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 |
|---|---|---|---|---|---|
test imageLuma | Official | 999per run | $4.541 | - | - |
Complete guide to using luma-photon
Integrate Photon Flash Modify on ApiPass to edit images at lightning speed. This image-to-image model applies natural-language instructions to an input image, making it ideal for text replacement, simple element changes, rapid fixes, and high-volume creative workflows with asynchronous REST API access.
Photon Flash Modify is a fast image modification model for prompt-driven edits. Provide a text instruction and, for image-to-image workflows, a publicly accessible image URL. The model can redraw or modify the image according to your prompt and returns generated image URL results asynchronously. It is optimized for fast iterations, simple text corrections, label updates, and lightweight visual changes where speed and cost efficiency matter.
Submit an input image and a natural-language prompt to modify or redraw the image. Photon Flash Modify is well suited for quick edits such as replacing text, changing visual details, updating labels, or applying simple style changes.
Use direct instructions such as replacing one word with another, fixing typos, updating a date, or changing a price tag. For best results, quote the original and replacement text clearly in the prompt.
Create a task with POST /api/v1/jobs/createTask, save the returned data.taskId, then poll GET /api/v1/jobs/recordInfo until the state becomes success or fail. On success, parse resultJson and read resultUrls for the generated image URL.
Photon Flash Modify prioritizes fast generation for rapid iteration. It is designed for lightweight prompt-driven modifications where developers need quick feedback loops and scalable editing throughput.
Describe the exact edit in plain English, such as changing hair color, adding sunglasses, replacing a background, or correcting visible text. The prompt field controls what should be preserved, replaced, modified, or redrawn.
The documented base price is $0.01 per image, and the current regular channel configuration is 6 credits per image. This makes the model practical for batch updates, e-commerce asset refreshes, and large-scale creative testing.
Build tools that fix typos, update words, replace dates, change brand copy, or revise labels directly inside images using a simple prompt-based workflow.
Quickly update product labels, price tags, promotional copy, packaging text, and simple product-scene details across large image catalogs.
Let users test many visual ideas quickly before committing to higher-fidelity production edits. Photon Flash Modify is ideal for quick fixes and concept exploration.
Create workflows for lightweight edits such as removing a small element, adding accessories, changing a background, or modifying a subject detail with a clear text instruction.
Photon Flash Modify is optimized for fast and affordable edits. Use it when you need quick prompt-driven modifications, especially text edits and simple element changes.
Choose Photon Flash Modify for the fastest iterations, text corrections, quick fixes, and high-volume image editing. It is best when the edit is specific and can be expressed clearly in a concise prompt.
For more complex scene changes, background swaps, or edits that require enhanced output quality, use a higher-quality modification workflow. Photon Flash Modify is focused on speed and affordability rather than the most complex reconstruction tasks.
The input.image parameter should be a publicly accessible JPEG, PNG, or WebP URL. Do not use local file paths, login-protected URLs, or expired temporary URLs, because the upstream image processor must be able to fetch the image.
The source documentation lists Photon Flash Modify pricing as $0.01 per image. Billing is per generated image.
The current ApiPass regular channel configuration is 6 credits per image. The final task charge shown in your account record is the source of truth for production billing.
Use the channel parameter to choose auto, starter, regular, or official routing. The default auto channel lets ApiPass route tasks across available providers based on pricing and stability.
Write a clear edit instruction, such as replacing one word with another, changing a background, or removing an element. If you provide an image, make sure it is a publicly accessible JPEG, PNG, or WebP URL.
Send a POST request to https://api.apipass.dev/api/v1/jobs/createTask with model set to luma/photon-flash-modify and your input.prompt and input.image values. The response returns data.taskId.
Call GET https://api.apipass.dev/api/v1/jobs/recordInfo?taskId=<APIPASS_TASK_ID> until state is success or fail. When the task succeeds, parse resultJson and read resultJson.resultUrls to get the generated image URL.
All APIs require authentication via Bearer Token.
Authorization: Bearer
Submit a new Luma Photon Flash Modify image-to-image task. The model modifies or redraws an input image according to a text prompt and asynchronously returns generated image URL(s).
The API accepts a JSON payload with the following structure:
1{
2 "model": "luma/photon-flash-modify",
3 "callBackUrl": "string (optional)",
4 "channel": "auto",
5 "input": {
6 "prompt": "string",
7 "image": "string (optional)"
8 }
9}modelRequiredstringThe model name. For this endpoint, use luma/photon-flash-modify.
"luma/photon-flash-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 desired image modification. This field cannot be empty.
Use the prompt to describe what should be preserved, replaced, modified, or redrawn in the input image.
"Turn the reference image into a cinematic sunset scene."
input.imageOptionalstringInput image URL to modify or redraw. It is optional at the API level, but recommended for image-to-image modification scenarios.
Use a publicly accessible JPEG, PNG, or WebP URL. Local file paths, login-protected URLs, and expired temporary URLs are not supported.
"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-flash-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, or an error description when the request fails.
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