Oct 13, 01:42:07 AM·Ready · Took 1 min 8 sec · −816 credits
@Mara on a rooftop at dusk, her coat caught in the wind, the city lighting up below. anamorphic, 35mm. push-in
Veo 3.1 Fast · 8s · 1080p · 16:9 · 2 takes
Extend Lead into
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 or a render from the image studio — and animates it on the engine you choose. The Seedance, Veo 3.1, Kling and Hailuo engines add an end frame, so a clip can travel from one exact image to another.
Video
Opens the studio with this filled in. Sign up when you generate: 40 free credits, no card.
Video · Create
Create Replace Effects Editor
Add character Add context elements First frame Last frame
@Mara on a rooftop at dusk, her coat caught in the wind, the city lighting up below. anamorphic, 35mm. push-in
Syntax4s6s8s2 takes
Generate 816Three ways in
- →Set the First frame in the composer: pick a picture from your Library or Storage, or paste or drop one. On the engines that take one, a Last frame ends the clip on another picture.
- →Add a Character with Add character: on the engines that read reference pictures their look sheet rides along, so the same face carries into the clip. Motion One does not take characters yet.
- →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. eroq Motion One, Seedance, Veo, Kling and Hailuo also accept an end frame and interpolate the motion between the two; Seedance, Veo, Runway Gen-4.5 and Wan 3.0 honor a seed for repeatable takes. Kling is the pick for faces, Hailuo 3 for physics, Motion One for uncensored, private renders. Each engine renders its own set of native aspect ratios.
Clap · AI agent
Or let Clap make the clips
Describe the result in Ask. Clap asks what it needs, picks the engines, writes the prompts and prices the plan. Once you approve, it renders everything into your library. Fully automated, and nothing runs before you say yes.
- 1Clap asks one question at a time and keeps the brief, the cast and the storyboard up to date.
- 2The plan lists every render and its price before anything runs.
- 3One click on Approve and everything renders. Failed takes refund themselves.
Ask · Clap
Three moody 5-second clips of Kai walking through neon rain, 16:9.
Clap · Thought for 6s
Three takes on the same move, each its own clip. Here is the plan.
Plan · 3 renders435 cr
Clip · Scene 1 · eroq Motion One · 5s · 16:9145 cr
Clip · Scene 2 · eroq Motion One · 5s · 16:9145 cr
Clip · Scene 3 · eroq Motion One · 5s · 16:9145 cr
Done · everything landed
Production
Saved to your library
Starting points
Pick one: it goes into the box at the top, ready to generate.
Frequently asked questions
Can I animate a photo of myself?
You can animate photos of 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?
Every engine: eroq Motion One, Motion Pro, Seedance, Veo, Kling, Hailuo, Runway Gen-4.5, Grok Imagine and Wan 3.0. eroq Motion One, Seedance, Veo, Kling and Hailuo additionally take an end frame.
How do I keep the same character across clips?
Save them as a Character and @mention them in each prompt: on the engines that read reference pictures their identity sheet rides along, so the face holds. In Cinema, each scene of a film has its own cast.
Does image-to-video cost more than text-to-video?
Only on Grok Imagine, which adds 5 credits per frame picture. Everywhere else the start image is free: the price is the engine's per-second rate at your resolution, or Motion One's 29 a second.
Keep exploring