CreateForge

Your photo, the ear-cup celebration

Enzo Fernandez Celebration AI Video Generator

Make an Enzo Fernandez celebration AI video from one portrait and an included motion reference. Create the hands-behind-the-ears gesture, puffed cheeks and black-and-white stadium slow motion with Seedance 2.0.

Create your version

Seedance 2.0

One consenting adult, face and ears visible; a waist-up photo also guides clothing.

JPEG · PNG · WebP · ≤25 MB

Motion reference

Sign in

About five seconds of reference motion guide an eight-second output; the quote includes the actual input duration.

Advanced prompt
Settings8s · 720P · 9:16
8s
Aspect Ratio9:16
Resolution

Add the required reference content before generating.

Silent third-party reference, about five seconds. Not a CreateForge output; generated videos will vary.

Prompts to try

One person, the ear-cup celebration

Photo plus the included silent motion reference. Edit the advanced prompt before generating; no song is included.

Image 1 identifies the single adult celebrating. Video 1 guides the celebration gestures, black-and-white slow motion, stadium setting and camera, not the reference character's face or costume. Replace only the foreground celebrant with the person from image 1, preserving their recognizable face, skin tone, age, hairstyle, build and own clothing. Do not turn them into a footballer or copy the reference character. In one eight-second vertical clip, establish the person beside a football pitch, then move closer as they cup both hands behind their ears with palms facing the crowd, puff their cheeks and lift their chin toward the stands. Keep the recognizable ear-cup pose visible before lowering the hands naturally. Follow the reference's motion without repeating or speeding up the five-second clip. Use a generic floodlit stadium and a subtle broadcast-style push-in, no real players or identifiable teammates. Keep one head, two arms and separate natural fingers; hands must not merge with ears, hair or face. Generate original crowd cheers and stadium ambience only, no song, lyrics or imitated commentary. No team crests, sponsor names, scoreboard, broadcast logo, captions or watermark. This is a fictional AI celebration, not real match footage.

  1. 01

    Add one clear portrait

    Choose yourself or a consenting adult, with the face, hair and ears unobstructed. One person and visible shoulders make the celebration role easier to follow.

  2. 02

    Review the motion and quote

    The included silent reference uploads with your photo after sign-in. Both must be ready. Review the server quote for the output settings and actual reference duration before generating.

  3. 03

    Inspect and save the clip

    Check the face, ear-cup pose, cheeks, hands and sound across the whole video. Preview or download the MP4 and find the saved result and actual credit use in Library.

What does Enzo Fernandez celebration AI recreate?

People searching for this effect want to put themselves into a recognizable celebration: hands cupped behind the ears, an expressive face and a slow-motion stadium close-up. It is often described as a Topo Gigio-style pose. This tool focuses on that sequence rather than a goal-scoring action, dance or static football portrait.

Your portrait identifies the celebrant while a short built-in video guides gestures and camera movement. Seedance 2.0 generates a new scene; it does not paste your face onto unchanged broadcast frames. Exact likeness, shot timing and hand placement are not guaranteed. CreateForge is not affiliated with Enzo Fernandez, any team or any tournament.

Prepare a photo that leaves room for the hands

Use a sharp front-facing or slightly turned portrait with even light. Keep ears, hair and the outline of the face visible; avoid headphones, a hood, sunglasses and hands already covering the head. A waist-up image gives the model clothing and shoulder detail as well as a face.

Upload only one person, using your own photo or an image you have permission to use. A small face in a group photo can make the model choose the wrong subject. The preset asks to retain age, skin tone and clothing, not to make the person look like a professional player.

Reference length, output length and sound

The included reference is approximately five seconds; the default generated output is eight seconds at 720P in a vertical frame. These are separate durations. The uploaded video is not stretched, repeated or labelled as an eight-second reference. The protected quote includes its measured input duration as well as the requested output.

The reference is silent and no separate audio reference is uploaded. With generated audio enabled, the prompt requests new crowd cheers and stadium ambience, without music, lyrics or copied commentary. Listen to the completed result before sharing; a successful task does not prove that its soundtrack or gestures meet your expectations.

Fix drifting faces or unnatural ear-cup gestures

If hands hide the face or merge with the ears, use a clearer photo and simplify the advanced prompt to one held ear-cup pose and a slow push-in. Avoid adding a ball, a costume change, several teammates and extra gestures at the same time. Check both hands and the face throughout the clip, not just the first frame.

If the output copies the reference character, keep the instruction that image 1 defines identity and clothing while video 1 guides motion only. You can edit the preset before another paid attempt; retries are not automatic or guaranteed to fix a creative issue. Share the result as an AI effect, not as evidence that someone attended a real match.

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. Add one portrait; this page includes the silent motion reference. Your photo and the reference must both finish uploading before a quote or generation can proceed.

No. The model creates a new fictional celebration guided by your photo and the reference motion. It does not guarantee unchanged broadcast frames, an exact face swap or official team footage.

No. The template submits no reference song. Generated audio requests original stadium ambience; add any licensed music separately in your publishing app.

A motion reference and a requested output need not have the same length. This template uses about five seconds of reference for an eight-second output. The server quotes the measured input and selected output settings, not a copied competitor price.

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.