Tool

Image to video

Start from a picture and describe only what moves. Image-to-video keeps the face, wardrobe and framing of your reference — a photo, a render from the image studio, or a saved Character — and animates it on the engine you choose. Seedance 2.5 adds an end frame, so a clip can travel from one exact image to another.

50 free credits · no card · adults only, by policy

Three ways in

  • Upload a reference photo in the composer — the first reference drives the motion.
  • Pick a Character from your cast: their reference photo becomes the source and the same face carries into the clip.
  • Press Animate on any image in your library: it opens the video studio with that render as the source.

Prompting for motion, not for the picture

The reference already says who and where. The prompt should say what happens: "she turns toward the window and the curtain lifts in the breeze", "slow push-in as steam rises off the cup". Describing the subject again fights the reference; describing the motion directs it.

Engines and controls

Every video engine on eroq accepts a start frame. Seedance 2.5 also accepts an end frame and interpolates the motion between the two; Seedance engines honor a seed for repeatable takes; Kling is the pick for faces, Hailuo for dramatic light, Motion One for mature scenes. Native aspect ratios apply on the next-gen engines.

Starting points

Every tile opens the studio with the prompt already written.

Frequently asked questions

Can I animate a photo of myself?

You can animate photos of adult, fictional characters and original creations. Real, identifiable people without consent — including deepfakes — are banned by the acceptable-use policy and enforced.

Which engines support image-to-video?

All of them: Motion One, Seedance 2.5, Seedance 1.0 Pro and Lite, Kling 2.5 Turbo, Hailuo 02 and Veo 3 Fast. Seedance 2.5 additionally takes an end frame.

How do I keep the same character across clips?

Save them as a Character with reference photos and @mention them in each scene — Film mode can cast a character per scene.

Does image-to-video cost more than text-to-video?

No — the same per-clip price for the engine and length.

Keep exploring