Generate videos

Create AI-generated videos from text prompts or images using models like Wan v2.2, Kling O3, and Runway Gen4.

You can create videos from text prompts or animate still images into video clips. The platform also offers tools to upscale, extend, translate, and add audio to videos.

Video tools

Tool	What it does	Cost
Create Video	Generate video from a text prompt	From 6 credits/sec
Animate Image	Turn a still image into a video	From 10 credits/sec
Upscale Video	Enhance video quality and resolution	3 credits/sec
Extend Video	Continue an existing video	10 credits/sec
Translate Video	Translate a speaker’s language	8 credits/sec
Add Audio	Synchronize audio to a video	1 credit/sec

Create a video from text

1. Open the tool

   Go to Tools and select Create Video.

2. Choose a model

   Pick a video model from the dropdown. See the comparison table below.

3. Write your prompt

   Describe the scene, action, and camera movement you want. Be specific about motion and transitions.

4. Generate

   Click Generate. Video generation takes longer than images — typically 30 seconds to a few minutes depending on the model.

Animate a still image

You can turn any image into a short video clip:

1. Open the tool

   Go to Tools and select Animate Image.

2. Upload your image

   Upload the image you want to animate, or use an image URL.

3. Describe the motion

   Write a prompt describing how you want the image to move — for example, “camera slowly zooms in, hair blowing in the wind”.

4. Generate

   Click Generate and wait for the video to process.

Choosing a video model

Model	Best for	Cost	Duration
Wan v2.2	General purpose, good quality	10 credits/sec	3-5 sec
Kling O3	High quality, detailed motion	44 credits/sec	5-10 sec
Runway Gen4	Cinematic, smooth motion	6 credits/sec	5-10 sec

Video generation takes longer than images. Most videos take 30 seconds to a few minutes to process. You can close the page and check your Library later — the video will be there when it is ready.

Tips for better videos

• Describe motion — Include camera movements like “panning left”, “zooming in”, or “tracking shot”.
• Keep it simple — AI video models work best with clear, focused scenes rather than complex multi-action sequences.
• Start with images — If you have a specific visual in mind, generate an image first, then animate it for more control.

Next steps

Generate audio

Add speech, music, or sound effects to your videos.

Generate images

Create images to use as video starting frames.