Skip to content

Use reference pictures and your own uploads

On Images, a model that works from pictures shows them beside the words, with Add after them. Fill them from your uploads, the pictures you made or your cast, then name each in the prompt by its @name, such as @vera. A model that reads words only keeps them aside, unsent.

Updated · 5 min read

On this page
  1. 01Add pictures
  2. 02Name them in the prompt
  3. 03Change a picture you have
  4. 04Use a picture you made
  5. 05Files
  6. 06When you change models
  7. 07Elsewhere

Some image models make a picture from your words alone. Others also work from pictures you give them: a person to keep, a product to show, a place or a look to follow. On Images, the Text to Image tab shows the pictures the model you've picked takes beside the words, and none for a model that reads words only, so pick the model first.

Add pictures

  1. Pick a model that takes pictures. In the model menu, its row says how many, such as "10 image refs". A row that says "Words only" takes none.
  2. Press Add, the dashed tile beside the words. A chooser opens with three tabs:
    • Uploads: every picture you've uploaded, in any tool, with your folders.
    • Made: the pictures you've made.
    • Saved: your Cast.
  3. Or bring in a new file. At the top of the chooser, drop pictures, paste one with ⌘V (Ctrl V on Windows), or choose files. New files are kept in Uploads, so they're there next time, in every tool.
  4. Pick one or several and press Add. Each picture in the chooser shows its @name under its name, the name your words call it by.

You can also drop files straight onto a tile, or anywhere on the bar. Each picture shows as a spinning tile until it's up, and the line under the words says how many the model takes.

Name them in the prompt

Each picture carries its own @name on its tile, and your words call it by that name: "@vera holds @lentilo up to the camera, warm window light". Naming them tells the model which picture is the person, which the product and which the place.

  • A picture is first called by the name it already has: a file called vera.webp is @vera, and a cast member keeps their name, such as @Amara.
  • A file whose name says nothing, such as a camera's IMG_4823.jpg, is numbered instead: @image1. Two of your pictures never share a name: a second hero.webp is @hero_2.
  • A name in amber says little about the picture. Press its tile to open it big and change its name and its @name there, or press ⋯ at the foot of its tile and choose Rename. In the chooser, press ⋯ on the picture. The new @name goes with the picture to every studio and board, and your words change with it.

Type @ in the prompt to pick one: first the pictures in the bar, then From what you keep, which brings the one you pick into the bar. Paste words that name pictures you keep, and they come in by themselves while the model has room: the line under the words says Added from your Library, with Undo. A name that matches no picture is marked in amber, such as "No @kitchen yet": give the name to a picture in the bar, or leave it, and it goes as a plain word.

The × on a picture takes it out. If your words still name it, the name stays marked, with Undo to put the picture back, and Take it out of the words too to leave the name as a plain word.

Change a picture you have

The Edit a picture tab changes a picture you give it rather than make a new one. Add the picture under Picture to edit and say the change in the prompt; Generate stays off until it's in. Where the model takes more pictures, they go under More pictures: Nano Banana Edit takes up to 9 more, and Qwen Image Edit none. Name each by its @name to say what it's for, such as "put the scarf from @scarf on @vera". The tab's menu lists the models made to edit first, then the ones that also edit as they make.

To make a picture bigger, use the Upscale tab. To remove its background, relight it or erase something from it, use Edit & Enhance: see Upscale, cut out, relight and edit a picture.

Use a picture you made

Point at any picture in My images and press Use as reference. It goes straight in beside the words on Text to Image, and if the model you have picked reads words only, the bar moves to one that takes pictures. Edit this picture puts it on Edit a picture as the picture to change instead.

Once a picture is made, open it to see the pictures it was made from, under References beside its prompt, in the order they went in, each by the @name its prompt called it. Press one to see it big.

Files

Pictures can be PNG, JPEG, WebP or GIF. A large photo is made smaller on your device before it uploads, so a big photo isn't turned away for its size. A GIF isn't resized, so it has to be under 8 MB.

When you change models

If you switch to a model that reads words only, the pictures you added stay in the bar, kept aside and unsent, until you pick a model that takes them. If you've added more pictures than the new model takes, Generate stays off and the bar says how many to take out.

Most models cost the same with pictures as without. Seedream 5.0 Pro adds a little for each picture past the first, and the price on Generate always includes it. On a board, or for a UGC ad's opening picture, a cast member wired in sends up to three pictures of them (their face, their look and their sheet), and the price counts each one.

Elsewhere

  • Video works from pictures too, as start and end frames or image refs: see Start and end frames, and reference clips.
  • On a Creative Board, wire picture cards into an image card: each wire is a reference picture, up to what the card's model takes.

If a picture shows a real person, see Real people: faces, voices and consent.

Was this helpful?

Still stuck?

A person reads every message.

Usually within 4 hours on a working day. support@team.vessero.com