How to make the zombie trend with Dreamina (Seedance)
Make the AI zombie trend in Dreamina with Seedance: the two start frames, the 9:16 clip settings, the prompts to paste, what the free credits get you, and the hard cut in CapCut.
5 min read · Updated
What Dreamina gives you
Dreamina is CapCut’s AI creative app, and it runs ByteDance’s Seedance video models. According to Dreamina, Seedance 2.0 makes clips of 5, 10 or 15 seconds, in 9:16, with sound generated alongside, and Seedance 2.5 goes longer. That is long enough for the zombie trend, but the trend turns on a hard cut from a cold scene to a warm memory, and a model won’t reliably cut on the frame you want. So the dependable route is two clips, joined in CapCut. This page was checked against Dreamina’s own pages on 11 October 2026.
- Clip 1, the cold side, about 10 seconds: one person faces the other, who has turned, then lowers the weapon and holds them.
- Clip 2, the warm side, 5 seconds: the same two people, alive, in a happy memory.
- The cut: the last frame of the embrace, then straight into the memory.
Step 1: make two start frames
Make one cold still and one warm still from a clear photo of each person, in Dreamina’s image generator or any image tool that takes reference photos. Fixing the faces in stills before any video is what keeps the same two people on both sides of the cut. Dreamina asks you to upload only material you have the rights to and to respect other people’s likeness, so ask the other person first. The best photos guide covers which photos work.
Cold still
Using the two attached photos, make a vertical 9:16 film still. A snowed-in town at night, one streetlight still on, snow falling. The person from the first photo stands in a red scarf, arms half open. A few metres away stands the person from the second photo, turned into a zombie: pale grey skin, clouded white eyes, frost on torn clothes, calm and still. Keep both faces exactly as in the photos. Cinematic, cold blue light, shallow depth of field, PG-13, no blood, no text.
Warm still
Using the same two photos, make a vertical 9:16 film still of both people, alive and happy, running hand in hand through tall summer grass at golden hour, warm amber light, candid and close. Same faces and hair as the photos. Cinematic, 35mm film grain, no text.
Step 2: animate each still with Seedance
- In Dreamina, start a new video and choose a Seedance model.
- Choose the frame mode and put the cold still in the first-frame slot. Leave the last frame empty, so the model is free to move them into the embrace.
- Set 9:16 and 10 seconds, paste the cold prompt and generate.
- Do the same with the warm still and the warm prompt, at 5 seconds.
Cold clip
Slow push-in through falling snow. The turned person takes two slow steps forward. The survivor flinches, then recognises them and lets their arms open. They hold each other, the survivor’s eyes closed, snow settling on both. Cold blue light, the hum of the streetlight, wind and a low heartbeat. No dialogue, no blood.
Warm clip
Handheld, warm golden-hour light. The two of them run through tall grass, laughing, then stop and fall into a hug. Wind in the grass, birdsong, soft laughter. Natural, joyful, no dialogue.
Button names move between Dreamina versions, so look for the frame option rather than an exact label. Make two or three takes of each clip, keep the ones where the faces hold, and download them.
Step 3: join the clips in CapCut
- Put both clips in a 9:16 project, cold clip first.
- Trim the cold clip so it ends on the embrace. Keep at least four seconds of the memory.
- Leave no transition between them. One frame grey, the next frame gold.
- Add a short line over the embrace and a sound with the drop on the cut. The CapCut guide has the timing.
The one-step route
If you’d rather not make stills, run takes and edit, AI Zombie takes the same two photos and returns one 15-second video with sound and the cut already in place, with no watermark. You choose who turns and the setting. For other models, see the Kling and PixVerse guides.
Questions
Is there a zombie trend template in Dreamina?
Not a two-photo one, as of 11 October 2026. Dreamina’s own Zombie AI Video Trend page is a guide to text prompts for a single transformation scene, not a template you drop photos into. For the trend, you start from your own stills and make the clips yourself.
Can I make the zombie trend in Dreamina for free?
You can try it. Dreamina gives free daily credits, and your account shows how many. What a clip costs depends on the model, length and resolution, and removing the watermark is a paid feature, so free downloads carry it.
Will Dreamina use my two photos as the start and end of the video?
Only if you choose that mode. Dreamina’s help says reference images are not turned into first and last frames automatically. To fix where a clip starts or ends, pick the first-and-last-frame option and put the still in that slot.
