Friendship hugs
Animate two friends in one photograph with a gentle embrace and a steady camera.
Upload a photo of two people, or a portrait of each, to create a short hug video.
Follow us and get 20 free credits — about 1 video
Use photos of yourself or people who agreed to appear. Generated motion can change faces and hands.
Real CLI-generated output. The people in these examples are fictional.
Subscribe for more credits and more models.
Three real four-second outputs: two single-photo examples and one pair of separate portrait references.
Animate two friends in one photograph with a gentle embrace and a steady camera.
Bring two separate portraits into one short embrace, then review the faces and hands.
Give a clear family photograph a little movement for a personal message or memory.
Use one balance across image and video tools.
Explore other models and settings in the full Renoise workspace.
Restore a damaged photo before animating it with video tools.
Upload one photo containing both people, or a separate portrait of each person, and generate a short hugging video. The tool uses the visible faces and clothing as references while creating new motion between them. Leave the second slot empty when both people are already in the first picture. The default setting requests a four-second clip at 480p using Seedance 2.0 Mini. Watch the full result before downloading, especially the moment the arms meet: generated movement can introduce changes that are easy to miss in a still frame.
Working with a damaged family picture? Restore the photo first
Upload a clear two-person photo, or place one portrait in each upload slot.
Click Generate Hug Video after checking the model, duration, resolution, and live credit quote.
Watch both faces and the hands through the embrace, then download the video.
Choose based on whether you want invented motion or an accurate edit of a moment you recorded.
| Your decision | This AI hug generator | Edit recorded hugging footage |
|---|---|---|
| Source material | One or two still photographs | An existing video recording |
| Motion | Synthesizes a new embrace | Keeps the action you recorded |
| Appearance | Faces and hands may change | Original appearance stays in the footage |
| Direct control | Guide through reference selection | Trim, crop, and arrange exact frames |
| Best starting point | You have photos but no hug clip | You already captured the moment |
A hug brings faces, shoulders, arms, and clothing into overlapping positions. A tightly cropped face gives the model little evidence about the bodies it needs to move. Start with a clear half-body or wider photograph where both faces are visible, the arms are not hidden, and there is room between the people. A static camera and one gentle movement keep the request focused.
For two separate portraits, choose similar camera angles and roughly matching body scale. A distant full-body figure paired with a close-up face asks the model to invent much more of the scene. Place just one person in each slot; a group photograph can make the intended pair ambiguous. The couple example on this page uses two portrait references, while the friendship and family examples begin with a single two-person image. All example people are fictional, and all clips are actual model outputs.
Treat the result as an imagined animation, not proof that an event happened. Review both faces before, during, and after the embrace, then look for joined fingers, changing sleeves, or arms passing through bodies. If a result is awkward, a clearer source photograph and more space around the shoulders are useful changes for the next attempt. Only use real people’s photos when you have permission to animate them.
Picking a file only previews it on your device. Not one byte is stored until you sign in and click generate.
Uploads land in your private library, never a public gallery, and re-running the same photo stores nothing new.
Remove uploads and results from your library whenever you want.
One credit balance for image and video tools. Check the live quote before each generation.
For first-time AI content creators
Billed $168 annually
Upgrade PlanSave $72/year
For creators shipping content every week.
Billed $504 annually
Upgrade PlanSave $216/year
For studios and pros producing at commercial scale.
Billed $1680 annually
Upgrade PlanSave $720/year
For first-time AI content creators
Billed monthly
Upgrade PlanFor creators shipping content every week.
Billed monthly
Upgrade PlanFor studios and pros producing at commercial scale.
Billed monthly
Upgrade PlanRenews automatically each year until canceled.
Renews automatically each month until canceled.
Following Renoise on X and YouTube earns 10 credits each, up to 20 shared credits. An unused balance currently covers one default four-second 480p video. After those credits are used, further generation is paid. Check the live quote before starting.
Yes. Put one portrait in each upload slot. Similar framing, camera angles, and body scale give the model a clearer starting point. The output combines the references into a new scene, so facial details and backgrounds may change.
Yes. Upload it in the first slot and leave the second empty. Choose a photo with exactly the intended pair, visible faces, and space around their shoulders and arms. A crowded group photo makes the target people less clear.
Not perfectly in every generation. The photos guide the result, but turning heads and overlapping bodies can change identity details. Watch the whole clip before sharing. If likeness matters more than invented movement, use original recorded footage instead.
Overlapping arms and partly hidden hands are difficult to synthesize. Try a wider source photo with visible arms, fewer obstructions, and space between the people. Inspect the moment of contact; a convincing opening frame does not guarantee a clean embrace.
You can try a clear family photo when you have permission to use it. Repair significant damage and improve visibility before animation with Renoise’s photo restoration tool. Restoration and animation are separate tasks, and neither guarantees perfect likeness.
The default clip is four seconds. Use the tool’s available model and duration settings, or the full video workspace, to explore other lengths. Check the updated credit quote before generating; the free-credit example applies only to the default setting.
Compare support for your photo inputs, facial consistency during motion, hand quality, clear pricing, and downloadable output. Test a representative photo before choosing. This page shows actual generated examples so you can judge its style without relying on a ranking claim.
Start with clear faces and room for a gentle embrace.


