Cubric Studio - Image Tools

Image Tools

Image operations for masking, painting, compositing, cropping, resizing, upscaling, and refining still assets from History.

Tool palette

The image tool palette is the rail down the left of the History workspace. Tools are stacked into labelled groups, and the group tells you what the tool produces:

Prompt — the Prompt Box and its operations.
Transform — Crop and Resize.
Enhance — Upscale and Remove Background.
Mask — Brush, Detect, Shapes, and Adjust. Everything that makes a mask.
Paint — Paint, Shapes, and Adjust. Real colour on the picture itself.
Composite: Paint Comp, Mask Comp, and Place. Blending or placing two of your images.

The Prompt Box stays open in the Mask and Paint groups, because a mask or a scribble and a prompt are one operation. The Composite group hides it: it ends at its own Apply and needs the column for its slots.

Image tools are non-destructive. Applying crop, resize, upscale, paint, a composite, or a prompt operation creates a new History entry so the original entry remains available.

Mask tools

Use a mask when a prompt operation should affect only part of the image. Everything that makes one now sits in the Mask group in the tool rail, and the four buttons all write into the same mask, so you can mix them freely:

Brush. Paint the mask by hand, with ten brushes to choose from.
Detect. Find it instead of drawing it — by clicking, by name, by colour, or automatically.
Shapes. Drop a rectangle, triangle, or ellipse and commit it.
Adjust. Grow, shrink, or reduce a mask you already have — and fill its holes.

None of it runs a model or downloads anything, apart from the detection methods noted below. It is all instant and all undoable.

After a mask is ready, pick an operation such as Detail from the operation strip above the prompt box. The active mask is passed into the operation when the selected model supports mask-based work. The prompt box stays open while you mask, so you can change a setting without leaving the tool.

To erase what you masked, use Inpaint with a prompt that names it, such as remove the man.

Brush

Paint the mask by hand. Switch between paint and erase in the options panel or with B and E, and set the brush size with the mouse wheel.

The brush is a pack of ten presets: Hard Round, Soft Round, Feather, Airbrush, Chisel, Calligraphy, Spray, Charcoal, Stipple, and Dry Brush. They resample to any brush size, and the same ten are available in the Paint group. Strokes stay continuous however fast you drag.

The brush also stays fast on a large picture: it now redraws only the area your stroke touched instead of the whole canvas, so masking, painting, and the Composite brushes no longer lag or leave jagged strokes.

Shapes

Drop a rectangle, triangle, or ellipse on the canvas, position it, then commit it with Add or Subtract.

Drag the shape to move it, or its handles to resize it.
Hold Shift while resizing to keep its proportions.
Hold Alt over a handle to rotate it.

The shape stays where you put it after you commit, so stamping the same ellipse three times is three drags rather than three set-ups. An uncommitted shape is a preview: leave the tool and it goes away.

Mask Shapes with the rectangle chosen: a rectangle over the middle figure with its corner and side handles, and Add and Subtract in the panel under the Shift and Alt hint — A shape waiting to be committed: drag it or its handles, then Add or Subtract.

Adjust

Adjust works over a mask you already have, which is why it sits at the bottom of the group — make the mask, then adjust it. Pick a mode, drag the slider, watch the live preview, then press Apply. Reset abandons it, and so does leaving the tool.

Grow. Push the whole mask outward.
Shrink. Pull it inward. The same slider row, running the other way.
Edge. Reduce the mask to a band around its own edge, set independently inward and outward.

The edge band is the one to reach for when a subject came out right but its outline did not: it lets you regenerate the boundary without touching the middle.

Fill sits in the same panel and closes enclosed holes in one press — the inside of a ring, the gap in a letter. You see what is about to be filled before you commit to it.

Mask Adjust in Edge mode: the masks on both hats reduced to green bands around their outlines, with Outward and Inward sliders, Apply, Fill and Reset — Adjust > Edge turns a mask into a band around its outline.

The same patch of sky twice: on the left a mask drawn as a ring, on the right the same mask after Fill, closed into a solid shape — Mask Adjust > **Fill**: a ring becomes a solid mask, so an outlined object is masked whole.

Detect

Detect is one rail button that opens four methods in a small strip beside it. All four end the same way: the result is drawn green as a preview, and you commit it with Add or Subtract.

Points. Click what you want and the mask snaps to it.
Text. Type what you want masked instead of pointing at it.
Auto. The face, hand, and person finder.
Colour. Pick a colour and select the pixels that match it.

One detection finds every match in a single pass, so picking a result — or changing your mind and picking another — does not run it again. Trying all of them costs what one used to.

While a detection runs, the status bar reports it with a timer and the Detect button becomes Stop. A slow pass over a busy image is not a frozen app, and you can call it off.

Points and Text run on a shared detection model of about 1.7 GB, fetched once. Auto uses its own smaller finders. Colour runs in the app itself, with no model. Press Esc to close the method strip.

A green preview is not a mask yet

A detection you have not added is only a proposal. Leaving the tool discards it, and generating without pressing Add no longer sends it — which it silently used to. That is also why operations needing a mask stay unavailable until you press Add or Subtract.

Points

Left-click what you want and the mask snaps to whatever you clicked — a face, a pair of headphones, the cup on the table. Right-click what to leave out when the selection grabs something by mistake. Click a dot again to remove it, or use Clear points to start over.

Dots are cumulative, but they describe one region per run. Click, hit Add, then start on the next part.

Cubric Studio Points mask tool: left-click and right-click dots placed on a dog's collar, the mask snapped to the collar and drawn green, with Clear points, Detect, and Add or Subtract in the options panel — Points snaps the mask to whatever you click. Green marks a region a detector found, so you can tell it from one you painted by hand.

Text

Type what you want masked instead of pointing at it — hair, cup, earring, bikini. Separate several objects with commas, and set the count for how many of each to find; a name with no count returns exactly one.

Every match comes back as its own thumbnail, so you pick which ones become the mask before committing with Add or Subtract.

Points and Text cover each other's weak spots. Clicking is precise, but thin strappy things — a strap, a handle, a chain — want more dots than you would expect, especially right-clicks to push the selection back. Naming the object handles those in one press.

Mask Text with hat typed and a count of 2: two numbered thumbnails returned and both cowboy hats masked green in the image — Text finds the object by description. The count says how many to look for, here two hats, and each match comes back as its own thumbnail to pick from.

Auto

Auto finds faces, people, or hands with no input from you. Choose whether detected areas should be drawn as boxes or as segments that trace the subject more closely, pick the candidates you want, then commit with Add or Subtract. In the example below, three faces were detected and two were selected.

Colour

Select pixels by colour: set the key colour, or press Pick and click it on the screen, set a Tolerance, then press Detect. Tolerance, from 0 to 100, is how far a pixel may stray from the key colour on any one channel and still count. Turn on Only touching the edges to take only the matching pixels joined to the border of the image, where a backdrop usually is, so the same colour inside the subject stays out. It runs instantly with no model, and changing a setting after a run runs it again.

Checking and undoing a mask

The mask options panel carries a black-and-white view that shows the mask exactly as the model receives it. It is the quickest way to catch stray specks before you generate. The same panel holds paint and erase, the brush picker, opacity, invert, and clear.

Cubric Studio mask black-and-white view showing the painted mask as white strokes on a black field, with the black-and-white toggle active in the mask options panel — The black-and-white view shows the mask as the model receives it — white is the area that will be regenerated.

Every canvas edit can be taken back with Ctrl+Z — a brush stroke, a Clear, a committed detection, an applied Adjust — and put back with Ctrl+Shift+Z. One history covers the mask and paint layers together, in the order you worked. It follows you between tools and starts fresh when you open a different image. Nothing else in the app has an undo; see Hotkeys.

Your mask reaches the model as you drew it

A masked operation used to close every hole in your mask and grow it slightly before generating, so a mask drawn as a ring around a subject arrived at the model as a solid blob. That no longer happens on any model, or in a composite: the shape you drew is the shape that is used. If you want a hole closed, press Fill in the Adjust panel, where you can see it happen.

Right-click a History entry for Copy mask, Paste mask, and Download mask. Paint and eraser strokes are carried separately, and Cubric warns if the two entries are different shapes.

Right-click the image for Clear mask, Convert mask to paint, Convert paint to mask, and Send to Composite. The two conversions are copies: the layer you converted from survives untouched, and what is already on the destination is kept.

Paint

The Paint group puts real colour on the picture. A rough scribble tells a model where, how big, and what colour — three things a prompt on its own cannot say. Paint a shape, mask it, run Detail over it, and the model works from your sketch instead of guessing.

The group has the same three buttons as Mask, pointed at the paint layer instead:

Paint. A brush, an eraser, and a colour picker, with the same ten brushes the mask has. Pick, beside the colour, takes a colour straight off the screen.
Shapes. The same rectangle, triangle, and ellipse, committed here as Fill or Erase in the colour you picked.
Adjust. Grow, shrink, or reduce your paint to a band around its edge, and fill the shapes it encloses.

The Paint tool with the Stipple brush: a rough stippled face painted beside the sheriff, the colour swatch with Pick and Apply, and the Brush and Opacity settings — A rough scribble in Paint, with the Stipple brush.

Adjust on paint is how you outline something. Grow a scribble and the new edge is filled in your current colour while what you already painted is left alone; shrink it and the edge is eaten inward with every surviving brushstroke keeping its own colour; reduce it to a band and the scribble becomes its own outline. Adjust has its own colour and Pick, shared with Paint, so you can change the outline's colour without leaving the tool.

Paint Adjust in Edge mode: the stippled scribble reduced to its own outline, with Outward and Inward sliders, Apply, Fill and Reset — Paint Adjust > Edge: the scribble becomes its own outline.

Fill works on paint too. It floods every enclosed area of your paint in the current colour, so a closed outline becomes a filled shape, and every stroke you already made keeps its own colour on top of the fill. Like the rest of the canvas, it is undoable.

The same patch of sky twice: on the left a pink paint outline drawn as a ring, on the right the same ring after Fill, solid pink inside — Paint Adjust > **Fill**: the closed outline floods with the current colour.

Your paint stays on the image while you switch to the mask tools — that switch is the point of the feature — and it is kept per image until you close the app. Undo covers it like anything else on the canvas.

Press Apply to bake the paint in as a new History entry. The original is untouched, so deleting the new entry undoes it. The opacity slider is what gets baked, so the new entry matches what you saw.

Composite tools

The Composite group blends two of your images and lets you watch it happen. Use it when a re-run fixed one part of a picture and ruined another, or when you want to drop one picture into another with Place, described below.

Open the image you want underneath, right-click it, and choose Send to Composite.
Open the image you want on top and pick a Composite tool.
Make the cut, then press Apply.

The selected image is always the one on top, so there is no direction to decide.

Paint Comp. Erase the top image and the one underneath shows through live where you erase. The brush paints the top one back, so the two are the reveal and its undo.
Mask Comp. Makes the same cut in one step from the mask already on the image. Everything the mask tools can select — brush, detect, points, text, shapes, adjust — can therefore drive a blend.

Paint Comp: the top image erased around the sheriff's head so the version underneath, still wearing its hat, shows through, with a preview of the underneath image and Apply in the panel — Paint Comp: erase the top image and the one underneath shows through.

Both tools open on the eraser, because revealing is the reason they exist. There is no opacity slider here: a composite is a hard cut, and a ghosted preview would disagree with the file that gets written.

Two images of different sizes are cropped to fill rather than stretched, and the preview on the canvas matches the file that gets written. Apply lands the blend as a new entry at full resolution; both originals are untouched.

Place

Place works differently from Paint Comp and Mask Comp: instead of cutting a hole in the entry on screen, it drops a second picture on top of it at its own size, and you position it yourself.

Fill its slot by dropping a file on it, clicking it to browse your project or your disk, or copying an entry elsewhere with Send to Composite and pasting it in. Drag the picture to move it, drag a handle to resize it, hold Shift while resizing to keep its proportions, and hold Alt over a handle to rotate it.

Turn on Remove background to cut the object out before it lands, so what you place is the object and not its box; turn it off and the original comes back at no extra cost. A second button beside Apply restores the picture to its original size and shape without moving it, if a drag went wrong. Press Apply to stamp it onto the entry as a new one.

A picture over 4K offers to shrink on the way into the slot, the same as any other import.

Localised edit

Mask an area before running an edit and only that area is regenerated — at the picture's own resolution.

A whole-image edit has to shrink your picture to the size the model works at. A masked edit crops to the mask instead, edits that crop, and stitches it back, so the picture keeps its original pixels and everything outside the mask is untouched.

It rewards a precise mask. For a broad change like a new pose, leave the mask off and let the model rework the whole image.

Available on Krea 2, FLUX.2 Klein, Qwen Image Edit, and Boogu Image Edit.

You can mask and reference at the same time: mask what should change, add a reference picture with the + button beside the prompt (see Prompt Box), and run Edit, for example her hair like this photo's hair or that jacket in this fabric. Drag the reference chips to reorder them when you use more than one and their order matters.

Inpaint

Inpaint regenerates the area you masked. Like any operation, it appears in the operation strip on models that support it — check the model reference for which ones do.

The model sees what is under your mask. It gets the whole picture as reference and regenerates only the masked pixels, so the result lands in the lighting, style, and perspective already there. What you type is the instruction:

Name it — erase. Write what to take out, such as remove the man or remove the tattoo. The bare word remove is not enough: it has to know what.
Describe it — replace. The masked area becomes what you described. Type hat and you get a hat.

Always write a prompt. The instruction is what tells the model what to do with the masked area.

For a removal, leave the style on None: styles apply to the patch rather than the picture, so the fill should match its surroundings.

If you outlined the object rather than filling it in, press Fill in the Adjust panel first. Masks are no longer closed for you behind the scenes — what you drew is what the model receives.

Cubric Studio with the rider of a horse masked in white, Inpaint selected in the operation strip, FLUX.2 Klein 9B chosen, and the prompt Remove the man. — Before: the rider is masked and the prompt names him. The example uses FLUX.2 Klein 9B.

The same image after Inpaint: the rider is gone, the horse and saddle are intact, and the sky behind him is filled in — After: the rider is gone and the horse and saddle are untouched — the sky behind him filled in from the picture.

Crop tool

Use Crop to define a new image frame. Choose Free to drag the crop handles unconstrained, Ratio to lock to a preset, or Resolution to type an exact output size. The ratio set includes model-friendly formats such as SDXL and Flux, social media formats, and cinema formats (2:1, 1.85:1, 21:9, 2.39:1).

A Divisible by control (default 16) rounds the crop's width and height to a clean multiple, which most models prefer. It only appears for Ratio and Free: Resolution mode already outputs the exact size you typed, so there is nothing left to round. Resize also defaults to 16. Applying the crop creates a new image entry based on the selected crop area.

The crop box snaps to your image edges when it gets close, so you cannot accidentally leave a one-pixel sliver of border.

The Crop tool: a crop frame over the image, and in the panel the Ratio, Free and Resolution types, the orientation toggle, a grid of ratios with 8:5 picked, Fill outside, Divisible by 16, and Apply — Pick a ratio, or switch to Free or Resolution, then Apply.

Crop outside the image

The crop box does not stop at the edge of your image. Drag it past any side and the new area fills with the colour you pick in Fill outside. Turning a portrait into a landscape, or giving a subject room to breathe, starts here.

That flat colour is the point. It is what you hand to a model next: switch to a model with edit capabilities, mask nothing, and describe what should be there. The model paints into the coloured area.

Extending the box and the Resolution mode are image-only. Video crop cannot extend past the frame.

Cubric Studio crop tool with the crop box dragged well past the edges of the image and Fill outside set to black, then the filled black border, then the generated result with the model having painted the scene into it — Extend the box past the image, pick a fill colour, then hand the result to an edit model and describe what belongs there. Most models with edit capabilities can do this — the example uses Krea 2.

Resolution mode

Resolution is the third mode beside Ratio and Free. Type an exact width and height and the box locks to that shape; the result comes out at exactly those pixels. Ratio and Free select pixels and keep them as they are, so Resolution is the only crop mode that resamples.

Resize tool

Use Resize when you need a different output size without changing the image through a generative model. Pick a Resolution Type, then Apply creates a new resized entry.

SDXL and FLUX. Pick a ratio preset and a multiplier (x1 or x2).
FREE. Type an exact width and height. Original Size puts both back to the picture's own dimensions, so you can try a size, change your mind, and start again without looking the numbers up.
MP. Type a target size in megapixels (1 MP = 1024×1024) and Cubric Studio works out the width and height from your picture's own proportions.
SCALE. Divide the picture's width and height by 1.5, 2, 3, or 4, keeping its proportions.

MP and SCALE show the result as a read-only width and height worked out from the source image, so you see the pixels you are about to get before you apply. The preview updates once you finish typing a width or height and click away; when ratio options are expanded, the settings panel can push the preview lower in the tool panel.

Under the size, Method picks the resampling filter (lanczos by default) and how the new shape treats the old one: crop by default, anchored at the centre or an edge, or stretch, pad, and a few other ways. Divisible by rounds both sides to a multiple, and the Transform row flips the picture vertically or horizontally and rotates it by 90, 180 or 270 degrees.

The Resize tool on Free: width 1744 and height 1088 with Original size, the method set to lanczos and crop with a center anchor, Divisible by 16, the flip and rotate options, a live preview, and Apply — The Resize preview updates while you adjust the settings.

Image Resize tool with ratio presets expanded and the live preview pushed lower in the settings panel — Ratio presets fill more of the panel, but the live preview remains available before you apply the resize.

Upscale tool

Use Upscale to enlarge the selected image. If no upscale model is selected, the tool behaves like a simple scale-up. If an upscale model is selected, Cubric Studio uses that model and can produce a better enlarged result depending on the model.

The model dropdown lists upscalers from your default models folder and, if you set your own, that one too, and a connected Pod's built-in upscalers appear in the list as well.

Applying the upscale creates a new image entry.

Image Upscale tool with upscale controls and no model selected — Without a selected model, Upscale performs a straightforward enlargement.

The Upscale tool with the 4x_NMKD-Siax_200k upscale model picked and the x1.5, x2, x3 and x4 factors, x2 selected — Selecting an upscale model routes the operation through that model for improved results when the model is suitable.

For a generative enlargement that invents real new detail, install the NVIDIA PiD Upscaler and run it from the Prompt Box. See Models for what it offers.

Remove Background

Remove Background is a History tool (Enhance) that cuts the subject out of an image using BiRefNet. Choose Transparent for a transparent PNG, or Color to fill the background with a solid color of your choice. Applying it creates a new image entry.

This removes the background, keeping the subject. To take an unwanted object out of a scene and leave the rest intact, mask it and use Inpaint with a prompt that names it instead.

Remove Background with Color chosen and the screen colour picker active over the image, the colour field with its Pick button, and the Remove background button — Choose Transparent or Color. Pick takes the fill colour straight from the screen.

Latent previews

When an operation is running, Cubric Studio shows previews as intermediate frames come back from the engine. These help you see whether a long operation is moving in the right direction before the final result appears.

Most models now preview in real colour, on every platform. A few still show a rough colour projection on purpose — Krea 2, Qwen Image Edit, and Wan 2.2 share a preview decoder with a known upstream bug that corrupts the real generation, so the mediocre preview is the safe choice until that is fixed.

Video previews on MiniMax H3 and LTX 2.3 now play the actual clip in real colour as it refines, rather than coloured blocks.

This now reaches every surface that shows a preview. A video run used to show nothing at all in the History workspace while it generated, and the floating preview window that appears when you minimise the app held a single frame; both now play the moving clip as it refines.

History workspace showing an early latent preview during a masked image operation — Latent previews appear while the operation is still running.

History workspace showing a later latent preview during the same masked image operation — Later previews make it easier to judge whether the current operation should continue.

Common image operations

Text to Image. Create a base image from a prompt.
Image to Image. Rework an existing image while keeping some of its structure.
Control. Copy the structure of a reference image and paint your prompt into it. See Models.
Edit. Change what you describe and leave the rest. Mask first for a localised edit.
Detail. Repair or refine a selected region such as a face, hand, or object.
Inpaint. Regenerate a masked area from a prompt, or erase what is under it by naming it.
Upscale. Enlarge a chosen result for sharper output.