Runway, the leading AI video platform, has introduced a “turbo” version of its Gen-3 model, enabling faster video creation from images. Gen-3, initially launched earlier this month as a text-to-video model, soon expanded to include image-to-video capabilities. Now, with the Turbo version, the process has become even quicker.
Using Turbo is straightforward—select it in the video creation tool, upload an image (Midjourney works well here), and optionally add a text prompt to describe camera movements and character actions.
In my experience, Turbo was able to generate a fully rendered ten-second video from an initial prompt in just 15 seconds, with no noticeable drop in quality. This brings us closer to near real-time AI video production.
Testing Gen-3 Turbo The Gen-3 Alpha Turbo Image to Video is now available, boasting a 7x speed increase at half the cost of the original Gen-3 Alpha, while maintaining performance across various use cases. Turbo is accessible on all plans, including free trials.
For my tests, I created five prompts using Midjourney to generate a variety of scenes as starting images, and I used Runway’s prompt guide to craft the corresponding text prompts. All clips are ten seconds long, as there is no option to extend beyond the initial generation. While you could use a screenshot of the last frame to start a new clip, I kept things simple.
Runway has hinted at more improvements to come, including enhanced control mechanisms and possibilities for real-time interactivity thanks to the new Turbo model.
The Ancient Tree Midjourney prompt:
“A massive, gnarled ancient oak tree standing alone in a misty meadow at dawn, with its twisted roots exposed and branches reaching out like arms.”
Runway motion prompt: “The camera starts at the base of the ancient oak, slowly spiraling upwards to reveal the full height of the tree against the backdrop of a misty dawn. The focus is on the intricate details of the bark, roots, and branches as the sun begins to rise.”
This prompt tests the ability of both Runway and Midjourney to handle complex textures and smooth camera movements. I think they both performed well.
The Village Market Midjourney prompt:
“A vibrant village market bustling with activity, featuring vendors selling colorful fruits, vegetables, and flowers, with people of all ages interacting under a bright, sunny sky.”
Runway motion: “The camera moves through the lively village market, capturing the energetic interactions of people bartering and laughing. The focus shifts between vendors displaying their goods and customers browsing, emphasizing the market’s vibrant atmosphere.”
This scene challenges the AI to manage dynamic, human-centered interactions while maintaining the visual consistency of the image.
The Influencer Midjourney image:
“A young woman recording a vlog in a cozy, well-lit room filled with plants, books, and soft decor, with a ring light and camera set up in front of her.”
Runway motion: “The camera follows the influencer as she moves around her cozy room, adjusting the lighting and camera, then begins recording her vlog. The shot focuses on her facial expressions and the warm, inviting atmosphere of the space.”
This prompt tests the AI’s ability to simulate human expression and handle hand movements. The results were good, though not perfect, with a hint of artificiality.
The Train Ride Midjourney prompt:
“A scenic train ride through a mountainous landscape during the golden hour, with passengers gazing out the window at the breathtaking view.”
Runway motion: “The camera starts inside the train, focusing on passengers looking out the window with golden hour lighting, then shifts to a view outside, capturing the beautiful mountainous scenery as the train glides through the landscape during the golden hour.”
This test examines Runway’s ability to transition between shots inspired by the image while maintaining a consistent feel. It was close but might have worked better with a text-to-video prompt without the starting image.
A Music Festival Midjourney image:
“A vibrant outdoor music festival at dusk, with a large crowd of people dancing, colorful lights illuminating the stage, and a band performing energetically.”
Runway motion: “The camera sweeps over the energetic crowd at a music festival, capturing the lively dancing and flashing stage lights as the band performs. The focus moves from the stage to the crowd, highlighting the collective excitement and energy of the event.”
This final test explores how Runway handles complex, high-energy scenes with multiple moving elements. It performed well, though the dancers appeared somewhat similar.
Final Thoughts The ability to rapidly generate videos marks a significant advancement for Runway. It suggests the potential for a future high-resolution mode where failed generations can be upscaled.
AI video technology has progressed remarkably over the past year. We’ve reached a point where short films composed of ten-second clips can look almost real. Each new generation enhances image and motion realism.
Turbo accelerates the entire process, enabling quick iterations, which is particularly useful given that the ratio of usable to unusable clips remains around 5:1.