 GB−8…−11%~430–600 s
fp8 CPU-offload (reference)17.7 GB−47%752 s

~2.7× less peak VRAM than the fp8 reference, and far less back-half drift (−8% vs −47%). Conditions: Wan2.2 image-to-video, 5 s · 81 f · 848×480, one 24 GB card, same clip and same card per row; step counts differ per row, so wall time is not an identical-condition comparison; drift is distance from fp8, not a quality score; measured on the veizik-native · int8 engine profile (2026-07-17). Claim id VZK-WAN22-I2V-INT8-3090.

Run it yourself: the same fixed config ships in veizik-bench — open a result PR with what your card does — start here. Negative results are welcome and published.

Why local

Why run it on your own hardware

Cloud video tools bill a monthly subscription plus metered GPU credits that scale with how much you render. Veizik is a local runtime instead: it runs on the GPU you already have, keeps your media on your machine, and takes the manual memory tuning out of running large models.

No per-render bill

Cloud video tools bill a monthly subscription plus metered GPU credits that grow with usage. Veizik renders on the GPU you already own — there's no per-render charge, only the electricity the card draws.

your GPU · electricity only

No manual memory tuning

Skip the model / VRAM / offload trial-and-error and the OOM restarts. veizik doctor scans your machine and reports a runnable support tier per model family, so you know what fits before you render.

doctor · live auto-apply · planned

Big models on the card you own

The runtime fits large video models on a single consumer NVIDIA GPU — LTX-Video 2B peaks at 9.55 GB, and doctor prints the fit per model family for your card. Frames and prompts are never uploaded to a rendering cloud.

LTX-Video 2B working set 9.55 GB

You own the runtime

It runs locally and keeps working offline for 30 days at a time. Media, prompts, and project data stay on disk — only license activation talks to veizik.com, and no output is sent anywhere.

local · 30-day offline

Every number above comes from a run on a pinned config — test conditions for every figure on this page →

Preview in 3 steps

Install, check your hardware, activate.

1 · Install

curl -fsSL https://veizik.com/install.sh | sh on Linux or Windows WSL2 (git + Python 3.10+). No key needed to install.

2 · Check your hardware

veizik doctor scans this machine and prints the support tier per model family — so you know what runs before you commit.

3 · Activate a free key

veizik login <key> redeems a free key from veizik.com for a signed entitlement. Universal t2v render is experimental today.

How it compares

Local runtime vs cloud tools

VeizikCloud video (Runway / Pika)Raw ComfyUI
Runs on your own GPU yesno — cloudyes
Large 30B-class video on one consumer GPUnative engine path, verified at block level (rel_L2 2.35e-6)n/a
Checkpoint branch (keep prefix)TimeMachine preview buildre-renderre-render
Per-render costyour electricitymetered / clipyour electricity
Data leaves your machine stays localuploadedstays local
PriceFree · paid from $29/momonthly cloud planfree / DIY
Who it's for

Built for four kinds of team

ComfyUI power users · Memory

Same graph. Your own GPU. No per-render bill. Keep the workflow you already built and run it low-VRAM on hardware you own.

runtime · low-VRAMComfyUI run/serve · preview validation

Studios · Recovery

Local, repeatable, resumable batch production. A crash doesn't discard the render — the good prefix is kept and only the tail re-runs.

local · reproducible benchTimeMachine · Preview buildqueue/batch · development

GPU hosts & API providers · Reliability · Transfer

More headroom per node — measured before a job runs. doctor profiles GPU capacity so admission is a decision, not a surprise OOM.

doctor capacity check · liveGPU-Oracle admission · private previewAPI bridge · planned

Model labs · Distribution

Ship your model to consumer GPUs. A native engine path verified at the block level against your reference — a low-VRAM distribution option without a fork.

native engine · block-level equivalenceOEM/SDK runtime · contract
Plans

The runtime is the product. Licensing follows capability and deployment scope.

Install is free, and inspecting the hardware scan and entitlement client is free. What you buy is a local runtime license: which model families the engine will run, how far you can push resolution and length, commercial use rights, and the advanced execution paths. No cloud credits. You supply the GPU.

Licence unit = 1 key, 1 PC. Rungs differ only by what the engine can do — never by how much you render. Need a second machine? That's a second key (volume discount from 5). Changing hardware is 3 self-service transfers a year.

There is no per-render charge, and there never will be. The engine runs on your GPU and your electricity — we don't pay for your renders, so we don't bill for them.

STARTER free
$0
Install free, verify on your own GPU, run the reproducible bench and submit your run-manifest.
  • LTX-Video and Wan 2.2 · up to 1280×720 · 121 frames
  • doctor hardware + per-model support scan
  • Run the fixed-config benchmark & submit results
  • 1 key · 1 PC
  • No watermark. Commercial use permitted — each model keeps its own licence
  • Machine-readable AI provenance marking stays on in every tier and does not restrict your rights. It is not a visible watermark. What this means and why
Start free
CREATOR
$29 /mo · or $249/yr
Annual works out to just over three months free versus paying monthly. Install free now, upgrade the same key later.
  • + CogVideoX, FLUX · up to 1920×1080 · 241 frames
  • Commercial use — nothing to declare
  • Sell what you render. Running Veizik itself as a shared server, a render fleet or a hosted service is a Business licence — that is about deployment, not about what you earn.
  • Machine-readable AI provenance marking stays on in every tier and does not restrict your rights. It is not a visible watermark. What this means and why
  • Runtime rights only — each model keeps its own licence. FLUX.1-dev is non-commercial. Model licences Benchmarks Third-party notices
  • After 12 months, one version is yours to keep — permanently, even if you stop paying how
  • Stable pinned profiles (not experimental)
  • Creator Model Adapters & Capsules
  • 1 key · 1 PC · device change 3×/year, self-service
Get Creator
PRO invited preview
Preview · not on sale
Pro is the automation tier. Its three defining capabilities — the automation API, queue & batch execution, and recovery — are not generally available, so it is not for sale. It runs as an invited preview at no charge, and opens for purchase on the day those three ship.
  • The engine’s full model range — see the licence and territory registry for what each model permits where
  • No resolution or frame cap
  • Commercial use — nothing to declare
  • After 12 months, one version is yours to keep — permanently, even if you stop paying how
  • Low-VRAM layer streaming · LoRA / adapters
  • Advanced FP8 / INT8 quantization private preview
  • Queue & batch execution development
  • Recover / TimeMachine / automation API private preview
Join Pro Preview
STUDIO private pilot
Pilot · scoped per deployment
Studio covers organisational deployment — headless serving, multi-GPU execution and central licence control. Those are not generally available, so Studio is run as a scoped pilot with a measured report rather than sold from this page.
  • Everything in Pro — identical model families, no resolution or frame cap
  • Multi-GPU on one machine — every card in the box drives one render
  • Audit log — every render on the node, exportable
  • Dedicated / private Model Adapters
  • Headless serve (no desktop session) development
  • Central license server for a fleet development
Talk to us
Not open yet. We are piloting with individual creators first and will open the node tier once that is steady. Tell us what you need and we will come back to you when it opens.

Every tier writes a machine-readable AI provenance mark (C2PA); it cannot be switched off. No tier watermarks your output — not even the free one. The C2PA mark is a signature in the file's metadata that says a machine made it; that is a legal obligation and stays. It does not put anything on the picture. AI transparency · Model licences — a paid tier licenses the runtime, not the models.

Twelve paid months earn you one version, permanently. Not a discount and not a trial. Complete a paid year and every version released during it is yours — including the one you were actually running on your last paid day, not a build from twelve months earlier. It keeps working at your tier if you stop paying, and if we stop existing. What exactly you get — including what we owe you if we shut down, the limits we cannot insure against, and the one condition we have not finished building, which is why nothing is issued today.

Running a GPU fleet? by inquiry

We measure whether your current model and quality target can move to a lower-cost accelerator tier — same weights, same output target, reported GPU memory, host memory, throughput and cost per output. Evaluations, design-partner pilots and OEM/embedding agreements are scoped per engagement.

Talk to sales

Billing opens after preview validation — nothing is charged today. Enterprise and deployment enquiries: sales@veizik.com.

What "commercial output" means: it is your right to use the Veizik runtime commercially. It does not change the licence of the underlying models — those keep their own terms. FLUX.1-dev is published under a non-commercial licence, and HunyuanVideo's licence does not apply in the EU, UK or South Korea. Check every model you plan to bill for on the model licences page before you take paid work.

One bootstrap CLI for every tier — no separate builds. The public binary carries the parser, updater, doctor, license client, telemetry client, pack loader, signature verifier and the public Adapter interface; a server-signed entitlement unlocks the matching private runtime pack (Veizik native runtime, advanced kernels, Adapters, Capsules, GPU Oracle planner, Recover, TimeMachine, Queue, API bridge). The runtime — not the UI — enforces features. Billing by Polar (merchant of record; USD, tax included). Veizik does not ship face swapping, lip-sync, or voice cloning — those capabilities are not in any build. The Service is currently not offered to residents of the EU, EEA or UK. Feature states are labelled research / development / private preview / public preview / shipped.

Quickstart

Technical Preview usage

# install (git + python 3.10+)
curl -fsSL https://veizik.com/install.sh | sh

veizik doctor                   # scan GPU + per-model support tier
veizik login <key>              # redeem a free key for a signed entitlement
veizik status                   # show current tier & entitlement
# experimental universal render — Linux + NVIDIA, your own torch/diffusers env
timings for measured configs are in the benchmarks table below
veizik t2v "a barista pouring latte art, warm cafe" \
  --model ltx --w 1280 --h 704 --frames 49 --steps 40
# NOT in the current download — landing in upcoming Preview releases:
#   veizik run my_workflow.json     # ComfyUI integration (next release)
#   veizik branch --from-step 15    # TimeMachine (Preview build asset)
#
# track status: github.com/veizikhq/veizik  ·  KNOWN_ISSUES.md
Questions

FAQ

No. Veizik runs entirely on your own GPU — nothing is uploaded and no cloud render credits are involved. A license is a local runtime license; you supply the hardware.

An NVIDIA GPU on Linux x86_64; Windows 11 + WSL2 + NVIDIA is experimental. How much VRAM you need depends on the model, not on a card class — the peak VRAM per model family is in the results table, and veizik doctor reads your card and prints the support tier per family before you download anything (free, no key needed). Apple Silicon is planned.

Not yet. ComfyUI integration (run / serve) is under preview validation and lands in the next release — it is not in the current download. The goal is that your existing graph runs under Veizik with low-VRAM + native engines.

It branches a render from a saved denoise-step checkpoint: the approved prefix is reused and only the failing tail is regenerated with a new prompt / style / CFG. It ships as a Preview build asset and is not in the current public download yet.

No — Veizik is a proprietary commercial runtime. Installation and evaluation are free; production use requires a license. The engine (Veizik) is not distributed as source.

Permission is a server-signed entitlement token, not the key itself. Activation binds to a device fingerprint, and feature gating lives in the runtime executor — not just the UI. You can issue and revoke keys above.

Step-Video 30B, HunyuanVideo, Wan 2.1, LTX, CogVideoX, and FLUX.1 each have a native engine path. We publish block/engine-level numerical checks for five of them (Step-Video, Wan 2.1, LTX, CogVideoX, FLUX.1 — rel_L2 ~1e-6–1e-7 vs reference, a component check, not an end-to-end render benchmark). We do not publish figures or outputs for HunyuanVideo: its licence excludes the EU, UK and South Korea from the territory it covers — see model licences. The experimental t2v render path today targets LTX-class models on Linux + NVIDIA.

Live

Get an API key

LIVE

Free keys allow commercial work and are not watermarked. Each model still carries its own licence. Every tier writes a machine-readable AI provenance mark. Your key authorizes via a server-signed entitlement — issued below, enforced in the runtime.

Your API key (shown once — copy it now):
Set once: export VEIZIK_API_KEY=… then veizik doctor.

Look up or revoke the keys tied to an email, in the account console.

Open the console
Roadmap
Coming soon

Being finalized

NEXT

ComfyUI integration

Run your existing ComfyUI graph under Veizik with low-VRAM + native engines — run / serve, under preview validation.

NEXT

TimeMachine Preview build

Checkpoint branching in the downloadable build: keep the good prefix, re-render only the failing tail.

LATER

Pro & Studio tiers

Batch, A/B fanout, multi-GPU and team seats open after Preview validation. Your free account carries over.

Live in the current download: doctor, login/status, and a free entitlement, plus an experimental universal t2v path. Everything above is on the way; release notes land in the public repo as each piece ships.

Stay in the loop

Get launch & billing updates — or ask us anything

Drop your email and the launch, billing-open and Preview-build notices go out to the list automatically. Compatibility questions land in the auto-acknowledged support inbox; anything worth a public answer goes to the public issue tracker and the docs.

No payment, no spam. Launch, billing-open, and Preview-build notices only, sent automatically. Unsubscribe anytime.
or email support@veizik.com