k-anvas Get k-anvas

k-anvas

paint with a prompt.

A photo editor and design tool where a sentence works like a brush. Fill, remove, extend or lift out any part of a picture, re-shoot it on another camera and film, and set it for print or social. The generative parts render on a GPU you run yourself.

Try the brush First release: coming soon

Desktop · iPad · iPhone

The k-anvas editor: a brass desk lamp, its base selected with a marquee, a new walnut base filled in, and the variant bar showing variant 2 of 3.
The k-anvas editor on desktop.

Try it here

Select it. Say it.

Brush over the lamp and press Remove, or switch to Fill and give it a new base. Your selection decides which pixels may change. Nothing outside it ever does.

Paint over the lamp

1/3
Operation

Remove what you select

A playback of real Qwen-Image-2.1 results from k-anvas's renderer tests, composited in your browser the way the app does it. In the app the same edit renders on your GPU in about 7 seconds.

Workflows

One composer. Every verb.

Generate, Fill, Remove, Expand, Extract and Compose all start the same way: a selection, a sentence, a button. Every result lands as a layer that remembers its recipe.

  1. Generate

    Start from a sentence.

    Describe a picture and get it at the size you need, up to about four megapixels. Words you ask for come out spelled right.

    4 to 5 s on the GPU at 1 MP

  2. Fill

    Change one part.

    Marquee the base, ask for a square walnut one, and get variants to choose from. The result is placed back through your selection, so the lamp, the desk and the light stay exactly as they were.

    6.6 s on the GPU

  3. Compare

    Choose with your eyes.

    See every variant side by side, hold to compare with the original, and keep the ones you like as layers. The rest wait in the Library, so nothing is lost.

    Variants · Compare · Keep as layers

  4. Remove

    Make it gone.

    Select Subject finds the lamp in one tap. Remove fills in the wall, the window and the desk that were behind it.

    6.6 s on the GPU

  5. Expand

    Give it room.

    Widen a square to 3:2 and the room carries on: more window, more wall, more desk. Your original pixels go back on top, untouched.

    10.4 s on the GPU at 1.5 MP

  6. Extract

    Lift it out.

    Extract returns the subject with real transparency, soft where the edges are soft. Drop it onto anything.

    6.6 s on the GPU, with alpha

  7. Compose

    Bring things together.

    Use up to ten pictures as references and say how they meet. k-anvas keeps track of which is image 1 and which is image 2.

    9.7 s on the GPU with two references

Straight off the renderer

Each of these took between 4 and 5 seconds of GPU time on the renderer k-anvas uses. The prompts are underneath.

  • A Swiss-style typographic poster titled FORMA, with a cobalt blue circle.

    “Swiss-style typographic poster … the title ‘FORMA’ in heavy grotesque letters” 4.0 s

  • An alpine lake at dawn with mist, snowy granite peaks and a rowboat.

    “Alpine lake at dawn, low mist over still water” 4.8 s

  • A rainy Tokyo alley at night with neon signs and a cyclist with a clear umbrella.

    “Rainy narrow alley in Tokyo at night … signs reading ‘喫茶 ミナト’” 4.5 s

  • A die-cut sticker of a cartoon fox reading a book, on a transparent background.

    “A die-cut sticker of a cartoon fox reading a book”, with transparency 4.0 s

  • A mid-century living room with concrete walls, an oak floor and a charcoal sofa.

    “Mid-century living room with board-formed concrete walls” 4.4 s

  • A wine glass half filled with red wine, on a transparent background.

    “A clear wine glass half filled with red wine”, with transparency 4.1 s

  • An overhead flat lay of white sneakers, a film camera, a notebook, earbuds and a watch.

    “Overhead flat lay on light grey paper” 4.6 s

  • A glossy cobalt blue cup on a saucer, on a transparent background.

    “A glossy cobalt blue ceramic coffee cup”, with transparency 4.1 s

Re-capture

Shoot it again, on another camera.

Choose a camera, a lens, an aperture and a film stock, and k-anvas develops your picture the way that film would: its colour, its tone, its grain and the glow around bright lights. Fourteen cameras, twenty-nine lenses, twenty-one films, and looks that set them all in one tap.

The original portrait, before Re-capture. Developed on this device
Looks
Camera
35 mm SLR
Lens
85 mm · Short telephoto
Aperture
f/1.4 · Razor-thin focus
Film
Colour negative · ISO 400

The film runs on your device, offline, in a second or two.

Real Re-capture output: the film stage of the app's next build, run on a real Qwen-Image-2.1 portrait. With a renderer paired, an optional optics pass also re-shoots perspective, depth of field and bokeh for the lens. It uses Qwen-Image-2.1 (research use only) and has not been tested against a live renderer yet.

The Re-capture screen on desktop: the picture, a strip of looks, and the camera bag with bodies, lenses, aperture and film.
Re-capture on iPhone.

Design

From a brief to every size.

Say what it is for and k-anvas lays it out: a headline, the details, a button and a picture, each set as large as it fits. Resize for… sets the same words again for a post, a story, a thumbnail or an A4 flyer, with the safe areas and the bleed already right.

From a brief

Kicker
Open studio
Headline
Light and form
Details
Sat 14 Nov · 10 to 6 · Atelier K
Button
Get tickets
Picture
Mid-century living room, board-formed concrete walls
Design it
Resize for

Instagram 4:5 · 1080 × 1350 px

An illustration of how a brief's layout moves between sizes, drawn in your browser around a real Qwen-Image-2.1 picture. In the app every part is its own editable layer.

Add a chart

Charts that stay editable.

Bars, columns, a donut, a big number or a timeline, drawn as shapes and type. Every bar and every label can still be changed, and one undo takes the whole chart back.

Templates

Eleven layouts to start from.

Posts, a story promo, a poster, a flyer, a business card and more, every part editable.

The Templates screen: a gallery of layouts to start a design from.

Brand kit

Your colours, your type, your logo.

Set them once and every brief and template uses them.

The Brand kit screen: colours, typefaces and a logo, with previews.

Print and social formats

Made for the press and the feed.

Sizes for the feeds, screens and print, from a Story to an A2 poster, with real DPI, bleed and safe areas on the canvas. Export at 0.5×, 1× or 2×, or as a PDF with crop marks.

A design in the editor with its print bleed and safe area shown.
  • ShapesRectangles, ellipses, polygons, stars, lines and arrows, as vector layers with fill and stroke.
  • Align and distributeLine layers up to each other or the page, and space them evenly.
  • Eleven typefacesOpen-licence faces for headlines and body text, built in and offline.

The editor

A real editor, made for touch.

Layers, masks, selections and adjustments, in a bold new layout: seven tool groups as labelled tiles, one clean top bar, layers and history as tabs, and big targets for a finger or a pen. Plain verbs, no sparkles.

Home: recent pictures and designs, with From a brief, Templates and Brand kit to start something new.
The editor with a generated lamp, the tool dock and the Layers tab.
From a brief: headline, details, a button and a picture prompt.
Add a chart, with the chart's kinds and its data.
Resize for…: the same design laid out for other sizes.
Re-capture, with the camera bag open.

Remove Background

One tap. A mask, not a deletion.

The background goes into a layer mask, so the original pixels stay underneath. An edge slider tunes the cut, and Select Subject refines it at full resolution.

A portrait of a woman in a teal sweater by a window. The same woman cut out onto a transparent background.

Upscale

Upscale on your own device.

Real-ESRGAN runs inside k-anvas, on your graphics card or your CPU, at 2x or 4x. It works offline and never touches your renderer.

A 4x upscale by classic resampling: the brass lamp stem is soft. The same crop upscaled 4x by k-anvas's on-device model: crisp edges and highlights. Classic k-anvas

Recipes

Every result remembers how it was made.

Prompt, seed, size, mask and model live with the layer. Reroll it, or edit the recipe and run it again, weeks later.

Fill · walnut basevariant 2 of 3
op
fill
prompt
Square dark walnut base
seed
1856410775
size
1024 × 1024 · Turbo
mask
marquee · feather 11 px
placed
outside the mask unchanged
Reroll6.6 s GPU

Layers

Keep picks as layers.

Every generation is a layer with a mask: hide it, paint its mask, change its blend mode, or bring back a variant you passed on.

  • SelectionsMarquee, lasso, magic wand and Select Subject, with add, subtract and feather.
  • AdjustmentsCurves, Levels and Hue/Saturation as adjustment layers, plus looks.
  • Branching historyUndo never throws work away. Go back, try something else, and both paths stay.
  • Command paletteEvery action a keystroke away, with familiar single-key tool shortcuts.
  • Brush, eraser, textPaint, retouch and set real type on its own layer.
  • LibraryEvery result goes to the Library first, searchable, with its recipe.

Your GPU

Your renderer. Your account.

k-anvas renders on an endpoint you deploy to your own Modal account. Your pictures go from your device to your GPU and back. There is no k-anvas server in between, no credits and no sign-up.

about 7 s
for a warm edit at one megapixel
65 to 130 s
to wake a cold GPU, shown as it happens, never a surprise
one token
per device, so each one can be paired and let go on its own
every result
shows its GPU seconds and what they cost you

Devices

At the desk and on the couch.

One app, laid out for the screen it is on. Touch gets big targets, tile sheets and gestures. A mouse and keyboard get the same screens with single-key shortcuts.

k-anvas on desktop, with a generated lamp and the layers panel.
k-anvas on iPad, in landscape.
k-anvas on iPhone.
  • Desktop appmacOS, Windows and Linux
  • iPadAdd to Home Screen from Safari
  • iPhoneThe same app, laid out for one hand

Before launch: the desktop builds are not signed yet, and the iPad and iPhone layouts have been tested in browsers but not yet on real devices.

part of the k-family

  • k-holeOS
  • k-chaincompanion
  • k-flowagentic remote control
  • k-streammedia center
  • k-anvaspaint with a prompt.

Get k-anvas

The first release is almost here.

Desktop

macOS, Windows and Linux.

Coming soon

Web app

iPad, iPhone and desktop browsers. Installs to your Home Screen.

Coming soon

What you will need

A Modal account to run your renderer. k-anvas pairs with it in a minute, and you pay Modal only for the GPU seconds you use.

k-anvas renders with Qwen-Image-2.1, which is licensed under the Qwen Research License for research and evaluation only. Please don't use k-anvas for paid or client work.