ImageX / Services / References & training / train.face

Train "me" from 10–20 photos

Being assembled Not in the app yet — the engine route is listed below so you can see exactly what it needs.

Olive oil, Tuscan table — made with ImageX — A tall glass bottle of golden extra virgin olive oil on a sunlit rustic Tuscan wooden table, sprigs of rosemar…
**Z-Image Turbo**

Free diver, cathedral of light — made with ImageX — A free diver descending into a deep blue ocean cenote, god rays piercing the water from above, tiny silhouette…
**Z-Image Turbo**

Night market, Taipei — made with ImageX — A busy night market street in Taipei after rain, red lanterns reflecting on wet asphalt, steam rising from foo…
**Z-Image Turbo**

Red door in the dunes — made with ImageX — A single bright red door standing alone in vast pale sand dunes at dawn, long shadows, surreal minimalist phot…
**Z-Image Turbo**

Serum on stone plinth — made with ImageX — A frosted glass skincare serum bottle with a dropper standing on a travertine stone plinth, soft studio light,…
**RealVis XL**

Field watch, hard light — made with ImageX — A steel field watch with a cream dial lying on dark slate, hard sunlight casting sharp window-blind shadows ac…
**Z-Image Turbo**

Coffee flat lay — made with ImageX — Flat lay top-down of a specialty coffee setup on warm white paper: ceramic pour-over, kraft coffee bag, scatte…
**Z-Image Turbo**

The chef — made with ImageX — Environmental portrait of a smiling female chef in a white apron in a busy restaurant kitchen, soft window lig…
**RealVis XL**

01 — How it works

Three steps.

01Describe it

Tell us what you want in plain words, or upload a reference.

02We route it

Auto sends it to the engine best at references & training and shows you which one and why.

03Perfect & download

Vary, fill, upscale 4×, remove the background, then download — with the AI label in the file.

02 — What you get

The spec.

DeliverableTrain "me" from 10–20 photos

OutputUp to ~2 megapixels native; 4× upscale on demand

Price300 credits per picture (≈ £3.00)

StatusBeing assembled plan: Partial

Engine routeHouse LoRA trainer exists (DiffSynth-Studio via ie-video lora-train); per-customer productisation NEW

FormatsPNG with the AI label · transparent PNG · SVG where it applies

03 — Questions

About train "me" from 10–20 photos.

Q01How long does train "me" from 10–20 photos take?

Most pictures develop in 30–60 seconds on our own GPUs; edits that keep your composition take a few minutes. The app shows your place in the queue and a live estimate.

Q02Can I use the result commercially?

On any paid plan, yes, subject to the content policy. Free-plan pictures are public and CC BY-NC 4.0. The engine and its licence are recorded with every picture.

Q03What if I don't like it?

Press Vary for new takes, or Fill with a brush to change just one part. A failed render is refunded automatically.

Q04Which engine makes it?

Auto routing picks it for you; today that's House LoRA trainer exists (DiffSynth-Studio via ie-video lora-train); per-customer productisation NEW. You can override it.

Q05Do my uploads leave your servers?

No — the default engines run on our own GPUs. Uploads are deleted after 30 days unless you save them.

04 — Related

You might also need.

→Style referenceStyle reference: upload 1–5 images, match their look300 crBeing assembled →Character / omni referenceCharacter / omni reference: keep a person, character or object identical300 crBeing assembled →Structure referenceStructure reference: keep the composition, pose and layout300 crBeing assembled →MoodboardsMoodboards: a saved bundle of refs + palette + prompt fragments, reused as a "profile"300 crComing