How do I turn an image into a video with AI?
Upload the image, describe what should move, and generate. Bonega accepts JPEG, PNG, WebP, HEIC, HEIF and GIF files up to 8 MB, animates the picture you gave it rather than inventing a new one, and bills the same 4.125 credits per second as text-to-video — 21 credits for a 5-second clip. Set the aspect ratio BEFORE you attach the image: the video is generated at whichever of 9:16 portrait or 16:9 landscape is selected in the form, and attaching an image freezes that choice rather than reading a ratio off the file. If you have no image, you can have one generated as the first frame for 5 credits.
Accepted files
- Images — JPEG, PNG, WebP, HEIC, HEIF and GIF, up to 8 MB.
- Videos, when you are extending existing footage — MP4, WebM, MOV, AVI and MKV, up to 64 MB.
- SVG is deliberately not accepted, on either route.
Writing the motion prompt
The image already fixes the subject, the colours and the composition, so the prompt is only about MOTION: what moves, in which direction, how the camera behaves. "Slow push in, steam rising from the cup, hand lifts it out of frame" gives the model something to execute. "Beautiful cinematic coffee" repeats what the picture already says and leaves the motion to chance.
Beyond one clip
A request longer than 15 seconds is generated as a chain: the first segment animates your image, and each later one animates the last frame of the previous segment, all merged into one MP4. So an image can be the starting point of a 1 minute sequence, not only of a single short clip.
Frequently Asked Questions
What image formats can I upload?
JPEG, PNG, WebP, HEIC, HEIF and GIF, up to 8 MB per file. SVG is not accepted.
Does image-to-video cost more than text-to-video?
No. Both are billed at 4.125 credits per second, rounded up. Only having the first frame GENERATED for you adds a cost, 5 credits.