Skip to workspace content
Back to Blog

Creation notes / Meme explained

Prepare photos for a Coffee Fail video

A preparation checklist for people, dog and cat candidates, with role order and full-sequence review.

The Virumi team3 min read
Prepare photos for a Coffee Fail video

Choose a people, dog or cat Coffee Fail scene, then choose whether to specify one or both identities. Virumi's current version produces a 15-second portrait video with the scene's soundtrack. Two-photo mode offers Balanced 480p and Premium 480p; one-photo mode is Premium 480p only.

Prepare photos in role order

Photo 1 identifies the coffee maker in the foreground on the right. In two-photo mode, photo 2 identifies the partner pouring behind on the left. Use two individual photos from the matching subject category. Keep faces unobstructed and enough body outline visible to judge posture; for pets, include ear shape, muzzle and recognizable coat patches. A group photograph can make identity assignment ambiguous.

One-photo mode creates an AI partner with a different appearance. It does not specify a second real identity. Use photos you are permitted to upload, and clear adult portraits for the people version.

Create the scene

  1. Open Coffee Fail and choose people, dogs or cats.
  2. Choose two-photo mode to specify both roles, or Premium one-photo mode for an AI partner.
  3. Upload the photo or photos in the labeled order.
  4. Check the 15-second portrait setting, available 480p version and current quote.
  5. Generate, review the full result and download the version with sound.

Check the price before confirming

Two-photo Balanced 480p costs 15 credits, or $7.99 for a one-off purchase without registration. Premium 480p in either input mode normally costs 30 credits, or 20 for an eligible account's first Premium full video. That offer is used once across the account. Premium one-off purchase is $9.99. Check the selected quote rather than estimating later videos using the one-time discount.

Review the whole ending

Follow the powder landing beside the cup, the exchange of glances and the later milk spill. Check both identities and the spoon/cup/liquid contacts. Our own samples capture the main joke, but paws can look finger-like, an extra spoon can appear and fine timing differs. A clear screenshot cannot establish motion continuity or audio delivery.

720p, 1080p and Standard one-photo combinations remain unavailable. For the scene's structure, read the Coffee Fail breakdown.