# Runway Image-to-Video > Runway Image-to-Video is available on Artifio.ai — a unified AI workspace with a single pay-as-you-go wallet. - Canonical page: https://artifio.ai/models/runway-image-to-video - Run it: https://artifio.ai/create/runway-image-to-video - Modality: image to video - Model brand: Runway - Pricing: from about $0.060 per generation (exact cost shown in the workspace before you confirm; varies with selected options) - Typical generation time: ~240s (catalogue estimate) - Full pricing table: https://artifio.ai/pricing/models ## About Runway Image-to-Video Image-to-video is the mode much of Runway's film and advertising user base actually works in: a still frame goes in, a moving shot comes out. The current generation is Gen-4.5, announced December 1, 2025, with image-to-video support rolled out on January 21, 2026. The mode animates any static image regardless of its origin, whether photographic, AI-generated, sketched, or illustrated. It builds on the reference-image approach Runway introduced with Gen-4, where a single image of a character or object keeps that subject consistent across new angles, lighting conditions, and scenes without any fine-tuning. Runway runs inference on NVIDIA Hopper and Blackwell GPUs, and the same model family holds the top launch score Runway reported on the Artificial Analysis text-to-video benchmark. On Artifio the model sits in one workspace beside 100+ others, paid per generation from a single wallet rather than a separate subscription. ## Features - Animates a supplied still image into a video clip, guided by an optional text prompt - Accepts photographic, AI-generated, sketched, and illustrated source images - Gen-4.5 image-to-video launched January 21, 2026, following the December 1, 2025 text-to-video debut - Single-reference consistency, carried over from Gen-4: one image of a subject holds it stable across different shots, lighting, and locations with no fine-tuning - Sits in a control family that also includes keyframes and video-to-video modes - Runway cites photorealistic character generation, establishing shots, chase sequences, and VFX-grade output as target shot types ## What people use it for - Bringing product photography to life for ads and social video - Animating concept art and storyboard frames into moving previz - Generating establishing shots or chase coverage from a single designed frame - Keeping one character consistent across a multi-scene edit using a reference still ## Reported strengths - Subject consistency from a single reference image is the feature Runway built the Gen-4 line around, and it requires no per-subject training - Handles a wide range of source imagery, including rough sketches and illustration, per Runway's launch materials - Physically plausible motion is the stated focus of the Gen-4.5 generation - The underlying model topped the Artificial Analysis text-to-video benchmark at its November 30, 2025 evaluation, per Runway ## Reported limitations - Runway documents causal reasoning failures in Gen-4.5, where effects sometimes precede causes - Object permanence is imperfect: elements of a scene may appear or vanish unexpectedly across frames - A documented success bias means depicted actions succeed more often than realism would suggest - Runway's announcement materials do not publish fixed output resolution or duration figures for the mode ## Sources 1. Introducing Runway Gen-4.5 (Runway): https://runwayml.com/research/introducing-runway-gen-4.5 2. Runway Gen-4.5 Image to Video Tool (Newsshooter): https://www.newsshooter.com/2026/01/21/runway-gen-4-5-image-to-video-tool/ 3. Introducing Runway Gen-4 (Runway): https://runwayml.com/research/introducing-runway-gen-4 --- About Artifio.ai: 100+ AI image, video, and audio models in one workspace with a single shared wallet — no per-model subscriptions. This is the markdown rendition of https://artifio.ai/models/runway-image-to-video for AI assistants and crawlers; the HTML page is canonical.