Image to video: bring a still image to life
Use a photo or an image you generated as the first frame, describe what should move, and the model animates it into a short clip.
Open the studioStarting from an image gives you far more control than text alone: the composition, the character and the colours are already set, and the model only has to add motion. Most video models in Visuatelier accept a start image, including Kling 4.0, the Seedance models, Veo 3.1 and Grok Imagine Video.
A common workflow is to generate a still with an image model, pick the best one, then send it to an image-to-video model with a short motion prompt.
How it works
- 1
Upload a start image or pick one from your media library.
- 2
Describe the motion: “the fox turns its head, snow falls softly, slow push-in”.
- 3
Choose model, length and resolution, then generate.
What you can make
Animate product shots
Add a slow rotation, steam, a splash or moving light.
Living portraits and characters
Subtle movement, hair in the wind, a turn of the head.
Illustrations in motion
Animate artwork you created with an image model.
Consistent series
Reuse one key visual across several clips.
Examples from our showcase
Showcase images were generated by Visuatelier. The prompt and the model used are shown under each one.
Fox in snow · Made with Seedance 1.0 LitePrompt: A red fox trotting through a snowy forest with snowflakes falling, soft morning light, nature documentary, slow camera follow
Latte pour · Made with Seedance 1.0 LitePrompt: Close-up of milk being poured into espresso forming latte art, steam, warm cafe light, slow motion
Anime breeze · Made with Seedance 1.0 LitePrompt: Anime style girl standing on a grassy hill as wind blows her hair and petals fly past, big clouds, vibrant colors, gentle camera push in
Models for this tool
- Kling 4.0 · from 36 credits
Kling 4.0 makes smooth, cinematic video from text or a starting image.
- Veo 3.1 Fast · from 19 credits
Google's Veo 3.1 Fast is the quicker, cheaper Veo, with optional generated sound.
- Veo 3.1 · from 37 credits
Google's Veo 3.1 gives the highest Veo quality, with optional generated sound.
- MiniMax Hailuo H3 · from 14 credits
MiniMax Hailuo H3 makes expressive video, from 480p up to 2K.
- Wan 3.0 · from 23 credits
Wan 3.0 is a capable video model with a low entry price.
- Seedance 2.5 · from 108 credits
ByteDance's Seedance 2.5 is the newest Seedance, with strong motion and prompt adherence.
- Seedance 2.5 Reference · from 108 credits
Seedance 2.5 Reference animates a clip guided by your uploaded image. Refer to it as @Image1 in the prompt.
- Seedance 2.0 · from 70 credits
Seedance 2.0 is ByteDance's cinematic video model, with native audio and multi-shot scenes.
- Seedance 2.0 Fast · from 56 credits
Seedance 2.0 Fast is the lower-cost tier of Seedance 2.0, up to 720p.
- Seedance 1.0 Lite · from 5 credits
Seedance 1.0 Lite is the light first-generation Seedance. The provider now routes it to Seedance 1.0 Pro Fast.
- Seedance 1.5 Pro · from 6 credits
ByteDance's Seedance 1.5 Pro makes clips up to 1080p, with optional native audio (dialogue, sound effects).
- Grok Imagine Video · from 20 credits
xAI's Grok Imagine Video makes short clips from text or an image, from 1 second.
Frequently asked questions
Which models support image to video?
Every video model that accepts a start image; they are listed below on this page.
Can I animate photos of real people?
Only with their consent and never to deceive. Sexual content is not allowed, and our safety checks can block requests that break the content rules.
Does an input image change the price?
For some models an input image adds a small flat fee. The studio always shows the final price before you generate.
Which formats can I upload?
Common image formats such as JPEG, PNG and WebP.