CreateForge

The perfect edit, then the real photo

Perdon Trend AI Photo Carousel

Make a four-slide Perdón photo carousel from one everyday portrait or pet photo. Three ordered GPT Image 2 edits lead back to your original, with editable captions and local PNG or ZIP export.

Make your four-slide carousel

GPT Image 2

One clear photo of one consenting adult, including the everyday setting.

JPEG · PNG · WebP · ≤25 MB

2K · 9:16 · 1080 × 1920 PNG

Three editing prompts

Three separate image generations. The original slide, captions and export cost no generation credits.

01 · Perfect version—
02 · Restore the background—
03 · Restore the outfit—

Estimated total—

Balance —

Caption language
25/120
29/120
26/120
7/120

Your carousel

01 · 1

Waiting for this edit

02 · 2

Waiting for this edit

03 · 3

Waiting for this edit

04 · Original photo

Waiting for this edit

AI images are saved individually in Library. Download the captioned carousel here; the original and ZIP are not permanently saved.

  1. 01

    Choose the everyday photo

    Use one adult or one pet. The unedited original becomes the final slide.

  2. 02

    Review three edits and quotes

    The background, outfit and grooming are progressively taken back. Each image is generated separately from the same original.

  3. 03

    Write captions and export

    Edit Spanish or English captions without regenerating. Download four numbered PNGs together as a ZIP.

What does Perdón mean in this trend?

Perdón means sorry. The joke begins with a picture that is too perfect, takes the edits back slide by slide, and ends on the real photo. It is a photo carousel, not a generic apology video.

Four ordered slides, three paid edits

The first edit upgrades the place, outfit and grooming. The second restores the place. The third restores the outfit too. Your untouched source photo is last. Each edit uses the same original, not three random outputs from one prompt.

Captions and downloads stay in your browser

Spanish is the default caption language, with English available separately from the website language. Change up to 120 characters per slide. Captions are drawn after generation, so spelling changes do not spend credits. Export uses a 1080×1920 canvas with the complete image fitted inside.

Partial results and temporary originals

Three protected quotes show the estimated total before starting. Tasks run one at a time. A price rise, missing reference or failure pauses the remaining work. Completed AI images stay in Library. The original and captioned ZIP are not permanently stored; after a refresh, select the same original to export or continue.

Credits and saved results

Sign in to upload references and review the current credit quote. Editing a prompt or changing a photo or setting clears the old quote. Generation starts only when you submit; opening this page or choosing a prompt does not spend generation credits.

Review the finished media before sharing. Successful results appear in Library with actual credit use. Result file URLs are public; browsing Library and task history still requires an account. References use temporary uploads, so a page refresh requires selecting photos again.

Common questions

No. There are three separately quoted image tasks. The fourth picture is your original; captions and export require no generation.

This version exports four numbered PNG slides or their ZIP. Add a sound and post the photos in order on your publishing platform.

Completed results are kept. Review fresh quotes and explicitly continue or retry the failed edit. Unknown submissions are never automatically retried.

Yes. The server quotes the selected model, settings and references before submission. This page does not promise a free generation or copy another website's credit prices.

References guide appearance, but likeness, hands and motion can vary. Use a clear photo and inspect the result. A completed task is not a guarantee that every creative detail is correct.