Bad Times AI Video Generator

One photo. An over-the-top kitchen argument.

Loading…

What is the Bad Times AI trend?

The Bad Times AI trend turns a photo into an exaggerated argument with the camera, set to Bad Times by Imael Angel.

The performer holds their head, turns sideways with a hand on the hip, raises stop palms and moves toward the camera with emphatic hand gestures. The joke is the dramatic attitude, not a complicated dance routine.

View the human kitchen reference post

This template uses the opening of the human kitchen reference. It is separate from cat and dog versions, which have different anatomy and ending shots. The reference below is not our generated example.

The gestures in this clip

The 15-second option follows the opening excerpt. The 5-second option stops before the raised stop palms and closer reaction.

  1. Opening

    Hands on head

    The character holds their head, turns sideways and brings a hand to the hip and temple.

  2. Middle

    Talk to the hand

    Both palms rise in a stop gesture, then the performer turns back toward the camera.

  3. Closer reaction

    An emphatic finish

    The performer approaches with pointing and open-palm gestures. This is a 15-second excerpt, not the whole source video.

How to make a Bad Times video from your photo

No choreography to learn and no prompt to write.

  1. Upload your photo

    Use one clear photo of yourself or a consenting adult. Show at least the head to the knees; a full-body photo gives more information about clothing and proportions.

  2. Choose length and quality

    Choose 5 or 15 seconds and 480P or 720P. Check the credit total shown on the generation button before submitting.

  3. Generate, preview and download

    Follow the task in History. Watch the complete result, including the expressions and hands, before downloading or sharing.

Give the performance a clear starting photo

A close-up selfie leaves the model to invent the body and outfit. A sharp standing photo provides more detail.

Clear, evenly lit face with visible facial details

Recommended

  • One clothed adult, facing forward or at a slight angle, with a clearly visible face.
  • Head-to-knees or full-body framing, with clothing and body proportions visible.
  • Even lighting and arms separated from the torso, without objects covering the hands.
A tightly cropped or obscured face with insufficient detail

Avoid

  • Group photos, overlapping people, or a second face in the background.
  • Blur, heavy filters, deep shadows, sunglasses or a covered face.
  • Tightly crossed arms, cropped limbs or a seated pose for this standing performance.

A focused setup for this performance

One character, one kitchen and the same recognizable gestures.

One photo, one role

Your photo guides the performer's face, hair, proportions and outfit. No cast selection or extra characters are needed.

No prompt to write

The reference supplies the acting, framing and timing. Keep the setup simple and choose your output settings.

Check expressions and hands

AI can change faces or fingers during fast gestures. Likeness and exact lip sync are not guaranteed.

Video length, quality and credits

Your selected settings determine the total shown on the generation button.

Choose your output

5- or 15-second opening excerpts, 480P or 720P, in vertical 9:16. The default is 15 seconds at 480P. Neither option is the full source video.

Review the live quote

Sign in to check your balance. A new generation is a separate paid attempt; changing the settings alone does not start one.

Watch an existing result before submitting another attempt. Higher resolution does not guarantee better identity or hand details.

Your character, the reference kitchen

This page replaces a character inside a fixed video. It does not animate the background from your photo.

This Bad Times template
Scene
The kitchen from the selected reference
Performance
The selected Bad Times excerpt
AI Motion Transfer
Scene
The scene from your uploaded image
Performance
A movement template or your own motion video

Try another routine, or supply a different video.

Bad Times video questions

What is the Bad Times AI video generator?

It makes a photo-based remake of the Bad Times kitchen argument associated with Imael Angel's song. Upload one adult's photo to replace the performer in a fixed reference excerpt. It is a performance template, not a song or lyrics generator.

How many photos do I need?

One photo of one consenting adult. Choose a sharp, unobstructed face with the body visible to at least the knees, preferably the full body. Group photos are not supported in this version.

Does it keep my photo's background?

No. This version keeps the selected reference kitchen, camera and timing. Your photo guides the character's appearance. For movement in your photo's own scene, use AI Motion Transfer instead.

How long is the video, and which quality can I choose?

Choose 5 or 15 seconds at 480P or 720P, in 9:16. Both start at the beginning of the selected reference; 15 seconds includes more of the gestures and closer reaction. These are excerpts, not the complete source video.

Can I upload my dog or cat?

Not for this version. It is configured for a single adult human. Upright pets need a separately tested routine and anatomy checks; a cat or dog result is not promised here.

Does the video include the Bad Times song?

This template preserves the selected reference excerpt's audio. Check the result before sharing. Using the generator does not grant unrestricted music rights for every platform or commercial use. The page is not affiliated with Imael Angel.

How many credits does it cost, and what if generation fails?

The generation button shows the current total for your selected length and quality. Confirmed technical failures return the task's credits under the site's existing process. If a request is delayed or its status is unclear, check History before starting another paid attempt. An imperfect but completed result is not the same as a technical failure.

Will my face and lip movements match exactly?

Exact likeness and word-for-word lip sync are not guaranteed. The reference guides the expressions and gestures, but fast hands near the face can distort details. Check the face, mouth, fingers and clothing throughout your result.

How are my uploaded photo and video stored or deleted?

The generator may save a short-lived draft in this browser and sends the photo to the video provider when you generate. Provider retention is governed by its policies; inputs are not added to our public template library. Results are private to your account by default and can be deleted from History. See the Privacy Policy or contact support for data-deletion requests.