Change materials & backgrounds
Restyle an image, change how surfaces look, or place the subject in a new setting. Natural-language direction keeps the edit easy to describe and easy to repeat.
DreamImage 2
Edit what matters. Keep everything else.
Change a background, remove distractions, or replace one specific object with a natural-language prompt. DreamImage 2 brings focused AI image editing to DreamAPI.
CapabilitiesOne image.
One image.
One clear edit.
Describe the change you want. DreamImage 2 applies it while keeping the subject, composition, and visual context recognizable.
Remove unwanted objects
Clean up crowded photos without rebuilding the whole scene. Remove people, clutter, or distracting elements and let the model fill the space around the edit.
Replace a specific object
Point the prompt at one item and say what should take its place. DreamImage 2 updates the selected object while preserving the wider image.
Simple workflow
DreamImage 2 keeps the workflow focused: one source image, one instruction, one edited result.
Before & afterOriginal in.
Original in.
Edited out.
Each edit keeps the original structure and content — only the part you describe changes.
Original
Edited
Materials & backgrounds
Restyle any surface in one pass.
Render the character as hyper-detailed hand embroidery artwork while preserving the original pose and structure.
MaterialsStyleBackground
Original
Edited
Style transfer
Change the look, keep the subject.
Change this image to a 90s retro anime style.
StyleMaterials
Original
Edited
Object removal
Clear the frame, keep the moment.
Remove the other people, leaving only me.
RemovalCleanup
Original
Edited
Object replacement
Swap one object, preserve the rest.
Replace the torch in hand with a sword.
ReplacementSubject
Developer APIAPI now
Open DreamAPI Workspace →
API now
available.
Send one publicly accessible image URL and one edit prompt to the async endpoint /api/async/dreamimage_2.0. The API returns a task ID you can poll, or connect to a callback for automatic delivery — fixed at 10 credits per request, with JPG, JPEG, PNG, and WEBP inputs.
01
Provide an image
Use a public JPG, JPEG, PNG, or WEBP URL as the source for the edit.
02
Describe the change
Write the edit in plain language — change a background, remove an object, or replace a subject.
03
Retrieve the result
Receive a task ID, then use DreamAPI polling or a callback to collect the edited image.
edit
const response = await fetch('https://api.newportai.com/api/async/dreamimage_2.0', {
method: 'POST',
headers: {
'Authorization': `Bearer ${process.env.DREAMAPI_KEY}`,
'Content-Type': 'application/json'
},
body: JSON.stringify({
image: 'https://d2t5pyzt5qvy2d.cloudfront.net/api/static_resource/prod/default/INj5UrnnrKIzCR1uYBWv0.png',
prompt: 'Replace the background with a beach sunset scene'
})
});
const { data: { taskId } } = await response.json();curl -X POST 'https://api.newportai.com/api/async/dreamimage_2.0' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer {{key}}' \
-d '{
"image": "https://d2t5pyzt5qvy2d.cloudfront.net/api/static_resource/prod/default/INj5UrnnrKIzCR1uYBWv0.png",
"prompt": "Replace the background with a beach sunset scene"
}'HttpClient client = HttpClient.newHttpClient();
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create("https://api.newportai.com/api/async/dreamimage_2.0"))
.header("Content-Type", "application/json")
.header("Authorization", "Bearer {{key}}")
.POST(HttpRequest.BodyPublishers.ofString("{\"image\":\"https://d2t5pyzt5qvy2d.cloudfront.net/api/static_resource/prod/default/INj5UrnnrKIzCR1uYBWv0.png\",\"prompt\":\"Replace the background with a beach sunset scene\"}"))
.build();
HttpResponse<String> res = client.send(request, HttpResponse.BodyHandlers.ofString());import requests
response = requests.post(
"https://api.newportai.com/api/async/dreamimage_2.0",
headers={
"Content-Type": "application/json",
"Authorization": "Bearer {{key}}"
},
json={
"image": "https://d2t5pyzt5qvy2d.cloudfront.net/api/static_resource/prod/default/INj5UrnnrKIzCR1uYBWv0.png",
"prompt": "Replace the background with a beach sunset scene"
}
)
print(response.json())Pricing plansTop up credits.
Top up credits.
Pay as you generate.
One credit pool for every model on DreamAPI — video, image, avatar and editing. Buy a pack, then spend credits at the per-model rates below.
$60
8,000 credits
$0.0075 / credit
Buy credits →$500
83,000 credits
$0.006 / credit
Buy credits →$1,000
222,000 credits
$0.0045 / credit
Buy credits →Credit packs are purchased on the DreamAPI pricing page.
Pricing
Clear, fixed billing.
One flat credit cost for each image edit request — no surprises.
DreamImage 2.0 — per request
ModelBilling modeCredits
dreamimage_2.0Per request10
Fixed billing at 10 DreamAPI credits per request. No card required to review the docs.
FAQBefore your
Before your
first edit.
What is DreamImage 2?+
DreamImage 2 is DreamAPI's natural-language image editing API. It takes an input image and an edit prompt, then generates a modified image while preserving the original structure and content.
What kinds of image edits can it handle?+
Use it to change materials, visual styles, or backgrounds; remove people and unwanted objects; and replace a specific object described in the prompt.
Which input image formats are supported?+
The API accepts a publicly accessible image URL in JPG, JPEG, PNG, or WEBP format.
How does the API return an edited image?+
The submit request returns a taskId. Use that ID with DreamAPI's Polling API, or configure a Callback URL to receive the result automatically.
How much does a DreamImage 2 request cost?+
DreamAPI lists fixed billing of 10 credits per request.
Where can I test the API?+
Open the DreamImage 2 documentation to review the API reference, launch the Playground, and see current billing details.
Editing images
in plain text.
Change a background, remove an object, or replace a subject — one image and one prompt.