Warm moment effect
The Hug That Happens From Behind
One person in front, one behind, arms closing around. This effect animates that single moment from one two-person photo, and it needs no text prompt at all.
A hug from behind is a small, specific piece of body language. It reads as reassurance rather than greeting, which is why it works in quiet content where a front-facing embrace would feel too loud. The effect animates exactly that motion from a single photo.
The input is one photo with two people where one stands slightly in front of the other, and the output is a 4-second 720p clip for 40 credits. This template runs without a text prompt — there is nothing to type, so the photo is the only lever you have.
Specs at a glance
Straight from the product panel, not from a marketing deck.
- Output
- 4-second video
- Credits
- 40 per run
- Resolution
- 720p
- Aspect ratio
- Matches your input photo
- Input
- 1 photo — two people, one slightly in front of the other
- Best results with
- A frame where one person is clearly in front and the other clearly behind, both visible from the waist up
- Known limits
- With both people at the same depth the effect has to guess who stands behind, and arms can attach to the wrong body. This template runs without a text prompt, so there is nothing to type to correct it — the photo is the only input you control.
What it does
Built for this specific job, not a generic editor.
No prompt to write
The motion is fixed by the template. That removes the guesswork of describing a gesture in words and makes the effect predictable, at the cost of not being able to adjust the action afterwards.
Depth over pose
The effect works from the depth relationship in your photo: one figure in front, one behind. Getting that separation right in the source image is the single biggest factor in whether the hug reads cleanly.
Short and quiet
Four seconds keeps the moment from tipping into melodrama. It is long enough for the arms to close and short enough to loop in a story without feeling repetitive.
Small footprint on credits
At 40 credits per run, this is priced with the other effects that animate people already in the photo rather than generating a new figure.
How it works
Four steps, no timeline to learn.
Shoot or pick a photo with clear depth
One person should be visibly closer to the camera than the other. If both stand at exactly the same distance, the effect has to guess the order and the result becomes unreliable.
Keep both figures waist-up or more
The arms are doing the work, so the frame needs to include shoulders and elbows. A tight crop on faces alone leaves no room for the gesture to appear.
Run it and check the arms
Watch which body the arms attach to. Incorrect attachment is the most common visible artefact and it almost always traces back to two people at the same depth in the source photo.
Re-shoot rather than re-run
Because there is no prompt to adjust, a failed result is a framing problem. Taking a slightly better photo is more efficient than spending another 40 credits on the same input.
Where people use it
The jobs this effect actually gets used for.
Quiet anniversary posts
The gesture is affectionate without being performative, which suits couples who want to post something meaningful without a public display of romance.
Family photos that already exist
Many family photos naturally have one person slightly behind another. Those photos are ideal inputs, so the effect works on images people already have rather than requiring a new shoot.
Comfort and support themes
A hug from behind reads as steadiness. That makes it a good visual for posts about support, recovery or simply being there, without any caption spelling it out.
Pre-visualising a shoot
Photographers planning a couple session can test how a back hug frames up before asking two people to hold the position in real life.
Why there is no prompt box on this effect
A fixed action with no text input is more predictable, not less capable.
Prompt fields are useful when the outcome is open-ended. A hug from behind is not open-ended — it is one specific motion, and the template is already tuned for it. Adding a prompt would mostly add ways to get it wrong.
What replaces the prompt is framing guidance: clear depth between the two people, shoulders in frame, arms free of clutter. Those are things you can control before you spend credits.
The trade-off is honest and worth stating: if the source photo does not contain the depth relationship, no amount of re-running will fix it, and we would rather say that here than let you discover it at 40 credits a time.
Credits and plans
Every effect draws on one shared credit balance.
Forty credits per run. The free tier gives 30 credits each month without a card, and the paid plans start at $9 with credits, faster queues and parallel jobs. Costs are always shown before you confirm a run.
Related guides
Longer reads on the same workflow, from the OpenFilmo blog.
Image to Video AI: Animate Any Photo in Seconds
A complete guide to image to video AI: what makes a good source image, how to write motion prompts, top use cases, and how to fix …
Character Consistency in AI Video: What Actually Works
How to keep characters consistent across AI video shots: reference images, prompt discipline, key frame locking and post-hoc corre…
Best AI Video Generators 2026: 15 Tools Tested
We tested 15 AI video generators on the same prompts and ranked them for 2026. Compare quality, speed, credit pricing and commerci…
Related effects
Same family of effects, on the same kind of input.
Frequently asked questions
Can I describe the hug in a prompt?
No — this template runs without a text prompt. The action is fixed, and the photo is the only input you control. Effects with prompt fields are a separate set of templates.
What makes a good source photo?
Two people with a clear front-and-back relationship, framed from the waist up or wider, with the arms visible and free of props.
Why did the arms end up on the wrong body?
That happens when both people stand at the same depth in the photo, so the effect cannot tell who is behind. Re-shoot with visible separation rather than re-running the same image.
Does it work with a pet instead of a person?
No. The input rule for this template is two people. Pet-specific effects are listed separately in the template directory.
Is the clip suitable for paid advertising?
It can be used commercially on any plan, including free. Get permission from both people in the photo before publishing it in an ad.