Getting Started

Framo is a workspace for generating, transforming, and composing AI images, videos, and 3D models on an infinite board, with a 2D pixel editor built in.

The big picture

The left icon rail is always there, and lists the sections you switch between:

  • Home: your library of boards, composites, 3D scenes, images, videos and 3D models.
  • Board: the infinite node board with the floating chat bar.
  • 2D Editor: the layered pixel/vector editor.
  • 3D Editor: the 3D Editor, which builds, renders and shares 3D scenes.
  • Video: the video editor, which cuts clips into one video on a timeline.

The Assistant, Friday, sits at the foot of the rail, on every account.

The Board section shows one open board (what Framo called a project until September 2026). With none open, it shows your recent boards to open and a field to start a new one. The 2D Editor edits composites, which belong to your library rather than to a board, so it opens with or without one.

Each editor keeps what it has open while you look elsewhere. A small dot on an editor's rail icon means it has something open; hover the icon to see its name and close it. If you move something to the bin from Home while an editor still has it open, Framo tells you, saves it, and closes it there first.

There is no keyboard shortcut for switching rail surfaces.

On the Board the top bar shows the open board's name (left, beside the Framo logo, which links Home), and your credit balance / plan (right).

The Board

The Board is the infinite surface where your generations live as nodes you can move, select, and connect. Each image, video, or 3D result lands here.

To work on the board:

  • Select a node by clicking it. What you select drives the AI's mode (see below).
  • Multi-select by holding Shift and clicking, or by dragging a selection box around several nodes.
  • Add your own image: right-click anywhere on the board to open the context menu, then Upload Image or paste from clipboard.
  • Board settings live bottom-left (gear icon) — toggle info badges, node edges, video auto-play, auto-place, and trackpad scroll/zoom.

Creating images, videos, and 3D models

You generate from the chat bar (2.0) or the AI sidebar (1.0). Pick a mode, pick an AI Model, write a prompt, then Generate (or Ctrl+Enter). The credit cost shows on the Generate button.

  • Image — text-to-image with nothing selected; image-to-image with one image selected; multi-image with several selected.
  • Video — animates images into clips. One selected image becomes the start frame; two images become start + end frames.
  • 3D — turns images into a 3D model. One image generates from a single view; up to 8 images combine multiple views for a more accurate model.

Prompt tools sit on the right edge of the prompt input: Favorites, History, Presets, an AI prompt Enhancer, From Image, and Dictate (speak your prompt; or hold ⌘D (Ctrl+D) with the prompt focused, and let go to stop). See Chat bar: generating images for the full composer.

New images first arrive in the Generation Collector — swipe right to keep a result and add it to the board, or left to discard.

Everything you make is saved to the Media Explorer (right side). Search by prompt, filter by images/videos, and drag any item back onto the board to reuse it. See Boards, media library & stock.

Steps chain together: a generated image can be selected as input for the next image, used as a video start frame, or turned into a 3D model. See the playbooks.

The 2D editor

The 2D Editor on the left rail is a pixel/vector editor for painting, masking, drawing paths, and editing layers. Open an image or composite in it from Home or the media panel with Open in 2D Editor. See 2D canvas editor.

From here you can generate edits (e.g. inpainting on a drawn selection) without leaving the image.

3D models

A 3D model you generate with the 3D mode, or add from the board's Add menu with 3D Model, lands on the board as a 3D model node and is listed under Home's 3D Models. Select the node to orbit it with Navigate 3D, frame it with Zoom to fit, and set its Background, Lighting and MatCap from its toolbar. The separate 3D Editor on the rail builds and path traces whole scenes. See 3D Editor. Scenes made in the previous 3D editor are not carried over to the new one.

Boards and saving

Everything on the Board lives in a board. The open board's name is in the top bar — double-click it to rename. The chevron beside it opens a menu to start a new board (New Board), switch to a recent one, close it, or Share Board. The board saves itself, so there is no save command; switching, closing or creating saves first. Boards are listed under Home. See Boards, media library & stock.

Getting help

  • Chat with Friday: press ⌘/Ctrl + K anywhere once you are signed in, or click the red dot near the foot of the left rail, and ask Friday, the red dot, your question in your own words, or hold ⌘D (Ctrl+D) and say it (e.g. "how do I get from a sketch to a 3D model?"). Friday knows every button in Framo and which of them are on your screen: it answers in its speech bubble, and when there is something to do, Show me walks you there step by step from where you are. A big goal ("I want a LoRA for my sneaker designs") is planned in stages, one walked at a time; ask a follow-up in the same bubble. Hold D anywhere you are not typing to ask out loud about what your pointer is on (it turns red while Friday listens), and Friday answers out loud. Rather keep it quiet? Choose Text only when Friday's intro asks, or switch off Talk out loud in Settings > AI > Friday: nothing is read aloud, and holding D still asks out loud. Until you have met Friday, the red dot opens its short intro over the page: who Friday is, talk or text, and where it lives on the rail. Talking, you move on by holding D and saying "next", then "done"; in text, with the Next and Done buttons in its bubble. Then Friday shows you around Home and on to your first board, unless you have made one already. Friday remembers what it has shown you and which buttons you have used, guided or not: a guide you left part-way picks up where you stopped (with Start over on its card), one you finished starts from the top when you ask for it again, and asking about something you have done before gets a quick reminder of where it is, with the walk-through offered rather than started. It opens straight on the chat: Friday flies in from the rail and lands beside the bubble you type into, and once you ask, both drop to the foot of the screen with the whole conversation above them. There is a learning path: eight guides in order, from your first image to turning an edit chain into a flow, each one's end offering the next; ask Friday for any of them. The send each guide walks you through is on us, once: the price beside Send reads On us, and anything more is charged as usual. Just start typing to ask; as you type it offers matching guides and your earlier questions. Asking costs no credits, up to 40 questions an hour.
  • What it cannot do: Friday knows which buttons are on your screen, reads the prompt, the settings and the cost in the chat bar when it is open, and gets a picture of the window with each question, though an image on the board can come out blank in it. It also reads your own account as you ask: your credits and plan, what failed in the last day and why, what is still generating, your LoRAs in training, the agent chat you have open, and how the pictures and videos you have selected or point at were made. It points and you act: it never clicks, selects or spends credits for you, and the one thing it types is a prompt you ask it for, into the chat bar, for you to send. Asked something while it walks you through a route, it answers about the step you are on and the route carries on from there. When the help pages do not cover a question, it says so.
  • Learn the chat bar in place: turn on the Explainer from the chat bar's ⋮ menu, then hover any control to read what it does.