Runway AI Video Generator
Runway is a video platform. Gen-4.5 is the current generation model: text-to-video or image-to-video, 2 to 10 seconds, native 720p, 24 or 25 fps. Aleph 2.0 is a separate video-to-video editor. The limits below are from Runway’s Gen-4.5 help article and Dev docs.
01 — Capabilities
A 10-second clip, or an edit of a clip you already have
Gen-4.5 creates. Aleph 2.0 rewrites. They are different model ids. Additional inputs on Gen-4.5 are marked coming soon.
01
2 to 10 seconds on Gen-4.5
Runway’s Gen-4.5 article lists 2–10 seconds for both text-to-video and image-to-video. That is the generation ceiling. It is not a 30-second model. Default duration on typical API wrappers is 5 seconds.
02
720p out, with extra ratios on image-to-video
Native output is 720p. Text-to-video is documented at 16:9 (1280×720). Image-to-video adds 9:16, 1:1, 4:3, 3:4 and 21:9. Frame rate is 24 or 25 fps. Higher delivery is a later step, not the generation resolution.
03
Aleph 2.0 edits a source up to 30 seconds
Aleph 2.0 is video-to-video. You pass a clip and a prompt; optional keyframes pin stills to moments, up to five. The source cap in third-party docs is 30 seconds. That is an edit, not a blank generation.
04
ProRes, PNG sequence, 10-bit SDR
Gen-4.5 and Aleph 2.0 can return ProRes, a PNG sequence, or 10-bit Rec.709 SDR as well as H.264. Those formats cost extra credits. HDR delivery is documented as a separate path, not the default mp4.
02 — Prompt to output
Prompts that match the clips above
Each prompt describes the picture on its card. “Use this prompt” sends that text to Create. The generator on this page runs Seedance 2.5, not Runway.
- 01 · Portrait
PromptClose-up of a young man with curly hair in a grey knit sweater, soft window light. He glances away, then smiles. Slow push-in, shallow depth of field.
- 02 · Product
PromptA white leather sneaker on a pale grey studio backdrop, soft diffused light. The camera orbits slowly. Stitching stays sharp, the look stays minimal.
- 03 · Street
PromptA slow dolly down a cobblestone lane in an old European village. Climbing roses on stone walls, café tables in morning sun, a few people walking in the distance.
- 04 · Character
PromptA young woman with shoulder-length brown hair in an olive t-shirt, late-afternoon gold light. She turns her head and looks off. Breeze in her hair, a handheld feel.
03 — Where it fits
Jobs that fit a 10-second generate or a 30-second edit
Use Gen-4.5 when you are starting from a prompt or a still. Use Aleph when the motion already exists and you need the picture rewritten.
A sequenced camera move in one prompt
Runway’s Gen-4.5 article is explicit that the model is built for choreography, timing and atmosphere written as instructions. Longer sequential actions want the top of the 2–10 second range.
Animate a still, keep its crop
Image-to-video takes a first-frame image. Aspect follows that still unless you change it and crop. Gen-4 Turbo on the API is image-to-video only.
Rewrite a clip you already shot
Aleph 2.0 keeps the source motion and changes how it looks. Up to five keyframes can pin a look at specific times. That is not how you start from a blank prompt.
Hand a file to editorial
ProRes or a PNG sequence can come out of Gen-4.5 or Aleph 2.0 on Max, Unlimited (legacy) and Enterprise plans in the product, or via outputFormat in the API. 720p is still the generation size.
04 — Verdict
What Runway’s current docs actually list
Strengths
- Gen-4.5: text-to-video and image-to-video, 2–10 seconds, 24 or 25 fps
- Image-to-video ratios including 1:1, 4:3 and 21:9
- Aleph 2.0: video-to-video with up to 5 keyframes
- ProRes, PNG sequence and 10-bit SDR on Gen-4.5 and Aleph 2.0
Trade-offs
- Gen-4.5 native output is 720p; 10 seconds is the generation ceiling
- Text-to-video is documented more narrowly on aspect ratio than image-to-video
- Additional inputs on Gen-4.5 are marked coming soon
- Runway is not available on ImgToVid
05 — Side by side
Runway Gen-4.5, Veo 3.1 and Kling 4.0
Clip length and whether you generate or edit are where these three stop lining up. Aleph 2.0’s 30-second source is an edit cap, not a Gen-4.5 duration.
06 — How it works
Start a clip on ImgToVid
Step 1
Describe one shot
Subject, action, camera. If you wanted Runway’s 2–10 second window or Aleph’s rewrite, write the move in the prompt. Runway will not be the model that runs it.
Step 2
Use the generator on this page
It runs Seedance 2.5, because Runway is not offered here. The prompt and the settings carry into Create.
Step 3
Generate in Create
Membership and credits are checked there. Coming back to this page does not switch the model over to Runway.
07 — FAQ
Runway, in plain terms
What is Runway?
Runway is a video platform. The current generation model is Gen-4.5 (text-to-video and image-to-video). Gen-4 Turbo is a faster image-to-video variant. Aleph 2.0 edits existing video. Act-Two is a separate character-performance model.
How long is a Gen-4.5 clip?
2 to 10 seconds. That is the range in Runway’s Gen-4.5 help article for both text-to-video and image-to-video.
What resolution does Gen-4.5 generate?
720p. Aspect ratios are listed as 16:9 for text-to-video, with more options on image-to-video. ProRes, PNG sequence and 10-bit SDR are delivery formats, not a higher generation resolution.
What is Aleph 2.0?
Aleph 2.0 is Runway’s video-to-video editor. You provide a source clip and a prompt, and you can pin up to five keyframe images. Third-party API docs cap the source at 30 seconds. It does not start from text alone.
Can I generate Runway videos on ImgToVid?
No. The generator on this page runs Seedance 2.5 so you can draft a shot. Runway itself is marked coming soon.
Can I use the results commercially?
Commercial use of anything you generate on ImgToVid depends on your plan. Check Pricing and our Terms before you publish, and make sure prompts and uploads do not infringe someone else’s rights.
08 — Explore more
Other video models
Runway is not the button on this page
You can still draft the shot. The generator runs Seedance 2.5, and the prompt goes with you into Create.
Draft in Create