Runway’s new AI image generator Frames is here

The provider of AI media technology runway has announced the release of Frames, its latest text-to-image generation model winning early praise from users for producing highly cinematic images – a fitting compliment considering Runway is best known as a provider of AI video models. Could Frames dethrone Midjourney as the top choice for AI filmmakers and artists?

Already announced in November 2024Frames was initially made available to select ambassadors and power users of the Runway Creators program in recent weeks.

From today it is available to everyone Runway’s Unlimited and Enterprise subscription plans, which costs $95 per month or $912 if paid annually or, in the case of the Enterprise plan, $1,500 per year. The company also released a showcase of new images created by Frames users on its website Hereunder the name “Worlds of frames.”

Users can use it to create still images Runway website at app.runwayml.com – if they’re subscribed to the appropriate plan – and then, with one click, use the images as the basis for movies created using Runway’s image-to-video models, such as: Gen-3 Alpha Turbo.

According to Runway, Frames offers a high level of stylistic control and visual fidelity, making it a versatile tool for industries such as editorial, art direction, pre-visualization, brand development and production.

As Cristóbal Valenzuela, co-founder and CEO of Runway, wrote on a Post on social network X: “Frames was built from the ground up for professional creative work. If you work in editorial, art direction, pre-vis, brand development, production, etc., this model is for you.”

Valenzuela further noted that the model’s prompt system allows for precision and depth, allowing users to achieve nuanced, naturalistic and cinematically composed results.

Users seem to agree with this @GenMagic writes on X: “Very high quality, lots of control with style and you can animate your images super quickly right on the runway.” I was craving to see the aesthetic nostalgia of a 90’s mall and Frames didn’t disappoint.”

Or as User @AIandDesign put it: “Damn @runwayml Frames is completely crazy. I can’t stop.”

Creativity meets consistency

Frames allow users to design worlds with specific viewpoints and aesthetic characteristics. Its ability to maintain stylistic consistency while allowing for broad creative exploration sets it apart from previous models, which were often more haphazard and “rolling the dice” in terms of user experience.

With frames, users can establish a clear visual identity for their projects and reliably generate variations that remain true to originality this specific style.

In addition to allowing custom style designs, Frames also comes with a library of 19 preset visual styles at launch that users can select and further customize:

1. Alive

2. Lively warm

3. Lively cool

4. High contrast

5. High contrast, warm

6. High contrast, cool

7. Black and white

8. Black and white contrast

9. Muted pastel

10. Dreamscape

11. Nordic Minimal

12. Light anime

13. Dark Anime

14. Painted Anime

15. 3D cartoon

16. Sketch

17. Low angle

18. On the move

19. Terracotta

These worlds showcase the wide range of creative possibilities that Frames offers, making it an ideal tool for artists, designers and filmmakers seeking stylistic precision.

Designed for creative professionals

Frames offers several enhancements tailored to professional users.

The model excels at rendering advanced textures, natural lighting and complex compositions, offering greater flexibility and a departure from the rigid outputs of previous imaging models.

This release is the first version of Frames and Runway has outlined a clear roadmap for future updates, including more style tools and controls.

Safety and ethical considerations

Runway continues to prioritize safety and ethical responsibility in its generative AI tools. As part of the company Basics for secure generative media Initiative, Frames has robust content moderation features to prevent abuse.

The company’s visual moderation system detects and blocks harmful or inappropriate content, balancing creative freedom and safety.

To address concerns about misinformation and abuse, Frames embeds invisible watermarks into all AI-generated content. These watermarks adhere to the provenance standards set by the Coalition for Content Provenance and Authenticity (C2PA) and allow users to track whether a media item is AI-generated.

Additionally, Runway is committed to improving fairness and representation in its generative models. Efforts have been made to reduce bias in visual output and to support diverse populations and languages.

Still, Runway remains party to a lawsuit by human artists who accuse the company and others like Stability AI and Midjourney of training on their artwork without permission, a violation of copyright law. The case, Andersen v. Stability AI Ltd. (3:23-cv-00201)remains unsolved for now, but is working its way through the courts.