Draft:Frames (AI image generation)
 | Review waiting, please be patient.
This may take 7 weeks or more, since drafts are reviewed in no specific order. There are 2,686 pending submissions waiting for review.
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
Reviewer tools
|
| Submission declined on 19 September 2025 by Protobowladdict (talk). This submission appears to read more like an advertisement than an entry in an encyclopedia. Encyclopedia articles need to be written from a neutral point of view, and should refer to a range of independent, reliable, published sources, not just to materials produced by the creator of the subject being discussed. This is important so that the article can meet Wikipedia's verifiability policy and the notability of the subject can be established. If you still feel that this subject is worthy of inclusion in Wikipedia, please rewrite your submission to comply with these policies.
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
This draft has been resubmitted and is currently awaiting re-review. |  |
Comment: Personally I feel it would be better if it was moved to "Runway Frames" as right now the title is a bit too disambiguated and it would then match up with the title in the lead. Zippybonzo | talk | contribs (they/them) 19:35, 23 September 2025 (UTC)
- Comment: This reads like it might be AI-generated —pythoncoder (talk | contribs) 20:22, 22 September 2025 (UTC)
- Comment: In accordance with the Wikimedia Foundation's Terms of Use, I disclose that I have been paid by my employer for my contributions to this article. Itsjuliamartins (talk) 17:30, 19 September 2025 (UTC)
Runway Frames, also known as Gen-4 Images, is an artificial intelligence image generation model developed by Runway AI, Inc. Released in November 2024, the model generates images from text descriptions and is part of Runway's Gen-4 series of generative AI models.[1][2]
Overview
[edit]Runway Frames is a text-to-image generation model that creates images based on text prompts provided by users. The system includes preset style options and allows for custom style creation through reference images.
History
[edit]Initial release
[edit]Runway announced Frames in November 2024.[1] The initial release was limited to participants in Runway's Creators Program before wider deployment.[3]
Commercial Availability
[edit]On January 10, 2025, Frames became available to users with Runway's Unlimited ($95/month or $912 annually) and Enterprise subscription plans.[4]
Integration with Gen-4
[edit]According to Runway's official documentation, Frames is now branded as "Gen-4 Images," indicating its integration into the Gen-4 model family released in March 2025.[1] This positions the image generation capabilities alongside Gen-4's video generation functions.[5]
Technical specifications
[edit]Frames is described by Runway as a foundational AI model that processes text prompts to generate images.[1] The system employs neural networks, though specific architectural details, training methodologies, and dataset sources have not been publicly disclosed by the company.[6]
Functionality
[edit]Text-to-image generation
[edit]The primary function involves converting text descriptions into generated images.[3] Users input text prompts describing desired visual content, and the model produces corresponding images.[1]
Style options
[edit]The model includes 19 preset visual styles at launch, covering various aesthetic categories including portraiture, vintage aesthetics, manga-inspired designs, and architectural photography styles.[1] Users can also create custom styles by providing reference images alongside text descriptions.[1]
Usage and applications
[edit]Creative industries
[edit]Users in film and television production have reported using the model for concept art and storyboarding purposes.[6][7]
Commercial applications
[edit]Some marketing agencies have reported using Frames for creating visual content for campaigns.[6] The model's role typically supplements rather than replaces traditional creative processes, with outputs often requiring additional editing or serving as conceptual starting points.
References
[edit]- ^ a b c d e f g "Runway Research | Introducing Frames". runwayml.com. Retrieved 2025-09-19.
- ^ Lloyd Coombes (2024-11-26). "Runway launches Frames — a new AI image generator that creates custom worlds". Tom's Guide. Retrieved 2025-09-19.
- ^ a b Franzen, Carl (17 January 2025). "Runway's new AI image generator Frames is here, and it looks fittingly cinematic". VentureBeat.
- ^ "Runway | Tools for human imagination". runwayml.com. Retrieved 2025-09-19.
- ^ Wiggers, Kyle (2025-03-31). "Runway releases an impressive new video-generating AI model". TechCrunch. Retrieved 2025-09-19.
- ^ a b c Horsey, Julian (2024-11-26). "Runway Launches Frames its AI Still Image Generator". Geeky Gadgets. Retrieved 2025-09-19.
- ^ Albergotti, Reed. "The new Hollywood: Runway's AI models edge closer to simulating reality".