Image to video AI: turn a photo into a moving clip
Image to video starts from a still photo and turns it into a short clip. You give the photo as the opening frame and describe in words how the scene should move.
In shuut this runs in the video tool, and every video model there accepts a photo as the first scene. Some models can also end on a second photo or pass through photos in between.
Models for this
| Model | Made by | Price | Lowest price | Length |
|---|---|---|---|---|
| Seedance 2.5 | ByteDance | 26 credits per second | 12 credits per second | 4–30 seconds |
| Veo 3.1 | 44 credits per second | 22 credits per second | 4 seconds, 6 seconds, & 8 seconds | |
| Kling 4.0 | Kuaishou | 18 credits per second | 18 credits per second | 3–30 seconds |
| Seedance 2.0 | ByteDance | 17 credits per second | 8 credits per second | 4–15 seconds |
| MiniMax H3 | MiniMax | 10 credits per second | 10 credits per second | 4–15 seconds |
| Wan 3.0 | Alibaba | 11 credits per second | 6 credits per second | 2–30 seconds |
| Grok Imagine Video 1.5 | xAI | 16 credits per second | 9 credits per second | 1–15 seconds |
| Omni 1.2 Flash | 8 credits per second | 3 credits per second | 3–15 seconds | |
| HappyHorse 1.1 | Alibaba | 16 credits per second | 8 credits per second | 3–15 seconds |
Prices are in credits (1 credit = US$0.01) and are deducted from your shuut balance per use. You see the exact price before each generation.
Image to video in shuut's video tool
Open the video tool and add your photo as the first scene.
Write a prompt that describes the motion, such as a slow turn of the head or waves rolling in behind the subject.
Choose the model, the length, the resolution and the aspect ratio.
With models that accept an end scene, add a second photo so the clip moves from one picture to the other.
Press “Generate” to make the clip.
Which models do image to video in shuut
Every video model in shuut takes a first scene, so any of them can animate a single photo.
Seedance, Veo 3.1, Kling 4.0, MiniMax H3, Wan 3.0, Grok Imagine Video 1.5 and Omni 1.2 Flash also take an end scene.
Kling 4.0 and Grok Imagine Video 1.5 go further and take middle scenes, so the clip can pass through several photos in order.
Seedance 2.5 from ByteDance makes long single clips, speaks lines you put in quotation marks, Korean included, and lets you turn sound on or off.
Seedance 2.5 Flash is faster and cheaper, at 480p and 720p with fewer references.
Kling 4.0 from Kuaishou is known for natural acting, and its sound is always made together with the video.
Kling 4.0 Flash is faster and more affordable at 720p, with shorter clips and a first scene only.
Veo 3.1 is Google's model for short clips with dialogue, sound effects and ambient sound, and its sound is optional.
Veo 3.1 Lite is the most affordable Veo and takes a first scene only.
Before you start an image to video clip
A sharp photo with a clear subject gives the model a cleaner first frame to work from.
Describe one main motion per prompt so the movement stays readable.
When you use an end scene, pick two photos with a similar setting so the change between them looks natural.
For dialogue, put the spoken line in quotation marks on models that support it, such as Seedance 2.5 or Kling 4.0.
Voices in reference video or sound for Seedance need the speaker's consent.
If real people appear in the clip, check whether the place you post it needs an AI-generated label.
How to make an image to video clip in shuut
- Open the video tool in shuut.
- Add your photo as the first scene, and an end scene or middle scenes if the model takes them.
- Describe the motion in the prompt.
- Choose the model, length, resolution and aspect ratio.
- Press “Generate” to get your clip.
Frequently asked questions
- Which model suits my image to video clip?
- For a single photo, any video model in shuut works. To end on a second photo, use Seedance, Veo 3.1, Kling 4.0, MiniMax H3, Wan 3.0, Grok Imagine Video 1.5 or Omni 1.2 Flash. To pass through several photos, use Kling 4.0 or Grok Imagine Video 1.5. For spoken lines, Seedance 2.5 and Kling 4.0 speak text in quotation marks, Korean included.
- How long can an image to video clip run?
- Seedance 2.5, Kling 4.0 and Wan 3.0 make the longest single clips in shuut. Seedance 2.5 Flash also reaches that long length, Kling 4.0 Flash runs shorter, and Veo 3.1 makes short clips. The exact lengths for each model sit in the “Length” column of the model table.
- How much does image to video cost in shuut?
- The price depends on the model, length and resolution you choose, and on some models such as Veo 3.1 it also changes with sound on or off. The exact quote shows before you press “Generate”.
- Can the clip move from one photo to another?
- Yes, with models that take an end scene. Add your starting photo as the first scene and the closing photo as the end scene, and the clip moves between them.
- Does image to video come with sound?
- On some models. Kling 4.0 always makes sound with the video. Seedance 2.5 and Veo 3.1 let you turn sound on or off, and Veo 3.1 can add dialogue, sound effects and ambient sound.
What you can make
- Text to video: write a scene, get a video clip
- AI shorts maker: vertical clips, captions and resizing in shuut
- AI video upscaler: enlarge clips and photos to 4K
- AI lip sync video with Kling Lip Sync
- AI talking avatar video from a photo and a voice
- AI UGC video from a presenter photo, a product photo and a script
Updated November 17, 2026
Before you start
You pay per result, with a quote before you press “Generate”; subscriptions are optional.
Motion shots, captions and resizing are free once you sign up.
Section 9 of the Terms covers commercial use; scope varies by model and agreement, and checking rights, ad rules and AI labels is up to you.
shuut isn't affiliated with the model makers.