gpt-image-2:reverse is a publicly callable variant of GPT Image 2, designed for text-to-image generation and visual re-creation based on reference images. It is suitable for organizing titles, subjects, color schemes, and composition requirements into posters, infographics, product concepts, or character design images, and can also describe desired modifications around existing assets. On this platform, you can create through both generation and editing entry points, obtaining image files or asynchronous task results.
Submit requests to the public API at api.acedata.cloud using the documented parameters, then use the results in your application.
api.acedata.cloudgpt-image-2:reverseInput parameters and result formats vary by service. Use the public API for this model and follow its guide for generation, task retrieval and editing operations.
Understand GPT Image 2's image creation positioning separately from this entry point's calling specifications: the quantities, dimensions, and response formats above apply to requests on this platform.
GPT Image 2 is suited to visual creation that includes titles, labels, and explanatory text. Prompts can specify text content, subject placement, backgrounds, and information hierarchy at the same time, making text part of the overall composition. Posters and infographics are tasks worth trying first; after generation, spelling, numbers, and reading order should still be checked word by word.
When editing, submit the original image together with modification instructions, clearly stating which elements to retain and which parts to change. For example, retain the product outline, viewpoint, and lighting, and adjust only the color or setting. Multiple reference images can respectively serve as references for the subject, style, and composition, but their purposes should be specified to avoid conflicting requirements from different materials.
Both generation and editing can deliver image results that are convenient for subsequent processing. When comparing options, you can request multiple candidates; when embedding in an application, you can choose image links or Base64 data. Longer tasks can use callbacks to receive final results, separating creation submission, waiting for completion, and image saving into clear processing steps.
Enter the event name, main title, brief description, brand color scheme, and aspect ratio requirements to create promotional posters or knowledge cards. When there is a lot of information, first define the title area, main subject area, and annotation area to avoid cramming all content into the same hierarchy. After delivery, focus on checking the text and facts in the image, then refine the layout before formal publication.
Use product photos as editing input, describe the desired background, material atmosphere, and display method, and generate key visuals, lifestyle images, or packaging mockups. Clearly state in the instructions which shapes and marks must be preserved to facilitate comparison of different creative options. The results are suitable for concept exploration; formal product displays still require verification of colors, structure, and brand details.
Enter a character description or reference image, and request the organization of expressions, clothing, equipment, and different viewpoints in the image to create character design sheets. You can also generate static images for early storyboard development around scene descriptions. Using the same set of appearance descriptions helps reduce deviations, but character consistency across consecutive images still needs to be checked and adjusted one by one.
When a task includes both titles and layout, and also requires adjusting visual content around existing images, you can try GPT Image 2 first. Use real copy and reference assets to validate the generated image before deciding whether to incorporate it into the production workflow. gpt-image-2:reverse and :official are publicly callable variants of the same base model and should not be understood as image models from different generations.
If the work focuses on quickly generating candidates, you can further compare GPT Image 2.5 Flare; if high fidelity and fine-grained control are more important, you can compare Sunburst. Existing GPT Image 1.5 workflows are suitable for parallel testing with the same prompts and assets to see whether text, subject preservation, and composition better meet the goal, rather than replacing solely based on version numbers.
Provide a prompt when generating; provide both image and editing instructions when editing. Clearly specify the original text, subject retention requirements, and target aspect ratio.
Call the image generation or image editing endpoint and explicitly specify model=gpt-image-2:reverse; use auto or WIDTHxHEIGHT for size, and generate one image before evaluating. Configure masks, quality, and file format according to this endpoint's guide.
Read the URL or Base64 image according to the response format, save task_id asynchronously before querying results; check text, reference details, and the alpha channel, and record usage according to the current Pricing rules.
Preserve the main subject, title position, and composition of the original image; change the background from red to dark blue, while making highlights and shadows match the new color scheme.
Use image and prompt for JSON image editing, and specify the complete model ID; do not apply another endpoint's multipart mask workflow to this variant.
No. It is a public invocation ID variant of GPT Image 2, and its core purpose remains image generation and editing. Specify the full ID when calling it to explicitly select this endpoint; do not interpret the :reverse suffix as a new-generation model, nor infer that there are image-quality tier differences from other variants.
Use /openai/images/edits, submit image and prompt, and explicitly set model to gpt-image-2:reverse. Images can be provided via URL or uploaded as local files. It is best to clearly separate what to preserve from what to modify in the instructions, for example, preserve the product and viewpoint while only changing the background, then check the subject details after completion.
The editing endpoint can accept up to 16 reference images. JSON requests use an array of URLs, while local files use multipart. It is recommended to explain the role of each image: which provides the subject, which provides the style, and which provides the layout. Multi-image input does not mean that different people, products, or compositions will automatically be accurately merged.
Use size=auto when you want the model to determine the aspect ratio based on the creative intent; specify WIDTHxHEIGHT when fixed pixels are needed, while meeting the size constraints. Results can be returned as URL or b64_json; use URL when comparing multiple options at once, as Base64 responses support only a single image, and check the actual dimensions after downloading.
This endpoint directly processes image generation or editing requests and returns image results. It should not be considered equivalent to the complete ChatGPT experience, which includes reasoning, search, or multi-step orchestration. For iterative revisions, have the application save the previous image and submit another edit; longer tasks can receive completion results through callback_url.
Choose a development approach or application suited to this model and follow its setup guide.
↗Python SDK Integration Guide
SDK installation, authentication and examples↗TypeScript SDK Integration Guide
SDK installation, authentication and examples
↗↗Pricing
$0.0105· per generation
You pay$13,584for 142,800 credits · $0.0951 / credits46% OFF
You're billed in credits. Pick a top-up tier to see its per-credit rate — the larger the top-up, the cheaper each credit.
This is only a basic call example. See the full docs for more parameters and advanced usage.
View Docs