VellmVellm guide
Which AI video template fits your photo?
By Vellm · Updated October 15, 2026
Choose a template by who is in your photo and which routine you want. Vellm’s current options cover cats, a dog and portraits. Each has its own upload requirements, length and credit cost.
| Template | Photos | Length | Credits |
|---|---|---|---|
| Bulin 47 Freestyle | 1 required | 10 seconds | 30 |
| Smalltown Boy | Cats: 1 required, 1 optional; People: 2 required | 21 seconds | 60 |
| Single Ladies Dog Dance | 1 required | 19 seconds | 60 |
| Burning Bridges | 1 required | 20 seconds | 60 |
| Zombie Couple | 2 required | 10 seconds | 30 |
| A2O LITE NEON Dance | 1 required | 23 seconds | 60 |
You have a cat photo
The Smalltown Boy template accepts one required cat photo and one optional photo. The first cat leads the opening close-up. The optional slot lets you choose the dance partner; leaving it empty creates a partner for you.
If you only know the clip as “the screaming cats,” the cat dance guide explains what to look for in the reference and how to assign the photos.
You have a dog photo
Single Ladies Dog puts your dog at the front of a trio with two fictional backup dancers. Use one clear dog photo with its body visible. You do not upload photos for the backup dancers.
A tight portrait of the dog’s face may miss the body information this setup asks for. Choose a frame with ears and paws visible.
You have photos of people
For two people, Smalltown Boy’s People mode uses separate photos for the opening lead and the dancer. Both people must agree to appear in the video.
For a single portrait, compare Bulin 47 Freestyle with Burning Bridges. One follows a freestyle performance, the other a party routine. Watch their references to choose the movement you want.
Bulin 47 uses vertical 9:16 framing; Burning Bridges uses landscape 16:9. Both offer a choice of settings. The portrait supplies the face and outfit. Avoid sunglasses or face coverings that hide details.
Match the frame to your post
The current cat and dog templates use vertical 9:16 framing. Bulin 47 also uses vertical 9:16, while Burning Bridges uses landscape 16:9. Check the template’s framing before generating.
Compare the amount you will pay
The table shows credits spent on generation. You buy those credits in a pack or receive them through an optional monthly plan. A larger pack may have a lower average per video but requires a larger upfront payment.
Read how credits and video costs work before choosing a pack. First-purchase offers depend on eligibility.
Know what the preview shows
Credited reference videos show the intended routine. They are labelled separately from product results. AI output varies, so check the face, body and movement across the complete generated clip.
The current templates export silent video. Add suitable audio when you post. The pricing page describes 1080p as enhanced export.