Prompt Box
The Prompt Box is where you choose the model, operation, prompt text, media inputs, and generation controls for the next Cue.
Compact and expanded modes
The Prompt Box opens in its compact mode by default. Compact mode keeps one prompt line visible so the Gallery can stay focused on media.
Use the small arrow at the top center of the Prompt Box to switch to expanded mode. When expanded mode is active, the arrow is rose-pink and the prompt field gives you more room for longer text.
Your prompt draft survives navigation within a session, and each surface keeps its own draft, so moving between the Gallery and History does not lose unsent text.
The selected model's mascot peeks over the top edge of the Prompt Box every so often. It is decoration, not a control, and changes with the model's media type.
Positive and negative prompts
The default text field is the positive prompt. Use the prompt mode button on the left side of the text field to switch to the negative prompt, then describe what the model should avoid.
Not every model reads a negative prompt; the field only appears on the ones that do. On LTX 2.3 it was being ignored until 1.4 — anything you typed there did nothing. It works now, and leaving the box empty switches it off cleanly.
Click the mic beside the prompt field to dictate instead of typing, or hold Ctrl + Space from anywhere a mic is active, speak, and release. See Audio and Dictation for languages and cost.
Enhance prompt
The Enhance button beside the prompt rewrites a short idea into a full prompt, in the shape the selected model reads best. It opens the Enhance Prompt dialog: your words sit in Your prompt at the top, and Enhance writes the rewrite into Enhanced prompt below, with a line saying which language model wrote it and for which model. Enhance always reads your own words, so change them and press it again for a fresh rewrite. On a model with a negative prompt, the negative half gets a box of its own.
OK keeps the rewrite: the Prompt Box still shows your short words, the Enhance button stays lit, and Cue runs the rewrite. Edit your words afterwards and the rewrite no longer matches them, so it is dropped and the button goes dark. Empty the lower box before OK to run your own words as they are, and Cancel leaves everything as it was. Where the rewrite runs is set in Remote > Where each job runs.
Add media
Drag a Gallery image or video onto the Prompt Box when you want to use that media as the source for a prompt operation. The Prompt Box adds the dropped item as a media input, then filters the available operations to the ones that can run with that media type.
For example, an image input can unlock image-to-image, upscale, or masked detail operations when the selected model supports them. A video input can unlock video operations such as Reference to Video when the selected model supports them.
Prefer not to drag? Click the + at the start of the media strip to add a reference picture instead. It is on the Gallery's Prompt Box and on a card's Prompt Box in History, image or video; see Prompting from a video for how a video card uses it. On Chatterbox it reads Add a voice and adds the voice the line is spoken in; see Text to Speech. It opens Choose media: one tile per Gallery card, showing the take selected on that card, with Upload file as the first tile for a file from disk, so you never have to leave the app to find one.
The picker opens showing images only. Filter is the Gallery's own filter, so you can switch other kinds back on, narrow by card marks, or change the order, without changing the Gallery behind it.
In History the picker has one more button, Add to history. Turn it on before you pick and the picture becomes a new entry on the card you have open, instead of a reference in the Prompt Box. A picture from another card is copied in, so deleting either one later leaves the other alone. This is how a picture from another card gets within reach of Paint Comp and Mask Comp. The button is off again every time the picker opens.
On a card you are masking, the same + lets you add a reference without losing the mask: paint what should change, add a reference for what it should look like, and run Edit with both in the same pass.
When an operation takes more than one image, the image chips are numbered. Drag them to change the order. Models that refer to images by position follow the order you set — for example Krea 2's identity Edit (scene first, subject second), Qwen Image Edit's combine-by-number, and Control on Krea 2 and FLUX.2 Klein (pose first, subject second). See Models for those usage notes.
First frame, last frame, or both
Drop a single image into the prompt box on a video model and it becomes the clip's first frame. The label along the bottom of the thumbnail is a button: click it and it reads Last frame, so the clip ends on that image instead of starting from it, and the model invents everything leading up to it.
Drop two images and you get both ends — first and last, in strip order.
This is useful for closing a loop, landing on a specific pose, or joining two shots you already have. LTX 2.3, Wan 2.2, and both MiniMax H3 models take it, including the end-frame-only case where the single image you give is the one the clip finishes on.
References on MiniMax H3 Reference
MiniMax H3 Reference works from references rather than from a frame, and takes up to nine images, three videos, and three audio clips at once.
Point at a specific one in your prompt by typing @. It lists what you have staged and drops in that item's tag — "the woman from <Picture 1> walking through <Picture 2>". Each thumbnail wears the tag it became, so there is nothing to memorise.
Reference detail decides how much of each reference the model reads. Match is the fast default. Max keeps more and is the one to use for a character sheet, but it costs time on every step.
Reuse previous prompts
Use Reuse Prompt when you want to continue from a previous generation without rebuilding the Prompt Box by hand. Reuse Prompt can copy prompt text, generation settings, model choice, images, video, and audio from an earlier Gallery card or History entry. Choose which parts carry over in Settings.
The default reuse behavior is controlled from Settings. Turn on Ask each time when you want Cubric Studio to show a chooser before it transfers anything into the Prompt Box.
Since 1.4, every control a generation used is recorded, whether you touched it or not — so reusing a run puts a setting you have since nudged back to what that run actually used. Generations made before 1.4 cannot be repaired: those values were never written down.
Reuse needs the picture, video, or audio you fed into that generation to still exist. Cubric Studio no longer keeps a hidden copy of every input the way earlier versions did, so deleting a card can break a later Reuse of anything built from it. Archive a card instead of deleting it and Reuse keeps working exactly as before; if an input really is gone, Reuse tells you which ones it could not bring back and carries over the rest.
In the Gallery, use Reuse Prompt from the card controls when you want to start a new Cue from an existing card. If Ask each time is enabled, the chooser opens before the Prompt Box is updated.
In History, hover an entry to access Reuse Prompt for that exact output. This is useful when a later branch is not the one you want to continue from.
Choose model and operation
Every operation your model can do sits above the prompt box as a row of chips, with the current one lit. Click a chip to switch operation. The same strip appears inside the parameters popup, so you can change operation without closing it.
An operation you cannot run right now stays visible but dimmed, and hovering it says exactly what is missing — needs 1 image, paint a mask first, takes at most 2 images. Nothing disappears from the strip, so it doubles as a checklist of what the current setup can run.
Clearing the last image drops you back to text-to-image on its own, and the operation you chose returns the moment you add an image again.
Click the model button above the prompt to choose a model. It opens a full-screen grid of preview tiles, like the Model Library, so you pick by looking at the work rather than reading names. LoRA and upscale settings open from the model's own tile.
The same picker is reachable without leaving the Gallery: hold Tab for the radial menu and pick Models. See Hotkeys.
How to prompt each operation
Operations want completely different prompts. Inpaint needs an instruction, and an empty prompt does nothing: describe what should fill the mask, or name exactly what to remove (the bare word "remove" is not enough on its own). Upscale is usually best with no prompt at all. Edit wants an instruction rather than a description.
Open the parameters popup and use the ? above the operation strip. It opens a short guide for whichever operation you are on: what the prompt is for, a couple of examples, and the mistake people usually make.
The guide follows your model as well as your operation, so the SDXL family is pointed at comma-separated tags while the newer models are pointed at plain sentences.
Model settings
Use the cog beside the model selector to open the parameters popup. When the active model is running one or more LoRAs, a LoRA rack sits at the top of that popup: one row per LoRA, with its name, strength, and a bypass switch that mutes it for the next run without removing it from the model, handy for A/B comparisons. The rack renders nothing when the model has none loaded.
The rack only shows what is already loaded. To add, remove, or swap which LoRA or upscale files the model uses, open LoRA & Upscale from the model's own tile in the model picker.
LoRA and upscale model folders are configured from Settings. Once Cubric Studio knows those folders, the LoRA & Upscale overlay lets you pick from the installed files while you work.
The LoRA picker there is a searchable, collapsible folder tree, so long or nested names are easy to find without clipping. Each LoRA slot has its own bypass toggle too.
Prompt controls
The lower controls in the options panel change with the selected model and operation. Image operations can show ratio and batch controls. Upscale can show upscale factor, grid, and denoise controls. Video operations can show quality, duration, motion, ratio, and resumable video controls. The video ratio picker offers 1:1, 9:16, 16:9, and, since 1.4.2, a wide 21:9, on every video model and at every quality level.
Control adds a Control Type picker on models that offer more than one kind of structure, and a Control Strength slider on Krea 2, FLUX.2 Klein, Chroma, and the SDXL family. See Models.
A control that would do nothing is hidden rather than shown doing nothing. The ratio picker disappears on operations that take their shape from the input image — every Krea 2 operation except Text to Image and Image to Image, Chroma's Control, Detail, and Upscale, and Klein's Control and Edit. Batch is hidden on SDXL's Image to Image and Control, which only ever return one image.
Models that ship built-in styles — such as Krea 2 and Qwen Image Edit — show a style strip of preview cards plus a Stylization slider for how strongly the style applies. On image-to-image, a Denoise slider controls how far the result moves from your input image.
The two FLUX.2 Klein cards carry different style sets. FLUX.2 Klein 4B offers eight: Muppets, Cartoon, Jojo, Anime, Chibi, Doodle, Vintage, and Aesthetic. FLUX.2 Klein 9B offers seven: Storybook, Comic, Anime, Chibi, Doodle, Vintage, and Watercolour. Each card installs its own style files, so a name the two share is still a separate style.
Cue and Loop
Click Cue to add the current Prompt Box state to the in-app queue. Cubric Studio snapshots the prompt, model, operation, media inputs, and current controls when you Cue the job.
Hold the Cue button for about a second to arm Loop. Loop keeps triggering generations from the latest Prompt Box state while it is active, so you can keep editing the prompt, switching settings, or trying model options as outputs arrive. Click the Loop button again to turn Loop off.
On a paid cloud model, the price of the next run appears beside Cue before you press it, billed to your own DeepInfra account. A staged stack quotes the total for every card it will run on.
Use the separate Queue page for the Cue side panel, job review, stop, cancel, and clear controls.
Resumable videos
Some video operations can run in a resumable two-stage mode. Turn on the resumable video control before you Cue the video. The first stage creates a lower-resolution preview card so you can review the motion before committing to the final pass.
A preview card is not a finished video, so opening it does not take you to the History page. Use the check button to finish the video in place, continuing from the preview stage. Use the branching button to create a separate final card while keeping the preview available for another second-stage attempt.
Branching is useful when you want to change LoRAs or other model settings after seeing the motion preview, then compare several final-stage results from the same first stage.
Video controls sit below the Prompt Box
Open a video card and its transport controls (play, frame step, trim, loop, mute) sit directly below the Prompt Box instead of above it, so a Prompt Box popup can no longer cover them.
Volume opens from the speaker button: click it to mute or unmute, and hover or focus it to reveal a vertical volume slider.