Cookie Preferences
We use cookies to personalize content and analyze traffic. See our Cookie Policy.
No image yet. Submit the form to generate image.
Explore different use cases and parameter configurations
Transparent pricing with no hidden fees. Pay as you go.
| Rule & Modality | Channel | Credits | Price (USD) | Official / Reference Price | Daily Savings |
|---|---|---|---|---|---|
luma-modify imageLuma | Starter | 0.4per image | $0.002 | - | - |
Complete guide to using luma-photon
Integrate luma/photon-modify on ApiPass to edit and transform images with simple text instructions. Swap backgrounds, adjust visual elements, transform scenes, or redraw an image while preserving the main subject, then receive generated image URLs through an asynchronous API workflow.
Luma Photon Modify is an image-to-image editing model that uses natural language prompts to modify or redraw an input image. Developers can describe the change they want, such as replacing a background, changing an object color, correcting visible text, adding accessories, removing elements, or transforming a scene. ApiPass exposes Photon Modify through a ready-to-use REST API with asynchronous task creation, status polling, optional callbacks, and normalized CDN image URLs in resultJson.resultUrls.
Describe edits in plain English instead of building a manual editing pipeline. Photon Modify interprets prompts such as background changes, object adjustments, style transformations, and scene updates while using the supplied image as the visual source.
Provide a publicly accessible JPEG, PNG, or WebP image URL and a prompt describing what should be preserved, replaced, or redrawn. The model is suitable for quick image edits, creative modifications, and production workflows that need consistent source-image context.
Create a task with POST /api/v1/jobs/createTask, save the returned data.taskId, then poll GET /api/v1/jobs/recordInfo until the task state becomes success or fail. When successful, parse resultJson and read resultUrls to get the generated image URL.
Photon Modify is well suited for replacing image backgrounds while preserving the main subject. Use it to move a person, product, or object into a performance stage, studio setup, beach scene, cityscape, or other target environment.
Modify specific image elements through a prompt, such as changing a car color, adding sunglasses, updating clothing, or removing unwanted objects. Clear instructions help the model focus the edit while keeping the rest of the image coherent.
Transform source images into new creative looks, including anime-style redraws, color restoration, stylized portraits, or imaginative scene compositions. Add lighting, mood, and atmosphere details for more cohesive results.
Build tools that replace product backgrounds with clean studio scenes, lifestyle settings, seasonal campaigns, or marketplace-ready visuals while preserving the product as the central subject.
Create fast editing experiences for creators who need background swaps, outfit changes, accessory additions, color edits, and scene transformations without opening a traditional design tool.
Let users place subjects into imaginative or cinematic environments, adjust atmosphere and lighting, or convert ordinary photos into stylized outputs for campaigns, avatars, thumbnails, and visual storytelling.
Photon Modify runs through ApiPass as an asynchronous image editing workflow. The request body stays simple, and task status can be handled with polling or callbacks.
Send POST /api/v1/jobs/createTask with model fixed as luma/photon-modify, channel set to auto unless custom routing is needed, and input containing a required prompt plus an optional image URL. The API returns data.taskId for tracking.
Poll GET /api/v1/jobs/recordInfo with taskId until state is success or fail. You can also provide callBackUrl during task creation, and ApiPass will POST the completion payload using the same structure as the Query Task API response.
When state is success, data.resultJson is a JSON string containing resultUrls. Parse it to access the generated CDN image URL or URLs. ApiPass returns URL outputs; base64 output is not exposed for this model.
Photon Modify is listed at $0.015 per image. The current regular channel is configured at 7 credits per image, and no additional billing field is required in the request body.
The low per-image cost makes Photon Modify practical for rapid prompt iteration, background replacement tests, product photography variants, and batch-style editing workflows.
Use the optional channel parameter to select auto, starter, regular, or official routing. The default auto channel lets ApiPass allocate tasks across available providers based on pricing and stability metrics.
Write a clear edit instruction that states what should change and what should remain. Use a publicly accessible JPEG, PNG, or WebP image URL for input.image, and avoid local files, login-protected links, or expired temporary URLs.
Call POST https://api.apipass.dev/api/v1/jobs/createTask with your ApiPass API key. Set model to luma/photon-modify and place prompt and image inside the input object. Optionally include callBackUrl for completion notifications.
Save data.taskId from the create response and call GET /api/v1/jobs/recordInfo until state becomes success or fail. On success, parse resultJson and read resultUrls to retrieve the edited image.
All APIs require authentication via Bearer Token.
Authorization: Bearer
Submit a new Luma Photon Modify image-to-image editing task. The model modifies or redraws the input image according to the text prompt and returns generated image URLs asynchronously.
The API accepts a JSON payload with the following structure:
1{
2 "model": "luma/photon-modify",
3 "callBackUrl": "string (optional)",
4 "channel": "auto",
5 "input": {
6 "prompt": "string",
7 "image": "string (optional)"
8 }
9}modelRequiredstringThe model name to use for generation. This must be fixed as luma/photon-modify.
"luma/photon-modify"
callBackUrlOptionalstringCallback URL for task completion notifications. If omitted, no callback will be sent.
"https://your-domain.com/api/callback"
channelOptionalstringYou may specify the corresponding provider within APIPASS via the channel parameter; these providers handle the actual image and video generation tasks. APIPASS currently offers three provider options:
The default value for the channel parameter is auto. When enabled, APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics to balance minimal cost and reliable performance. Retain the default auto value unless you have custom routing requirements.
Available options:
auto
The input object contains the following parameters:
input.promptRequiredstringPositive text prompt describing the image edit or redraw instructions. This field cannot be empty.
Describe the desired modification clearly, including what should be preserved, replaced, or redrawn in the input image.
"Turn the reference image into a cinematic sunset scene."
input.imageOptionalstringInput image URL used as the editing source for Photon Modify. It is recommended to provide this field for image-to-image editing scenarios.
Use a publicly accessible image URL. Supported upstream-readable formats typically include JPEG, PNG, and WebP. Avoid local paths, login-protected URLs, and expired temporary URLs.
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
1curl --request POST \
2 --url "https://api.apipass.dev/api/v1/jobs/createTask" \
3 --header "Authorization: Bearer ${APIPASS_API_KEY}" \
4 --header "Content-Type: application/json" \
5 --data '{
6 "model": "luma/photon-modify",
7 "callBackUrl": "https://your-domain.com/api/callback",
8 "channel": "auto",
9 "input": {
10 "prompt": "Turn the reference image into a cinematic sunset scene.",
11 "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
12 }
13 }'1{
2 "code": 200,
3 "message": "success",
4 "data": {
5 "taskId": "task_12345678"
6 }
7}codeStatus code, 200 for success, others for failure.
messageResponse message. When the request fails, this contains the error description.
data.taskIdTask ID used to query task status and results with the Query Task API.
flux
flux
Generate photorealistic images with robust text
Starting from
0 credits
Nano Banana 2 Lite, aka Gemini 3.1 Flash-Lite Image, is a newly released image model from Google DeepMind built for fast 1K image generation, efficient creative iteration, prompt-based image editing, and responsive visual output in product-facing creative scenarios.
Starting from
0 credits
apipass
apipass
Integrate production-ready AI face swapping into your app with a single API call.
Starting from
0 credits
OpenAI
OpenAI
Generate intentionally designed visuals with less prompting using the latest OpenAI GPT Image 2 model.
Starting from
0 credits
Qwen
Qwen
Starting from
0 credits
Fast image generation model built on Gemini 3.1 Flash Image. Supports text-to-image, image editing, multi-image fusion with up to 14 reference images, Google Search grounding, and outputs up to 4K resolution.
Starting from
0 credits
apipass
apipass
Seamlessly remove watermarks, logos, and unwanted text from your images at scale with our powerful AI-driven API.
Starting from
0 credits
seedream
seedream
Starting from
0 credits
grok
grok
Grok Imagine is xAI’s AI video generation model for creating high-quality videos with realistic motion, native audio, and synchronized speech. Grok Imagine 1.5 introduces faster generation speeds, improved motion physics, and stronger visual consistency for modern AI video applications.
Starting from
0 credits
seedream
seedream
Starting from
0 credits
OpenAI
OpenAI
Bring your ideas to life with sharper, faster, more precise image generation using the GPT Image 2.5 API.
Starting from
0 credits
seedream
seedream
Starting from
0 credits
Nano Banana 2.1 is Google's latest Nano Banana image model for high-quality text-to-image generation and prompt-based image editing, with up to 10 reference images and 1K, 2K and 4K output.
Starting from
0 credits