Introduction

Gen-4 creates fast, controllable and flexible video generation that can seamlessly sit beside live action, animated and VFX content. Gen-4 creates videos in 5 or 10 second durations based on an input image and text prompt you provide.

The Turbo version of Gen-4 delivers further enhanced speeds at a lower cost, and is a powerful model for quickly iterating ideas.

This article outlines the steps to create videos with Gen-4, the available settings, and more.

Article highlights

• The Turbo model uses 5 credits per second of video
• The Gen-4 model uses 12 credits per second of video
• We recommend testing generations in Turbo, then switching to Gen-4 as needed
• You can generate infinite Gen-4 videos in Explore Mode on Unlimited plans
• Gen-4 requires an input image

Gen-4 Spec Details

	Gen-4	Gen-4 Turbo
Cost	12 credits per second	5 credits per second
Supported durations	5 seconds (60 total credits) 10 seconds (120 total credits)	5 seconds (25 total credits) 10 seconds (50 total credits)
Infinite generations in Explore Mode	Yes
Platform availability	Web
Base prompt inputs	Text, Image (required)
Text prompt character limit	1000 characters
Output resolutions	16:9 — 1280x720 px 9:16 — 720x1280 px 1:1 — 960x960 px 4:3 — 1104x832 px 3:4 — 832x1104 px 21:9 — 1584x672 px
Frame rate (FPS)	24fps

 

Step 1 — Drafting the Prompt

Begin by selecting Generate Video from the homepage of your dashboard.

Ensure that the Gen-4 or Gen-4 Turbo model is active in the model selector located in the bottom left-hand corner:

 

💡 Choosing between Gen-4 and Turbo:
Because of the reduced credit cost and faster generation times, we recommend first exploring generative possibilities in Turbo. If you're finding that your results in Turbo aren't quite meeting your expectations, switching to Gen-4 may help you achieve your desired outcome.

Begin by uploading your input image, which is required on both Gen-4 models.

The input image establishes the visual starting point of the entire generative process and acts as the first frame of your output video. 

After uploading, selecting, or creating the input image, begin drafting your text prompt.

Since the image conveys key visual information about subjects, composition, colors, lighting, and style, your text prompt should be almost entirely focused on describing the desired motion.

See the Gen-4 Prompting Guide for more best practices to consider when drafting the prompt. After writing your prompt, you're ready to review the settings before generating.

 

Step 2 — Configuring the Settings

Gen-4 has a few additional settings to consider before starting your generation. Click each setting for more information.

Duration

Gen-4 currently offers outputs in 5 and 10 second durations. The selected model and duration will determine the credit cost, unless generating without using credits while in Explore Mode:

Gen-4

• 5 seconds = 60 credits
• 10 seconds = 120 credits

Gen-4 Turbo

• 5 seconds = 25 credits
• 10 seconds = 50 credits

When choosing a duration, consider the complexity of motion in your prompt. Simple actions can work well in 5-second clips, while prompts requesting multiple movements benefit from the longer 10-second duration. This ensures the model has sufficient time to execute all requested motions completely and naturally without rushing through the sequence.

Resolution

The resolution determines the size and format of your output video. Selecting a resolution that differs from your input image will prompt you to crop the image.

Gen-4 supports the following resolutions:

Format	Aspect Ratio	Pixel resolution
Horizontal	16:9	1280x720
Vertical	9:16	720x1280
Square	1:1	960x960
Horizontal portrait	4:3	1104x832
Vertical portrait	3:4	832x1104
Widescreen	21:9	1584x672

Fixed seed

Using a Fixed seed will allow you to create generations with similar motion. This is unchecked by default to give you a wide variety of results.

Enable the Fixed seed slider and copy and paste the seed of a previous output if you'd like to receive generations with similar style and movement. 

After confirming the settings, you're ready to begin the generation.

 

Step 3 — Generating and Iterating

Click the Generate button to start the generation.

Your generations will be scrollable through your session as you continue to generate. You can also access completed videos in your Assets, where they will save to the associated sub-folder within the Sessions folder by default.

Continue working with your output

Once the generation completes, you can favorite, upscale, or download the output using the controls beneath the right side of the output. Clicking the ellipsis will reveal options to rename, share, or report the video:

Beneath the left side of the output, you'll see additional options to continue working with your video with Runway:

You can learn more about each of these options by expanding the sections below:

Restyle

Opens the video in the Gen-3 Turbo Video to Video tool. Visit the Creating with Video to Video guide for more details.

Expand

Opens the video in the Gen-3 Turbo Expand tool. Visit the Creating with Expand Video guide for more details.

Adjust Video

Opens an editor that allows you to make the following adjustments:

• Trim the video
• Adjust the speed
• Add a handheld shake effect
• Reverse the video

Clicking the Render button will begin an export with the specified adjustments within the session. Adjusting a video does not spend credits.

Lip Sync

Use the video as an input video with the Lip Sync tool. Learn more by visiting the Creating with Lip Sync guide.

Use current frame

Loads the currently previewed frame as the image input.

Upscale to 4K

Begins an Upscale action to increase the video's resolution to 4K. 

 

Iterating the results

You can further refine the results through iteration, which may involve prompt or input image adjustments. Review the Gen-4 Prompting Guide for more details on prompting for iteration.