Veizik is a ComfyUI drop-in powered by the LimML engine: low-VRAM capacity-compute + native CUDA DiT. TimeMachine Render branches from a saved checkpoint — keep the approved prefix, re-render only the failing tail.
The value is execution quality — running the biggest open models reliably on hardware you already own — not license protection.
Capacity-compute tiering (hot / warm / cold placement) fits 30B-class video on a single 24 GB GPU without OOM.
measured on RTX 3090Flagship models run on Veizik's own DiT kernels — N-layer streaming + fp16 tensor-core, verified bit-exact vs reference.
6/6 verifiedNo per-step reloading; fp16 tensor-core paths give up to ~10× vs fp32 at the layer/kernel level.
profile-conditionalStep-level checkpoints + retry/degrade + isolation — one job's fault never discards the render or takes down the farm.
testedBranch from a saved checkpoint: keep the good prefix, re-render only the failing tail with new prompt / style / CFG.
beta · GPU-validatedSwap comfy → veizik. Same graph, low-VRAM + native DiT. Unknown models fall back — the swap never fails.
run / serve / t2vThe biggest waste in AI video is "the first part is good but the rest breaks, so I re-render everything." TimeMachine fixes that — one checkpoint infrastructure serves both crash-resume (same settings) and creative branching (new settings).
Flagship families run on native CUDA DiT (verified bit-exact at the block/engine level). Everything else runs a universal fallback, so a comfy → veizik swap is never rejected.
Numbers are profile-conditional (resolution, frames, steps, model). VRAM is reported from framework allocators — authoritative on WSL2.
| Run (RTX 3090, 24 GB) | Time | Peak VRAM | OOM |
|---|---|---|---|
| LTX-13B · 1280×704 · 49f · 40 steps | ~109 s | 9.55 GB | none |
| Step-Video 30B · 992×544 · 51f | single GPU | ≤24 GB | none |
| TimeMachine branch · step 8 of 16 | 8/16 steps | 807 KB tl | 50% saved |
| Native DiT engine | Numerical match (rel) | |
|---|---|---|
| Step-Video 30B | 2.35e-6 | bit-exact |
| LTX-Video | 1.94e-7 | bit-exact |
| CogVideoX | 8.43e-7 | bit-exact |
| HunyuanVideo | 3.6e-6 | bit-exact |
| Wan 2.1 | 5.53e-7 | bit-exact |
| FLUX.1-dev | 4.58e-7 | bit-exact |
We don't claim uncrackable protection. The durable advantage is execution quality, optimization depth, update cadence, and benchmarks — not secrecy.
Download the runtime for Windows (WSL2) or Linux. Runs without a key — the free path proves it runs on your GPU.
Replace comfy with veizik (or vz) in your existing workflow. Same graph, low-VRAM + native DiT.
Render, then branch the parts that broke — never re-render the whole clip again.
| Veizik | Cloud video (Runway / Pika) | Raw ComfyUI | |
|---|---|---|---|
| Runs on your own GPU | yes | no — cloud | yes |
| 30B video on 24 GB | no OOM | n/a | OOMs |
| Checkpoint branch (keep prefix) | TimeMachine | re-render | re-render |
| Per-render cost | your electricity | ~$0.05–0.95 / clip | your electricity |
| Data leaves your machine | never | uploaded | never |
| Price | $9–59 / mo license | ~$28–76 / mo | free / DIY |
Pricing is a local runtime license — not cloud credits. You supply the GPU. Checkout — coming soon · free keys are live today.
+ TimeMachine Beta Pack — $12/mo · branch render + collapse detection. Licensing is a server-signed entitlement (the runtime, not the UI, enforces features). Launch pricing target; annual discounts planned.
# make veizik your comfy
alias vz='veizik'
comfy() { veizik "$@"; } # comfy run wf.json now runs veizik
veizik doctor # probe GPU + per-model support tier
veizik activate <key> # bind device, receive entitlement token# direct native text-to-video (low-VRAM + native DiT) veizik t2v "a barista pouring latte art, warm cafe" \ --model ltx --w 1280 --h 704 --frames 49 --steps 40 # or run an existing ComfyUI workflow unchanged veizik run my_workflow.json
# keep the good prefix, re-render only the tail
veizik base --job clipA --model ltx --prompt "..." --steps 30
veizik branch --job clipA --from-step 15 \
--style "luxury commercial" --cfg 4.5 --seed-policy branch
# A/B fanout: 3 looks from one branch point
veizik fanout --job clipA --from-step 20 \
--styles "warm cinematic,cyberpunk neon,luxury glossy"# auto-detect where it went bad -> suggested branch points veizik collapse --job clipA # - 3.2s: face drift begins # - 4.0s: optical-flow discontinuity # - 4.6s: prompt adherence drops veizik timeline --job clipA # checkpoints + branch lineage + storage
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 RTX 3090 / 4090 (24 GB) or better, a recent driver, and Windows (WSL2) or Linux. 30B-class video was measured on a single 24 GB RTX 3090 with no OOM.
No — Veizik is a strict drop-in. Swap comfy → veizik and the same graph runs low-VRAM on the native DiT engine. Models without a native engine fall back to a universal path, so the swap is never rejected.
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's the same checkpoint infrastructure as crash-resume. Real-GPU validated on LTX (a mid-point branch re-ran only half the steps). It's live in the CLI today as a beta feature; the paid Beta Pack checkout is coming soon.
No — Veizik is a proprietary commercial runtime. Installation and evaluation are free; production use requires a license. The engine (LimML) 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.
Native CUDA DiT (verified bit-exact) for Step-Video 30B, HunyuanVideo, Wan 2.1, LTX, CogVideoX, and FLUX.1; Llama/Qwen-class LLMs via an OpenAI-compatible endpoint; any other ComfyUI model via the universal fallback.
Free keys render watermarked, non-commercial. Your key authorizes via a server-signed entitlement — issued below, enforced in the runtime.
Keys are stored hashed; the raw key is shown only once. Revoke anytime — the entitlement stops validating.
Visual timeline branching — generation filmstrip, collapse auto-detect, one-click A/B fanout in the browser.
Creator / Pro / Studio via merchant-of-record (USD, tax handled). Your free account carries over.
Multi-GPU orchestration, team seats, API, parallel branch candidates with auto-evaluation.
Grab a free key today — the engine, drop-in CLI, and TimeMachine (beta) are live; the surfaces above are on the way.