Beta is live · 167/200

Every image,
in your brand.

Set your palette, style, and “never include” rules once. Then generate as many images as you need — every one inherits your brand. No more stock photos. No more Photoshop.

5 free images · no card requiredsame brand, every image: editorial photography · 16:9 · webp
cellar.press/burgundy-2018-vintage
live
CCellar Press
Wine·Vintage·March 12, 2026

Why 2018 Burgundy Rewards the patient cellar

a wine cellar at golden hour
a wine cellar at golden hourwebp · 16:9

The 2018 vintage in Burgundy is one that rewards patience. After three challenging seasons, conditions finally aligned for the kind of vintage that ages into something extraordinary — if you can wait.

Share
1 / 4 · same brand, new prompt
How it works

Three steps. Then never again.

Once your brand is set, every image inherits it. The only thing you change is the prompt.

01 · brand
Set your look once
Palette, render style, and a 'never include' list. Lock it once — it's the only configuration the model ever sees.
02 · prompt
Describe the image
Type a prompt, pick a size. Your brand is already applied — palette, style, and exclusions ride along automatically.
03 · ship
Generate and use it
Get an on-brand image in seconds. Download it or grab the hosted URL — drop it wherever you need it.
Brand · once

Set your look once.

The biggest problem with on-demand AI imagery isn't quality — it's consistency. Your dashboard locks the variables that matter, so the model only changes what should change: the subject.

Aspect & format16:9 · webp
Styleeditorial photography
Palettelocked to your hex list
Never includetext · watermarks · faces
Providerauto-routed by cost
Brand · winecellar.dev
active
Aspect16:9
Formatwebp
Styleeditorial photography
Moodwarm, low contrast
Palette
Never include
text overlayswatermarkspeople's faces
Made for every surface

One brand. Every size you ship.

Different aspect ratios per surface. Your brand applied to every output, automatically.

[ BLOG HERO ]16:9
a wine cellar at golden hour, editorial photography
a wine cellar at golden hour
16:9
Article hero images
A hero for every post that actually matches the topic — and your brand. No more recycled stock.
[ OG / SOCIAL ]1.91:1
OG social preview of a wine cellar interior
2018 burgundy vintage, social preview
1.91:1
Social preview images
On-brand OG images for every page. Twitter, LinkedIn, iMessage previews — all looking like you.
[ NEWSLETTER ]4:5
vineyard at dusk with rolling fog, vertical crop
vineyard at dusk, vertical
4:5
Newsletter visuals
Substack, Beehiiv, Ghost. Tall vertical-friendly crops made for inbox-first reading.
[ DOCS ]1:1
wine decanter and glass on burgundy linen, square crop
decanter & glass on linen, square
1:1
Docs illustrations
Square illustrations for concept pages and tutorial steps. Always in your style.
Why not just…

Stock looks like stock. AI looks generic. Yours doesn't.

Other tools give you images. We give you images that look like you.

Looks like your brand
Stock
No
Generic AI
No
drifts every gen
Inktag
Yes
locked config
On-demand, in seconds
Stock
No
search & license
Generic AI
Partial
then re-edit
Inktag
Yes
one prompt
New unique image per post
Stock
License each
$ per use
Generic AI
Yes
Inktag
Yes
Render time
Stock
Instant
if licensed
Generic AI
30–60s
interactive only
Inktag
<2s cached
No Photoshop step
Stock
Depends
Generic AI
No
crop & cleanup
Inktag
Yes
Locked “never include”
Stock
Generic AI
No
drifts
Inktag
Yes
config-level
FAQ

Questions before you give us a dollar.

We expect a few. Email hi@inktag.io if yours isn't here.

01How do I get started?
Sign in with your email — no application, no waitlist. You start with 5 free images so you can set up your brand and try it before paying anything.
02Do I need a credit card to start?
No. Every new account gets 5 free credits up front. When you run out, a $9.99 pack adds 50 more credits — no subscription, buy more whenever you need them.
03What image-gen model is under the hood?
Right now we generate with Google's Gemini image models, tuned so your brand settings — palette, render style, and exclusions — steer every output. As the model landscape shifts we may route across providers; the point is you never have to think about it.
04How do I use the images once they're generated?
Generate from the dashboard, then download the file or copy the hosted URL and drop it wherever you need — blog, newsletter, social, docs. A developer embed and API are on the roadmap, not in this beta.
05Where do my generated images live?
Each render is stored on a fast CDN and served from a stable URL, so you can hot-link it or download and host it yourself. Bring-your-own storage (S3 / R2 / Cloudflare) is planned post-launch.
06Do you train on my prompts or outputs?
No. Your prompts and rendered images belong to you. We log prompts briefly to debug routing, never train on them. Image outputs are deleted after the cache TTL you specify.
07How much will it cost after beta?
We're using the beta to figure out what pricing makes sense. Current thinking: usage-based with a free tier for indie bloggers and a per-render rate after that. Selected beta participants get founder pricing locked in for life — whatever rate you're on at launch is yours forever, even when we raise prices later. Beta-only; not extended to the launch waitlist.
08Who is this not for?
If you want pixel-perfect Photoshop control — this isn't it. If you don't have a clear brand look — set one up first, then come back. If you're trying to make memes or one-off images — Midjourney is better. We're built for repeated, on-brand imagery across many surfaces.
Beta is live · 167/200

Start with 5 free images.

Set your brand once, then generate. No card required to start — buy more credits whenever you run out.

Beta seats
167 / 200
33 left · hand-picked, no card

Founder pricing locked in for life · beta only