Ideogram
Ideogram/ideogram-v4-5-edit/Released Sep 2026

Ideogram v4.5 Edit

Reference-guided image editing with pixel preservation

Commercial use
Image
Ideogram v4.5 Edit

About Ideogram v4.5 Edit

Ideogram v4.5 Edit transforms a source image using text instructions, with optional reference images and masks for targeted changes.

Regular editing supports broad transformations, while high precision restores unchanged pixels to preserve areas outside the edit. Up to four reference images can guide an edit, reduced to three when a mask is supplied. Masks must match the source dimensions: black regions are edited and white regions are preserved, and both regions must be present.

Output preserves the source geometry by default, with downscaling when needed. Only unmasked regular edits can pick a different aspect ratio and resolution (1K or 2K), and Ideogram prices each image by quality tier only. Four quality tiers cover quick iteration through final designs.

See what this model can do

A handful of real prompts and their outputs.

Before and after of a flower shop storefront: the dark green Petal & Stem sign becomes a burgundy Wild Roots sign.
Text Replacement
Storefront Rebrand
"Swaps the shop name in matching gold serif lettering and recolors the frontage while the flowers and street stay put."
Before and after of an outdoor cinema poster translated from English into Spanish with the same layout.
Localization
Poster Translation
"High-precision edit rewrites every line in Spanish, accents included, keeping fonts, sizes and artwork unchanged."
Before and after of a jam jar: a red Strawberry Jam label becomes a blue Blueberry Jam label with blueberries beside it.
Packaging
Flavor Variant
"Changes the label text, color, icon, jam and props in one instruction for a new product variant."
Before and after of a street with a sunflower mural in summer, turned into a snowy winter street with a winter landscape mural.
Scene Edit
Summer to Winter
"Repaints the mural and the real street for a new season while the building and camera angle stay fixed."
Before and after of a book cover: a lakeside cabin photograph restyled as a flat vector illustration with the same title.
Restyle
Photo to Vector Cover
"Converts the whole cover to flat illustration while keeping the title and author type exactly in place."
Before and after of a cafe chalkboard menu: every coffee price is raised and a new Oat Latte line is added.
Menu Update
Chalkboard Menu Prices
"Rewrites four prices and adds a fifth item in matching chalk handwriting and column alignment."
Before and after of a wine bottle label: the vintage changes from 2019 to 2021 and the region from Toscana to Piemonte.
Label Edit
New Vintage Label
"High-precision edit swaps just the year and region in the label's own serif type, leaving every other pixel alone."
Before and after of a grey t-shirt mockup: the arched print text changes from Stay Wild to Go Outside.
Merch Mockup
T-Shirt Graphic Text
"Re-sets arched display text and a small caption on fabric while the sunset graphic and folds stay intact."
Before and after of a green countryside road sign changed from Ashbury 12 to Willowmere 7.
Signage
Road Sign Swap
"Fits a longer town name onto the sign in the same road-sign typeface, keeping the arrow and landscape."

Ready to build with Ideogram v4.5 Edit?

Try Ideogram v4.5 Edit 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": "ideogram-v4-5-edit",
  "prompt": "A cat sitting on a chair",
  "input_image": "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/ox_zoom_out_1926_1076.png",
  "lock_unmasked": true,
  "edit_precision": "regular",
  "quality": "medium",
  "aspect_ratio": "auto",
  "resolution": "1K",
  "sync_mode": false
}'

Request parameters

Every field Ideogram v4.5 Edit accepts in the request body. See the API reference for response formats.

POSThttps://hub.oxen.ai/api/ai/images/edit
FieldTypeRequiredDefaultDescription
promptstringYes
—
Describe how to edit the source image, using the optional reference images for guidance.
input_imagestring
uri
Yes
—
Primary source image to edit.
input_imagesarray<string>No
—
Up to four reference images, or three when a mask is supplied, in addition to the primary source image.
maskstring
uri · nullable
No
—
Paint the part of Image 1 to change. Takes up to three reference images.
lock_unmaskedbooleanNotrueOnly modify the pixels within the masked region.
edit_precisionstringNo"regular"Regular performs generative editing. High uses precise editing with restoration of unchanged pixels.
regularhigh
qualitystringNo"medium"Image quality tier. Very low costs $0.008, low $0.03, medium $0.06, and high $0.22 per image, independent of image size.
very_lowlowmediumhigh
aspect_ratiostringNo"auto"
auto1:116:99:164:33:43:22:35:44:516:1010:162:11:2
resolutionstringNo"1K"
1K2K
image_sizeobjectNo
—
Pixel dimensions sent to fal, looked up from aspect_ratio and resolution in the size table below. Auto passes through unchanged.
seedinteger
nullable
No
—
Random seed. Omit to choose automatically.
sync_modebooleanNofalseReturn image data directly in the response.