How to Make a Bad Times AI Dance Video from One Photo

What the Bad Times AI template does

Bad Times AI is a single-person dance template. One adult is placed into a home interior and follows the Bad Times move set: expressive hand gestures, body turns, bouncing and a playful lean toward the lens. The output is one continuous vertical 9:16 shot, 15 seconds long and silent. ZoopFizz runs the template on Wan 3.0 in reference mode: your photo supplies the identity, and a fixed reference video supplies the timing, gestures and camera framing. The displayed sample is a real ZoopFizz test generated from one user-provided photo and a fixed motion reference; the silent result is 480×854 pixels, 15 seconds and vertical.

Because the gesture sequence is fixed, the best results come from a clean, front-facing photo and from expectations that match what a single reference workflow can do. The template is built around confidence toward the camera, so a calm expression and visible hands in the source photo help the model keep the performance readable.

What you need before you start

You need one suitable adult photo, permission to use it, a ZoopFizz account that can run the template, and sound you are licensed to publish. The photo may be PNG, JPEG or WebP up to 10 MB. The request is 15 seconds at 9:16 and silent, at the SD (480p) or HD (720p) resolution you choose. A completed run consumes its credits; preparing a draft is free.

• One photo of one consenting adult; this template is for adults only.
• Face clear and toward the camera, with the half body the role needs.
• An account with credits, an eligible plan or a template-video pack.
• A licensed track to add after the silent clip downloads.

Choose the photo that carries the identity

The photo is the only identity input you control, so its quality decides how much of the person survives into the clip. Pick a sharp image with a clear face, visible eyes and the clothing you want the dancer to wear. A chest-up or half-body photo is enough; full body works if the hands are visible, because the routine depends on gestures and a close approach to the lens. Even light beats hard flash, and a simple background keeps attention on the dancer instead of inviting warped detail behind them.

• One adult only; another person in frame gives the model a second subject to track.
• Face unobstructed by hats, hands or deep shadow.
• Clothing that reads clearly at 480p, since fine patterns can shimmer.
• Hands visible in the source photo where possible.

The fixed reference and what you cannot change

Movement, gesture timing and camera framing come from a fixed Bad Times reference video selected by ZoopFizz. There is no text box to rewrite the routine, so the template is predictable rather than open-ended. The style is called You: your look, one confident solo with hand gestures, turns and a playful close-up at the camera. What you control is the photo, the SD or HD resolution and the price. Expect one continuous vertical shot of 15 seconds, not a multi-cut edit, and review the whole clip rather than a single poster frame.

Step 1 — add the photo and keep the draft local

Open the Bad Times AI page and fill the single role, Your photo (adults only), which replaces the only adult dancing toward the camera. Selecting a file creates a preview in this browser; nothing is uploaded until you submit. Compare the preview with the role hint, replace the file if the face is cropped or the light is flat, and confirm the permission statement including that no minors appear in the image. If you are signed out, the action reads Sign in to generate.

Step 2 — confirm settings, consent and price

Choose SD (480p) or HD (720p) and read the account price before you submit. The cost is 750 or 1,500 credits depending on resolution, with plan discounts for eligible accounts, or one template video credit when your plan includes 480p template videos. Template video packs cover 480p generation: $7.99 for one, $19.99 for three or $29.99 for five. When using credits, template pricing is 750 credits at 480p or 1,500 at 720p HD; Starter and Pro pay 375 or 750, and Unlimited pays 225 or 450. The page confirms your account price before submission. If the balance is short, the payment window opens without discarding the draft.

Step 3 — review the result honestly

Watch the clip start to finish. The routine pushes the person toward the lens, so the close-up is where identity drift, hand shape and body proportions are most visible. Check the face across the whole sequence, the number and shape of fingers, the clothing across turns, and the background behind the dancer. The prompt asks for a consistent face and coherent hands, but it cannot guarantee them. A confirmed failed or cancelled generation restores unexpired credits once, with the original expiry date; unknown outcomes are checked before any credits are returned. If one detail fails, rerun with a sharper photo and a simpler background rather than repeating an identical setup.

Step 4 — add sound and publish

The generated clip is silent. The generated clip is silent. Download it from your library, then add music or sound in your editing or publishing app using a track that is licensed for your account and intended use. The 9:16 frame is already vertical, so it fills a vertical feed without cropping. The displayed showcase copy carries an added audio track; that track is for the sample, not part of the generated output. Choose a sound whose hook lands early in the 15 seconds, keep the downloaded file as a backup, and check that the track is cleared for your account and publishing context.

Limits, privacy and common mistakes

No exact match to the reference is promised: face, clothing, hands and body proportions may drift, especially near the lens, and no completion time is guaranteed because queue and model availability depend on the supplier. The validated sample used one photo and a fixed motion reference; it is not a promise that every photo will keep identity intact. Photos stay local while you build the draft: selecting a file creates a preview in this browser, and continuing saves the draft locally. The image reaches the server and the generation provider only when you choose Create. Generated files are private to your account. Completed videos are stored for 30 days after saving with an email reminder three days before removal; uploads become eligible for deletion seven days after upload when no active video uses them.

• A child in the photo: this person template is for adults only.
• A cropped face or heavy shadow: identity retention drops quickly.
• A busy background: detail behind the dancer can warp during turns.
• Expecting a different routine: the choreography is fixed by the template.