Skip to content
AI for businessFor building ownersHow it worksPricingResearchCompany
Let’s talk
AI for businessFor building ownersHow it worksPricingResearchCompanyLet’s talk
On this pageThe jobHow it is deliveredEvaluationStraight answers

Solutions / Post

The overnight shift for frames that cannot touch a public cloud.

Overnight roto, cleanup and upscaling for pre-release content that your client's rules keep off public clouds, on the Azita fleet or on an installation in your building.

Arrange a workload evaluationHow an evaluation works

Prefer email? hello@azitalabs.com, subject “VFX workload evaluation”.

The job

The artists' day, and the render room's night.

The work is the grind under every episode: roto, matting, wire and rig removal, plate cleanup, upscaling to delivery resolution, frame interpolation and denoise. Open models can propose much of it, frame by frame, if they are allowed to see the frames. On an OTT title the client's content-security rules keep pre-release frames off a public cloud, so the work needs a location your assessor can review: on the Azita fleet, or in your own building.

What you bring
Plates and queued shots, with the supervisor's notes for each pass.
What comes back
Roto, mattes, cleanup, upscale, interpolation and denoise passes returned to your review queue for artists to check and finish.
By day

The artists

Supervisors queue the shots, artists review the overnight passes, fix what needs a hand, and send the next batch.

By night

The frames

Queued shots processed pass by pass, frame by frame, after the floor empties, with the results returned to the review queue. When they are ready is agreed in your evaluation.

What runs

What runs for the queue.

Open video and image models of the classes below, pinned once your supervisors have approved the look on your own shots. No vendor names: the model is chosen against your material, not a showreel.

Segmentation and matting models
Roto and mattes proposed frame by frame for the artist to refine, judged on how consistently they hold across the shot.
Inpainting and cleanup models
Wire, rig and marker removal, plate cleanup, and fills across a moving camera, for the artist to check.
Upscaling, interpolation and denoise models
Delivery-resolution upscales, frame-rate conversion and grain-aware denoise for the passes that used to wait for a farm slot.
Your pipeline
Your node-based tools and render management stay yours. How they connect to the capacity is confirmed during the evaluation and set out in your proposal.

How it is delivered

Two ways it reaches the queue.

Both routes are scoped around your queue, and how your pipeline connects is set out in your proposal.

Capacity from the Azita fleet

The work runs on capacity from Azita's installations, with the processing location set in your agreement. If a pipeline or render-management vendor runs your queue, how it connects is scoped in the proposal.

An installation in your building

Azita designs, installs, commissions and operates an installation in your own building, serving your queue, and meters the work. Whether a room suits an installation is decided by a site assessment.

An agency review wall of pinned campaign boards receding into soft focus under a copper spotlight

Boundaries

Agreed before any work runs.

For a post house the argument is content security: the client's rules forbid a public cloud for pre-release material. Each of these is agreed in your proposal and set in your agreement before any work runs.

Processing location
Where frames are processed and stored during the work: on the Azita fleet, or on an installation in your building, as your agreement sets out.
Model choice
Which open models run each pass, and the version each is pinned to once your supervisors approve the look.
Access
Who can reach the frames and the installation, and how that access is recorded for your content-security assessor.
Retention and exit
How long frames and passes are kept, and how they are handled when the agreement ends. Exit and erasure terms are set out in your agreement.

Evaluation

Judged on your own work.

Your supervisors pick the shots and judge the passes. No delivery depends on it until they say so.

Representative input
A handful of shots your artists would rather not roto by hand, on material you are cleared to share for a test.
Quality criteria
The look your supervisors approve: edge quality, consistency across the shot, and the fixes an artist still needs to make.
Volume
The shots and passes in scope, agreed to represent an episode's grind.
Turnaround
When passes are back in the review queue, agreed before the evaluation starts.
Acceptance
Your supervisors judge the passes against the criteria. If they do not meet them, nothing moves.
Concept of two people reviewing visual outputs at a laptop and on printed storyboards.
Workload-review concept.

Evaluation template ·. No measured results

Compare the same work.

Agree the workload, conditions and acceptance criteria before comparing a baseline with Azita.

Agreed workload
[Agree before evaluation]
Same input and scope
[Agree before evaluation]
Acceptance criteria
[Agree before evaluation]
Evaluation template. No measured results.
Comparison basisCurrent baselineAzita
Output qualityEvaluate against the agreed acceptance criteria.Current baselineTo measureAzitaTo measure
Completion timeUse the same start and finish definitions.Current baselineTo measureAzitaTo measure
VolumeRecord the amount of work in the agreed unit.Current baselineTo measureAzitaTo measure
Data locationRecord the processing location and relevant boundaries.Current baselineTo measureAzitaTo measure
Total costCompare the same scope and included cost items.Current baselineTo measureAzitaTo measure

Evaluation template only. Every result remains to be measured; no saving, performance advantage or verified deployment is claimed.

Arrange a workload evaluation →

Commercial basis

Proposal based on your workload and deployment.

There is no price list on this page. Your proposal sets out what is quoted, the commitment and what is included.

Named in your proposal where they apply

  • Licences for the compositing and pipeline tools involved
  • Integration with your storage, pipeline and render management
  • Artist review time for the passes
  • The commitment, and what is included

Compare quality and total cost on your own workload before you decide.

How pricing works →

Where this stands today.

Available to evaluate on your own workload. On the Azita fleet, or on an installation in your building.

Arrange a workload evaluation →

Who it is for

Who this is for.

An episodic queue is a steady workload on its own. It suits houses that already have a render room, a content-security assessment, and a grind their artists would rather not do by hand.

  • Post houses delivering episodic OTT with spare power in an existing render room
  • Content-security assessed studios in Mumbai and Hyderabad
  • Regional localisation and finishing vendors with an overnight queue
  • VFX supervisors who want the grind off the artists' desks without an upload

Not your kind of work? See other workloads →

Straight answers.

Do the frames ever touch a public cloud?+

Not unless your agreement allows it. Where frames are processed is set in your agreement before any work runs: on the Azita fleet, or on an installation in your own building. Your content-security assessor reviews the arrangement.

Is the quality good enough for a delivery?+

That is what the evaluation is for. Your supervisors pick the shots and your artists judge the passes. Where a pass needs a hand it gets one; where it does not, the artist moves on to the next shot.

Will it run with our tools?+

Your node-based compositing and pipeline tools stay yours. How they connect is confirmed against your own setup during the evaluation and set out in your proposal, before anything is signed.

What about our client's content-security assessment?+

The arrangements your assessor asks about are set in your agreement: where the frames are processed, who can reach them, which model versions run and what happens at exit. Which certifications apply to your deployment, and their status, are set out in your proposal.

How is it priced?+

Proposal based on your workload and deployment. There is no price list on this page. We agree a representative job and the acceptance criteria, then set out what is included, the commitment and the total cost next to what the same passes cost you today, before you decide.

Will a delivery ever depend on it?+

Not until your supervisors say so. The evaluation starts with passes your team would otherwise queue, judged before any deadline rides on them.

Other workloads

Voice

Voice agents for BFSI floors

Indic voice agents and every-call quality review for collections and service floors, on the Azita fleet or on an installation in your building.

Read this one →

Code

Private coding pods

Private coding assistance for engineering teams whose client contracts keep code off the public cloud, on the Azita fleet or on an installation in your building.

Read this one →

Health

Hospitals and diagnostics

Consultation audio and imaging AI for hospitals and the vendors that serve them, on the Azita fleet or on an installation inside the hospital.

Read this one →

Promo

Overnight promo and product clips

Promo and product-clip variants from approved stills, rendered on open models on the Azita fleet or on an installation in your building.

Read this one →

How pricing works →Security and compliance →All workloads →

Start with your own workload.

Send us one episode's grind

A handful of shots your artists would rather not roto by hand, on material you are cleared to share for a test. We agree the acceptance criteria with your supervisors, then compare the passes, turnaround and total cost with how you work today. We’ll review what you need to run and contact you to discuss the right setup.

Arrange a workload evaluation

AI factories in buildings that already have power.

Platform

  • How it works
  • RackQuilt
  • Token Mills
  • AzExchange

For buyers

  • AI for business
  • Voice agents for BFSI floors
  • Private coding pods
  • Hospitals and diagnostics
  • VFX assist for post houses
  • Promo and product clips
  • Creators
  • Agencies
  • Engineering
  • Finance
  • Healthcare & BFSI

For buildings

  • Estates
  • For building owners

Tools

  • Pricing
  • Room illustrations

Proof

  • Trust & compliance
  • Sources
  • Research

Company

  • Company
  • Team
  • Careers
  • Press
  • Investors
  • Contact
AI enquirieshello@azitalabs.comProperty enquirieshello@azitalabs.com

© 2026 Azita Labs Private Limited

PrivacyTermsHosting terms

New Delhi, India