Send to ShotGrid from the canvas
Before: download by hand from an outside tool.
Now: pick the shot from live lists, pass the checks, and get a receipt that links to the Version.
Direct send 7 August 2026. Desktop hand-off 28 September 2026.
How an artist’s AI image gets into ShotGrid without leaving the pipeline.
Send to ShotGrid: shipped August 2026
Two minutes? Read the five frames, then see what changed for artists.
Start with how a send works, frame by frame.
Start with the one picture, then how I built it.
Employer work. This page shows outcomes and the shape of the system only. The screens are real: Lupin desktop, on a test profile with my own illustrations and made-up shot codes.
Lupin, the studio’s AI image and video tool
Five frames. The last one opens the long read.
What it isThe studio’s canvas for making AI images and video.

Who forArtists at a film studio. I was the first hire. The team is now 40+.
Headcount as of October 2026.

What I didI built Lupin, and the send to ShotGrid.
July to October 2026.

What happenedArtists send work straight into ShotGrid. File names pass the checks first time.
Shipped August 2026.

NextClose the loop between prompts and approved work. Read the long version
Frames 2 to 5: Lupin desktop.
An AI image only helps a studio once it is in the pipeline. It needs the studio’s file name. It needs a stored version, linked to the right shot.

Download by handAn outside tool makes the image. The artist downloads it.

Rename by handThey rename the file to fit the studio’s rules, and hope it passes.

Keys on every machineEach artist also needs their own account and key.
Illustrations I made in Lupin.
Lupin runs in the artist’s browser. Artists wire nodes together on a canvas, or use a simple form. Every output lands in one gallery.




All four: Lupin desktop, on a test profile with my own illustrations.
Six canvas features, then how Lupin helps artists prompt each model with reference images.






All six: Lupin desktop, on a test profile with my own illustrations and made-up shot codes.
Each model reads reference images in its own way. Lupin shows the rules where artists pick the images, so nobody has to look them up.



Two images per person: a neutral frontal headshot and a frontal full-body shot. Plain background, even light, no expression.
A still that shows the look only: grain, brushwork, lighting, palette. No faces.
Do not save a contact sheet as the reference. Seedance reads a multi-view sheet as several people, and Wan and Veo want one subject per image.
Cite images in the prompt by order or by role: “the first image”, or “use @Style for the look only, not the content”.
Guidance I compiled from vendor documentation on 29 September 2026. Captures: Lupin desktop.
From a prompt to a Version in ShotGrid.

demo_010_sea_0040_harm_render_main_v0002. Lupin desktop.In the studio’s build of Lupin, these codes come from live ShotGrid lists.
Version numbers come from ShotGrid’s next free number. Nobody counts by hand.
File names follow the studio’s rules, so the checks pass with no renaming.
Every send lands in the studio’s version store, with dailies rendered on the farm.
Send the same file twice and Lupin asks first.
Direct send shipped 7 August 2026. Hand-off to the desktop tool shipped 28 September 2026.
The lesson from this is a note: what the pipeline checks first.

GenerateThe artist makes an image on the canvas, through the studio’s relay.

Pick the shotProject, sequence and shot come from live ShotGrid lists.

ValidateThe pipeline’s own checks run first. A refusal comes back as a checklist.

Hand offThe desktop Submission tool takes the file and creates the Version.

ReceiptA receipt in Lupin links back to the new Version.

TelemetryThe send is logged by person, sequence and task, for the funnel.
Frame 1: Lupin desktop. Frames 2 to 6: illustrations I made in Lupin. The studio’s ShotGrid screens stay private.
The artist works in the browser. Everything else happens around them.
Model calls go through the studio’s relay, so no keys sit on artist machines. A send passes the checks first. Then the desktop tool files it in ShotGrid and the version store, and logs it for the funnel. Pipeline media flows back onto the canvas.
The first three answer the three steps from before. Dates are ship dates.
Before: download by hand from an outside tool.
Now: pick the shot from live lists, pass the checks, and get a receipt that links to the Version.
Direct send 7 August 2026. Desktop hand-off 28 September 2026.
Before: rename by hand and hope it passes.
Now: files follow the studio’s naming rules, so pipeline checks pass unchanged.
July 2026.
Before: an account and a key on every machine.
Now: the studio manages access to the model providers, over three routes.
August 2026.
Artists pull approved and working media, including plates, onto the canvas.
Stable release, September 2026.
Each send is tagged by person, sequence, task and status. A funnel shows opens, sends, failures and work ready for review.
July to August 2026.
No time-saved or adoption figure is given here, because none has been measured.
Artists generate through three studio-managed routes to the model providers. Provider keys never sit on artist machines.
Colleagues built most of the relay underneath. My part was access for each person on top of it, and one direct provider route.
I set up direct deals with model providers. They brought early access and free tokens for research. Going direct to provider APIs, not image aggregators, also costs less.
Going direct also unblocked big references: artists work at 2K and 4K, a 4K PNG is often over 20 MB, and at the time the image aggregator capped an upload at about 20 MB. Sent inline to Google, a big reference often failed. Since 24 September 2026, Lupin sends any reference over 8 MB through Google’s Files API, by way of the studio relay: Google stores the image for 48 hours and the model reads it from a link, so far larger references go through. The upload is reused across parallel variants, and if it fails Lupin sends the image inline as before. Bigger references mean better detail for the model to work from.
My role at AcmeAI covers product, AI operations, hiring and partnerships. Lupin is the tool I built.
I decided what Lupin does for artists, what ships next and when it is ready, and I built it, July to October 2026.
I ran hiring and recruitment with AI. Candidate search across portfolio sites, CV review and interview scheduling are automated. I also set up the studio’s direct deals with model providers.
Lupin shares one code base, a monorepo, with the rest of the studio’s web platform. Other people’s work sits next to mine, so my changes went through pull requests.
I built it with AI coding agents, steered by skills I wrote. Three of them:
Checks run before the send. A refusal arrives as a list of fixes.
Each send carries a person, a task and a status. Record which tool sent it from the start too. It is harder to add later.
Prompts stay in the artist’s browser, on purpose. Any measure of what works has to respect that.
When this started, the aggregator capped a reference at about 20 MB, and Google’s inline route failed on big ones. A 4K PNG is bigger. Storing the file on Google’s side for 48 hours and sending a link fixed it.

I checked how hard it would be to turn the web canvas into an Electron desktop app. Standalone means no third-party costs and simple wiring.
The screens on this page come from Lupin desktop, the standalone build. It has no ShotGrid link, so the send is shown in illustrations.
It is a feasibility check, so there is nothing to link to.
Say what you are building and where it gets stuck. I read every message.