Does the hand always reach toward the camera itself?

Not always — in one of our two test runs, the hand grabbed at the subject's own collar instead of reaching toward the viewer. Both versions still end on the same lurching push-in to a close-up.

Is the push-in jarring?

It's sudden by design, a lurch rather than a slow push, so expect a quick, punchy move.

Can I use a different model, or make it longer?

Yes. Five seconds on MiniMax H3 is the default; before you generate you can set up to 15 seconds or 2K on H3, or switch to another model listed for this effect in Studio, such as Wan 3.0 for up to 30 seconds. The Generate button shows the updated price first. Our samples were made on MiniMax H3, so other models may interpret the prompt a little differently.

Will it change what's in my photo?

No. The effect only adds motion, light and atmosphere; everyone in the photo stays exactly as they appear in it. The default model doesn't filter photos. Some models you can switch to in Studio apply their own content filters and may turn a photo down.

Is my result private?

Yes. Your upload and the finished clip stay private to your account and never appear on a public page.

Each effect defaults to a five-second clip priced in US dollars on the Generate button. Before you run it, you can switch to a different model, adjust the length, or change the resolution in Studio, and the price on the Generate button updates to match. An ordinary failed or expired run normally releases the reserved amount. For a content refusal, follow the selected model’s billing policy.

Will this effect change how the person in my photo looks?

Your photo anchors the subject; the effect adds the motion and look described in its prompt. Check the face, hands and clothing in the result. If a gesture distorts them, try a clearer crop or a simpler movement.

Can I upload a photo of someone else?

Only one you have the right to use, and never to make intimate content of a real person without their documented consent. The content policy has the full rule.

Pull You In AI Video Effect

Styles

After Dark

Laser Room

Color Smoke

Silk Drop

Petal Storm

Slow Shutter

Candlelight

Behind the Hair

Call Me

Champagne Toast

Darkroom Red

Doorway Lean

Eyes on You

Join Me

Late-Night Dance

Club Strobe

Pull You In

Romance

Kiss

Camera moves

Tiny Planet

Transform

Molten Gold

Fashion

Mirror Glance

Atmosphere

Lace Shadows

Motion

Groove

Fun

Meltdown

Product

Ingredients Burst

Film looks

Film Burn

Video templates

The Glance Back

Candles Come Alive

Silk Drift

Neon After Hours

Sway Under the Lamp

Mirror Moment

Morning Light

Passing Headlights

Whisper Session

Slow Push-In

Half Orbit

Drone Rise

This effect writes the prompt for you. Add one image.

We never filter your prompt.

Back to the studio

Your subject reaches for the lens as if catching your collar, and the camera lurches in close on their smirking face.

MiniMax H3

Model: MiniMax H3
Length: 5 s
Resolution: 768p
Per run: $0.185
Type: After Dark
Also runs on: Seedance 2.0 Fast, Seedance 2.0, Wan 3.0, Vidu Q3 Turbo, Wan 2.6 Flash, Seedance 2.0 Mini

What this effect sends

This is the full prompt, word for word. Copy it, or open it in the generator and change anything you like.

The main subject reaches toward the camera as if catching the viewer by the collar and pulls the lens in close with a playful smirk; the camera lurches forward until their face fills the frame, then holds on their eyes. The person stays exactly as they appear in the photo.

Customize in the generator

Pictures that work best

A seated or standing photo with at least one hand and arm visible gives the reaching gesture room to work.
This effect's grab direction varied slightly between our two test runs — try more than one photo if the exact gesture matters to you.
Sharp, well-lit close or medium portraits give the cleanest result, since the camera ends on a very tight close-up.
A relaxed or neutral starting expression in your photo gives the smirk at the end more contrast to land against.

Models this effect runs on

The same prompt on different models. Pick by look and by price.

MiniMax H3$0.185 per run
5 s · 768p
Seedance 2.0 Fast$0.484 per run
5 s · 720p
Seedance 2.0$0.76 per run
5 s · 720p
Wan 3.0$0.45 per run
5 s · 720p
Vidu Q3 Turbo$0.33 per run
5 s · 720p
Wan 2.6 Flash$0.113 per run
5 s · 720p
Seedance 2.0 Mini$0.265 per run
5 s · 720p

How it works

01
Add one photo
Choose the photo to match the example: include both people for a shared gesture, and keep the face and any hands involved clearly visible. Upload your own photo or start with a Pull You In sample.
02
Check the price
Pull You In defaults to a 5-second clip for $0.185. Swap the model or change the length and resolution before you run — the price on the button updates to match, and that's the whole cost of the clip.
03
Generate
Your Pull You In clip renders in the background, lands in History and is never published.

Do the move yourself

Pull You In keeps one version of this shot. To give Pull You In your own motion or ending, write it yourself in Image to Video, starting from the prompt above.

Open Image to Video

What it does to your photo

Pull You In is as direct as it gets: your subject reaches toward the camera as if catching the viewer by the collar and pulls the lens in close with a playful smirk; the camera lurches forward until their face fills the frame, then holds on their eyes. It's built for a sudden, punchy moment rather than a slow build.

In our test runs on MiniMax H3, an East Asian woman in a leather jacket reached out, grabbed at the lens as if catching the viewer's collar, and the camera lurched in to a close-up of her smirking face by second three. A man in a white tee gripped his own collar and leaned into the lens until his grin filled the frame; in that run the grab landed on his own shirt rather than reaching toward the viewer, which is a variation worth knowing about before you run it.

The honest takeaway: the reaching gesture reads most reliably toward the viewer on some photos and toward the subject's own clothing on others, so it's worth trying more than one source photo if the exact direction of the grab matters to you.

It runs on MiniMax H3 for five seconds by default, and H3 itself goes up to 15 seconds and 2K if you want more. Studio also lets you move the same prompt to another model before you generate, such as Seedance 2.0 or Wan 3.0, and the price on the Generate button updates with every change. Our samples were all made on MiniMax H3, so other models will read the prompt in their own way.

It's a bold opener for a teaser clip, an attention-grabbing hook for a short-form post, or a punchy single beat inserted into a longer edit.

The prompt is public and editable. If you want the grab-toward-viewer direction to be clearer, open it in the generator and add detail describing exactly where the hand should reach.