Skip to main content

Search

Creating with Frames


Frames is available to Unlimited and Enterprise plan users

 

Introduction

Frames is our most advanced base model for image generation, offering unprecedented stylistic control and visual fidelity.

This guide covers accessing Frames in your dashboard, the available settings and how to use them, and how to reiterate your results to receive your desired output.

Article highlights

  • Each generation costs 32 credits and creates 4 images
  • Simple prompts work well, but more advanced prompts yield more control
  • Enable the Aesthetic Range setting for more creatively diverse results in an image set
  • Use the Vary action to create a new image set based on a single output

Related links

Spec Information

Pricing Cost 32 credits per 4 images
Explore Mode on Unlimited Plans Yes
Prompting Base prompt inputs Text
Maximum prompt size 1000 characters
Outputs Aspect ratios 16:9
9:16
1:1
4:3
3:4
21:9
Resolution 1080p

 

Step 1 – Drafting the Prompt

Begin by navigating to Generative Session from your Runway Dashboard to create a new session with Frames.

From an existing session, you can switch to Frames by selecting Image from the top of the canvas.

Either method will bring you to the Frames canvas that includes the prompting box and other settings:

ui.png

Draft your text prompt in the prompting box. Simple prompts work well, but more advanced prompts will yield more stylistic control. See the Frames Prompting Guide for examples, inspiration, and more details on prompting. 

After drafting your prompts, you’re ready to configure the additional settings.

 

Step 2 – Configuring the Settings

Frames currently supports the following settings before generating:

  • Aspect ratio: Choose the dimensions of the image outputs
  • Style: Apply a curated style preset
  • Aesthetic Range: Configure the creative variation between images in a generation set
  • Settings: Configure a randomized or fixed seed (seeds are randomized by default)

Understanding the Aesthetic Range setting

The Aesthetic Range setting is powerful for exploring creative concepts in an image set without making adjustments to your prompt.

This setting can be configured to a value between 0 to 5, where 0 represents no variation from the input prompt and 5 will result in more dramatic aesthetic range.

Prompt Aesthetic range value Outputs
cinematic photograph of a human made entirely of white hologram static in a field of flowers at night. dynamic pose Off
3
5

 

Understanding fixed and randomized seeds

Frames uses randomized seeds by default to create more variety between generations. 

Fixed seeds are useful for receiving similar results when prompt adjustments are needed for a completed image set. See Step 4 – Reiterating the Results for examples of fixed seed outputs.

 

Step 3 – Generating the Image

After configuring the prompt and settings, you’re now ready to generate your image set.

Each 4 image set generation will use 32 credits, or 8 credits per image. If you’re on an Unlimited plan, you can generate infinite images without using credits while in Explore Mode.

Click the purple Generate button to start the generation.

Your generations will begin processing on the right-hand side of the canvas, and will be scrollable through your session as you continue to generate.

If you receive a generation error, please ensure that your prompt complies with our acceptable content policies.

Once your generation is complete, you can hover over an image to reveal options to continue working with the output, such as Use and Vary:

  • Use will load the image into the Generative Video tools, using Text/Image to Video by default
  • Vary will immediately start a new image set generation in the style of the selected output

If you're ready to bring your image to life by transforming it into a video, select the Use option and learn more about our Generative Video tools on the Gen-3 Alpha models.

Keep reading to learn how to further perfect your images through iteration.

 

Step 4 – Iterating on Outputs

There are three options for iterating on your outputs once the generation completes:

Iterating with text prompt updates

Iterating with text prompt updates is helpful when you'd like to receive larger changes or to reinforce elements that were not conveyed to preference in the output of the image set.

As an example, say we used the following prompt for our first generation attempt to receive these results:

Prompt Outputs
photograph of warped ornate classic buildings in a black abyss. stark white color palette with cool blue and green tones. avant-garde. vibrant red, blue, purple, jewel green. Screenshot 2025-01-06 at 9.38.19 PM.png

However, we wish to see more exaggerated warping and and the buildings conjoined by a liquid material. Updating the prompt would be best to receive these dramatic changes:

Prompt Outputs
photograph of warped ornate classic buildings in a black abyss. the buildings are in surreal shapes. the buildings curve and bend impossibly high into the black sky in a glitched swirl formation, defying gravity. stark white color palette with cool blue and green tones. distorted. warped, squished, and extremely deformed and exaggerated. avant-garde. vibrant red, blue, purple, jewel green. conjoined bubblegum stretch. hologram. encased in translucent liquid chrome with an iridescent sheen. Screenshot 2025-01-06 at 9.49.16 PM.png

 

Iterating with Vary for structurally unique results from a single image

The Vary action allows you to further explore a single image by generating new results in a similar style, but with a different structure or composition.

Hover over a completed generation to reveal the Vary action:

Clicking Vary will immediately start a new image set generation that’s based on the selected image. Below are the Vary results of the previous example:

You can continue to use Vary on any output to explore new worlds and find inspiration from Frames.

 

Iterating with fixed seeds for similar results from an image set

By default, seeds are randomized per image set, meaning that the four unique images in a single generation share the same seed, and the seed will change between generations.

Fixed seeds are useful for receiving similar results when minor prompt adjustments are needed for a completed image set. 

Using a fixed seed will regenerate the entire image set and cannot be isolated to a specific result in the set. Additionally, seeds are not shared across aspect ratios, so selecting a different aspect ratio would create unexpected results.

Below are the steps to use fixed seeds with Frames:

  • Click an image from the set you’d like to regenerate to open the full prompt details
  • Click the Copy button next to the Seed
  • Click Reuse prompt to load the previous prompt settings
  • Click the Settings icon to open the seed settings
  • Paste the copied seed in, and click the randomize button to change it to a lock
  • Close the settings menu and make the necessary changes to your prompt

ℹ️ Please note that fixing the seed to a previously generated image set without changing the prompt will result in the same images being generated.

Below is an example of when using a fixed seed to regenerate the results with a modified prompt:

Prompt Seed Output
cinematic photograph of a woman in a white sundress sitting in a field of flowers in a relaxed pose. 208761375 (Original) Frames 208761375, cinematic photograph.png
cinematic photograph of a woman in a blue sundress sitting in a field of flowers in a relaxed pose. 208761375 (Fixed) Frames 208761375, cinematic photograph (1).png
cinematic photograph of a woman in a blue sundress standing in a field of flowers in a relaxed pose. 208761375 (Fixed) Frames 208761375, cinematic photograph (2).png

In this example, we used a fixed seed to change the white sundress into a blue sundress while maintaining a similar subject pose and scene composition. 

More dramatic prompt updates, such as changing the subject pose from sitting to standing, resulted in more noticeable changes in the output.