
AI first and last frame to video generator
Pick the frame a shot starts on and the frame it ends on, and get the clip between them. Choose from 13 models, all on one account.
You bring
Two images
The first frame and the last, in that order.
A prompt
What happens between the two. Optional on some models.

Pick a model
13 models run first and last frame to video here. The table below compares their limits and prices.

Add both frames
Upload the first frame, then the last. A prompt can say what happens on the way.

Get your clip
You see the price before you run it, and a generation that fails costs nothing.
AI models for first and last frame to video
Ardscale runs first and last frame to video on 13 models, made by Kuaishou, MiniMax, ByteDance, Google, ShengShu, and Alibaba.

Kling 2.6· Video
Videos up to 10 seconds, up to 1080p

Kling 3.0· Video
Videos up to 15 seconds, up to 4K

Kling 4.0· Video
Videos up to 30 seconds, up to 1080p

MiniMax H3 Max· Video
Videos up to 15 seconds, up to 768p
| Model | Maker | Length | Top resolution | Aspect ratios | Price |
|---|---|---|---|---|---|
| Kling 2.6 | Kuaishou | 5–10 sec | 1080p | 16:9, 9:16, 1:1 | From 7 credits per second |
| Kling 3.0 | Kuaishou | 3–15 sec | 4K | 16:9, 9:16, 1:1 | From 8 credits per second |
| Kling 4.0 | Kuaishou | 3–30 sec | 1080p | 16:9, 9:16, 1:1, 21:9 | From 11 credits per second |
| MiniMax H3 Max | MiniMax | 5–15 sec | 768p | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | From 8 credits per second |
| MiniMax H3 | MiniMax | 4–15 sec | 2K | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | From 11 credits per second |
| Seedance 2.0 | ByteDance | 4–15 sec | 4K | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 | From 10 credits per second |
| Seedance 2.5 | ByteDance | 4–30 sec | 1080p | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 | From 12 credits per second |
| Veo 3.1 Fast | 4–8 sec | 4K | 16:9, 9:16 | From 10 credits per second | |
| Veo 3.1 | 4–8 sec | 4K | 16:9, 9:16 | From 36 credits per second | |
| Vidu Q3 Pro | ShengShu | 1–16 sec | 1080p | 16:9, 9:16, 4:3, 3:4, 1:1 | From 8 credits per second |
| Vidu Q3 Turbo | ShengShu | 1–16 sec | 1080p | 16:9, 9:16, 4:3, 3:4, 1:1 | From 5 credits per second |
| Wan 3.0 Prime | Alibaba | 2–30 sec | 1080p | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | From 11 credits per second |
| Wan 3.0 | Alibaba | 2–30 sec | 1080p | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | From 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.
More video tools

Text to video
Write a scene and get the clip.

Image to video
Turn a photo into a moving shot.

Reference to video
Put your own characters, products or places in a clip.

Video to video
Change a clip you already have.

Motion control
Make your character copy the moves in a video.
Which AI models run first and last frame to video on Ardscale?
Ardscale runs first and last frame to video on 13 models: Kling 2.6, Kling 3.0, 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, 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, and Veo 3.1.
How much does first and last frame to video cost?
On Ardscale, first and last frame to video starts at 5 credits per second, on Vidu Q3 Turbo. Every model has its own price and you see it before you generate. A generation that fails costs nothing.
When should I use first and last frame instead of image to video?
Use first and last frame to video when the end of the shot matters, like a product landing in place or one scene turning into another. Image to video fixes only the start.