Kling/kling-image-v4-0/Released Nov 2026

Kling Image 4.0

Photos that look taken, not generated, at up to native 8K. Sets long, exact text in posters, pages and packaging, and keeps people, products and places from up to 10 reference images.

Commercial use
Image
Kling Image 4.0

About Kling Image 4.0

Kling Image 4.0 generates photographic images at 2K, 4K, or native 8K from a text prompt, alone or guided by up to 10 reference images. It is built for camera-style realism: natural light, skin, and material detail that read like a phone snapshot, a documentary photo, or a film still.

It renders long, exact text in complex layouts, up to about 2,000 characters in one image, so posters, covers, menus, packaging, and infographics come out with their titles, body copy, and small print in place. Name a typeface next to the text it applies to, such as "Font: Nova Grid", and say where each block sits.

With reference images, give each one a role in the prompt as @image_1, @image_2, and so on: a person's identity from one, an outfit from another, a product or a style from a third. The aspect ratio follows the prompt and references at auto, or pick one of eight fixed ratios from 21:9 to 9:16. Price follows the resolution, plus a small fee for each reference image.

See what this model can do

A handful of real prompts and their outputs.

A soot-streaked welder with his mask pushed up sits on a crate with a lunch tin beside a rust-red ship hull.
Documentary
Shipyard Lunch Break
"Soot, stubble and frayed canvas under flat overcast light, like a frame from a photo essay."
A grandmother in a lilac cardigan blows out candles on a chocolate cake in a direct-flash phone photo.
Phone Snapshot
Birthday Flash Photo
"Hard flash shadows, a blurred hand and a crooked party hat: an unstaged family snapshot."
A man in a mustard jacket sits alone in a laundromat at night, lit by a glowing dryer and red neon.
Film Still
Midnight Laundromat
"A 21:9 frame with anamorphic falloff, film grain and mixed neon and fluorescent light."
A broadsheet front page with a blackletter masthead, a ferry headline, a photo, two text columns and a tides box.
Long Text
Harbor Ledger Front Page
"Masthead, headline, caption, body copy and a sidebar, each set in its own typeface."
A station departure board listing Kyoto, Osaka, Hiroshima and Nagoya in English, Japanese and Korean.
Multilingual Text
Trilingual Departure Board
"Four rows of times, kanji, hangul and platform numbers, aligned in LED columns."
A museum poster titled The Shape of Wind with a vermilion, cobalt and saffron diamond kite on off-white paper.
Poster Layout
Kite Exhibition Poster
"A title, a subtitle, three lines of details and a seal, each placed where the prompt put it."
A top-down view of a clear tide pool crowded with anemones, mussels, limpets, a sea star and a hermit crab.
Native 8K
Tide Pool in 8K
"Rendered at 9984 x 6656: every tentacle, shell ridge and grain of sand holds up when cropped."
Three reference images, a portrait, a koi bomber jacket and a flower-shop street, beside the photo that combines them.
Multi-reference
Three References, One Photo
"Her face, the jacket and the street each come from a separate reference image, shown on the left."
A sage-green olive oil tin labeled Casa Novello stands on stone beside a dish of oil, bread and an olive branch.
Packaging
Olive Oil Tin
"Six lines of label copy from small capitals to script, on a tin with a dented corner."

Ready to build with Kling Image 4.0?

Try Kling Image 4.0 in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.

curl -sSf -X POST https://hub.oxen.ai/api/ai/images/edit \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    -d '{
  "model": "kling-image-v4-0",
  "prompt": "A cat sitting on a chair",
  "aspect_ratio": "auto",
  "resolution": "2K"
}'

Request parameters

Every field Kling Image 4.0 accepts in the request body. See the API reference for response formats.

POSThttps://hub.oxen.ai/api/ai/images/edit
FieldTypeRequiredDefaultDescription
promptstringYes
—
Describe the image, and how to use each reference image: @image_1, @image_2, and so on.
input_imagearray<string>No
—
Reference images for people, products, places, or style.
aspect_ratiostringNo"auto"
auto1:14:33:43:22:316:99:1621:9
resolutionstringNo"2K"
2K4K8K