Upload 2 photos
Upload 2 clear reference photos, one per role in the shown order.
Two pets make coffee and spill milk across the kitchen counter.
A preview of the source clip, not a generated result.
Character 1 · First role0:01
Character 2 · Second role0:01Frames captured from this reference video. These are not upload photos or a generated result.
Source publication date; views are a snapshot, not a promise of reach.
How it works
Upload 2 clear reference photos, one per role in the shown order.
Pick 720p or 1080p, review the credit cost, and start creating.
Confirm permission, create your video and download it from My videos when it is ready.
A preview of the source clip, not a generated result.
Character 1 · First role0:01
Character 2 · Second role0:01Frames captured from this reference video. These are not upload photos or a generated result.
The template
Coffee Making AI brings your photos into the scene shown in the reference. Two pets make coffee and spill milk across the kitchen counter.
Upload 2 separate photos, in this role order: First role and Second role. Your photos guide the cast; the reference guides the scene and timing.
Use separate photos for the performers and keep their role order consistent.
AI results can vary in appearance, movement and sound.
Credits & quality
Buy this template once at your chosen quality, or use subscription credits. Review the cost before creating; video length follows the template.
A lower-credit option for everyday sharing.
Per video generation · About 14 seconds · timing may vary.Sharper detail for posting and sharing.
Per video generation · About 14 seconds · timing may vary.Credits are returned when a task is confirmed failed or canceled. If a submission is still being confirmed, it stays in My videos so it is not submitted twice.
View credit plansFAQ
This template needs 2 separate photos. Upload them in this order: First role and Second role. Keep one subject per photo.
Upload 2 clear reference photos, one per role in the shown order. Use separate photos for the performers and keep their role order consistent.
The prepared reference is about 14 seconds long. Generation follows this scene; exact timing may vary. You do not need to select a duration.
Reference audio guides the performance. Sound is generated by the video model; an identical original soundtrack is not guaranteed.
One video costs $9.99 at 720p or $12.99 at 1080p. With a subscription, this template uses 550 credits at 720p or 850 at 1080p. The selected cost is shown before you submit.
Processing time varies with the AI provider and its queue, so we do not guarantee a fixed completion time. You can leave the page and check the same task in My videos. If its status is unconfirmed, check that task or contact support before submitting another paid request.
Credits are returned when a task is confirmed failed or canceled. If a submission is still being confirmed, it stays in My videos so it is not submitted twice.
Photos are sent to the selected AI provider to process your request. You can remove completed videos and their media references, export account records and request account deletion in Privacy & data. Provider cleanup is a separate tracked process, so removal from the app does not promise immediate deletion of third-party copies.
Bring your photos. Choose your quality. Make the scene yours.
Make my video