Runway Gen-4.5: Text & Image to Video Online

Text & Image to Video4.2 / 5Strict content filter

Bottom line

The top of Runway's line on VdoBloom — cinematic text- or image-driven clips up to 10 seconds. Start from a prompt or a still image in the Text to Video tool; VdoBloom shows the exact credit cost before each Runway Gen-4.5 run, with no separate Runway account.

Gen-4.5 sits at the top of the Runway lineup on VdoBloom. Where Gen-3 established the family's cinematic look and Gen-4 Turbo optimized for speed, this release is the one to reach for when the prompt itself is demanding — layered scene descriptions, specific camera direction, or an image start that has to be respected while everything around it moves.

The model takes either a text prompt or a source image and produces clips of 5, 8, or 10 seconds. Framing options cover 16:9, 9:16, 4:3, 3:4, and 1:1, so output drops into any standard deliverable format without letterboxing workarounds.

As with all Runway models, the content policy is strict: Gen-4.5 is labeled CENSORED, and prompts involving explicit material or real-person likeness are filtered at the provider level. VdoBloom users rate it 4.2. Generation runs on VdoBloom credits, with the exact cost for your chosen settings shown before you commit — worth noting because a flagship model is where careful shot planning tends to pay for itself.

What creators use Runway Gen-4.5 for

  • Render a complex multi-element scene description as a 10-second cinematic clip for a pitch reel.
  • Animate final key art with precise camera direction written into the prompt for a launch teaser.
  • Produce matched 16:9 and 9:16 versions of the same hero shot for cross-platform campaigns.

How to use Runway Gen-4.5 on VdoBloom

  1. 1Open the Text to Video tool and select Runway Gen-4.5 from the model picker.
  2. 2Write your prompt — or upload a starting image for image-to-video.
  3. 3Choose your duration (5–10s), aspect ratio, review the credit cost, and generate.

Frequently asked questions

Does Runway Gen-4.5 accept both text and image inputs?

Yes. Gen-4.5 is a text-and-image-to-video model: describe a scene from scratch, or upload a starting image and use the prompt to control how it moves. This dual-input flexibility is one of the main things separating it from the image-only Gen-4 Turbo.

What clip lengths does Gen-4.5 offer?

5, 8, or 10 seconds per generation, in any of five aspect ratios: 16:9, 9:16, 4:3, 3:4, and 1:1.

How strict is Gen-4.5's content moderation?

It carries the CENSORED label, VdoBloom's strictest tier. Runway filters explicit content, graphic violence, and real-person likeness at the provider level, which makes the model dependable for brand and client work but unsuitable for edgier concepts.

When should I pick Gen-4.5 over Gen-4 Turbo?

Pick Gen-4.5 when you need a text-only start or when the prompt is complex enough to benefit from the newest generation in Runway's line. Gen-4 Turbo is the faster choice for rapid iteration when you already have a source image and mainly need motion options.

Related models