Skip to content
Ardscale

AI image to video generator

Upload a photo and get a clip of up to 30 seconds that starts on it. Choose from 17 models, all on one account.

What you bring and what you get

You bring

  • One image

    The first frame of the clip. On most models it also sets the clip’s shape.

  • A prompt

    What moves and what the camera does. Optional on some models.

You get

A video clip

Longest clip
30 sec
Top resolution
4K
Aspect ratios
9
17 models in the table

How it works

  1. Pick a model

    17 models run image to video here. The table below compares their limits and prices.

  2. Add your photo

    Upload the image the clip starts from and say what should move. Some models need no prompt at all.

  3. Get your clip

    You see the price before you run it, and a generation that fails costs nothing.

AI models for image to video

Ardscale runs image to video on 17 models, made by Alibaba, Kuaishou, MiniMax, ByteDance, Google, and ShengShu.

Models that run image to video, compared
ModelMakerLengthTop resolutionAspect ratiosPrice
HappyHorse 1.1Alibaba3–15 sec1080p16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, 21:9From 19 credits per second
Kling 2.6Kuaishou5–10 sec1080p16:9, 9:16, 1:1From 7 credits per second
Kling 3.0Kuaishou3–15 sec4K16:9, 9:16, 1:1From 8 credits per second
Kling 4.0 FlashKuaishou3–20 sec720p16:9, 9:16, 1:1, 21:9From 12 credits per second
Kling 4.0Kuaishou3–30 sec1080p16:9, 9:16, 1:1, 21:9From 11 credits per second
MiniMax H3 MaxMiniMax5–15 sec768p21:9, 16:9, 4:3, 1:1, 3:4, 9:16From 8 credits per second
MiniMax H3MiniMax4–15 sec2K21:9, 16:9, 4:3, 1:1, 3:4, 9:16From 11 credits per second
Seedance 2.0ByteDance4–15 sec4K16:9, 4:3, 1:1, 3:4, 9:16, 21:9From 10 credits per second
Seedance 2.5ByteDance4–30 sec1080p16:9, 4:3, 1:1, 3:4, 9:16, 21:9From 12 credits per second
Veo 3.1 FastGoogle4–8 sec4K16:9, 9:16From 10 credits per second
Veo 3.1Google4–8 sec4K16:9, 9:16From 36 credits per second
Vidu Q3 ProShengShu1–16 sec1080p16:9, 9:16, 4:3, 3:4, 1:1From 8 credits per second
Vidu Q3 TurboShengShu1–16 sec1080p16:9, 9:16, 4:3, 3:4, 1:1From 5 credits per second
Vidu Q4 PreviewShengShu3–16 sec4K16:9, 9:16, 4:3, 3:4, 1:1From 7 credits per second
Wan 2.6 FlashAlibaba2–15 sec1080p16:9, 9:16, 1:1, 4:3, 3:4From 5 credits per second
Wan 3.0 PrimeAlibaba2–30 sec1080p21:9, 16:9, 4:3, 1:1, 3:4, 9:16From 11 credits per second
Wan 3.0Alibaba2–30 sec1080p21:9, 16:9, 4:3, 1:1, 3:4, 9:16From 7 credits per second

Length, resolution and aspect ratios show each model’s full range. One mode can narrow it, and a clip that starts from your image usually takes the image’s shape.

Questions and answers

Which AI models run image to video on Ardscale?

Ardscale runs image to video on 17 models: HappyHorse 1.1, Kling 2.6, Kling 3.0, Kling 4.0 Flash, Kling 4.0, MiniMax H3 Max, MiniMax H3, Seedance 2.0, Seedance 2.5, Veo 3.1 Fast, Veo 3.1, Vidu Q3 Pro, Vidu Q3 Turbo, Vidu Q4 Preview, Wan 2.6 Flash, Wan 3.0 Prime, and Wan 3.0.

How long can the clips be, and at what resolution?

Clips run up to 30 seconds, on Kling 4.0, Seedance 2.5, Wan 3.0 Prime, and Wan 3.0. The sharpest output is 4K, from Kling 3.0, Seedance 2.0, Veo 3.1 Fast, Veo 3.1, and Vidu Q4 Preview.

How much does image to video cost?

On Ardscale, image to video starts at 5 credits per second, on Vidu Q3 Turbo and Wan 2.6 Flash. Every model has its own price and you see it before you generate. A generation that fails costs nothing.

What is the difference between image to video and first and last frame to video?

Image to video takes one picture, and the model decides where the shot ends. First and last frame takes two, so you set both ends of the clip.

Make your first clip