What you say to the agent
No special syntax — just describe it like you would to a person.
What it does, step by step
- 1
Attach your character/photo AND a reference video containing the motion you want copied (e.g. a dance clip).
- 2
The agent routes to a Kling Motion Control model, passing your photo as image_url and the reference clip as the motion source.
- 3
It generates a video of your photo's subject performing the reference video's motion.
What it needs from you
- •A text prompt describing what you want
- •Which AI model(s) to generate with (or let the agent pick)
What comes back
A video of your photo animated with the reference clip's motion.
What it costs
Priced per model, shown before you confirm — motion-control models are a premium tier.
Good to know
- Needs two inputs: your photo and a separate motion-reference video. This is distinct from the plain photo-to-video capability, which only needs one image.
Under the hood
This is what the agent actually calls when you ask for it — real tools from its live surface, not marketing copy.
generate_video_from_imageAnimate an image into a video. Use when the user has attached an image and wants to turn it into a video or animate it. Requires an attached image URL from [Attached image: URL] in the message (or a first_frame_url — see below).
The full tool behind it
See it done in a real workflow
Lunchwell — Hospital Visit Story
AI-animated emotional product ad — a Pixar-style wife packs her hospitalized husband's Lunchwell lunchbox with love across 18 cinematic shots: fresh bread, his favorite layers, halved fruit, a "Get well soon, love." note, then the drive to him and the quiet reveal as he tastes home. ~28s vertical reel.
TrendingMorning Matcha Routine
UGC-style wellness reel — a clean-girl creator walks through her actual morning matcha ritual, then cuts to a cozy animated hero shot of the finished iced latte.
TrendingNYC Street Interview
Photorealistic street-vlog interview — Riley works three different NYC corners at golden hour asking strangers one question: "What's the wildest thing you've ever done?" Three candid OTS/two-shot clips with locked character references, real handheld energy and native spoken dialogue. Vertical 9:16.
Or start from a one-tap template
Frequently asked questions
What do I actually say to the agent to transfer a dance or motion onto my photo?+
Just describe it in plain English — for example: "[Attach my photo and a dance video] Make me do this dance" The agent handles picking the right tool and model from there.
What does the agent need from me first?+
At minimum: A text prompt describing what you want; Which AI model(s) to generate with (or let the agent pick). Anything else it needs, it asks for before running.
What do I get back?+
A video of your photo animated with the reference clip's motion.
Does this cost credits?+
Priced per model, shown before you confirm — motion-control models are a premium tier.
Anything I should know before asking for this?+
Needs two inputs: your photo and a separate motion-reference video. This is distinct from the plain photo-to-video capability, which only needs one image.
You can also just ask for
Ask your Versely agent to transfer a dance or motion onto my photo
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.