# SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation

Source: [SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation](<https://www.sota2.com/research/paper/69fd6e565497b3b670c896b2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-13T05:00:05.563Z

Authors: YaoYang Liu, Yuechen Zhang, Wenbo Li, Yufei Zhao, Rui Liu, Long Chen

Published: 2026-05-07T14:34:23.000Z

## Abstract

High-resolution image-to-video (I2V) generation aims to synthesize realistic temporal dynamics while preserving fine-grained appearance details of the input image. At 2K resolution, it becomes extremely challenging, and existing solutions suffer from various weaknesses: 1) end-to-end models are often prohibitively expensive in memory and latency; 2) cascading low-resolution generation with a generic video super-resolution tends to hallucinate details and drift from input-specific local structures, since the super-resolution stage is not explicitly conditioned on the input image. To this end, we propose SwiftI2V, an efficient framework tailored for high-resolution I2V. Following the widely used two-stage design, it addresses the efficiency--fidelity dilemma by first generating a low-resolution motion reference to reduce token costs and ease the modeling burden, then performing a strongly image-conditioned 2K synthesis guided by the motion to recover input-faithful details with controlled overhead. Specifically, to make generation more scalable, SwiftI2V introduces Conditional Segment-wise Generation (CSG) to synthesize videos segment-by-segment with a bounded per-step token budget, and adopts bidirectional contextual interaction within each segment to improve cross-segment coherence and input fidelity. On VBench-I2V at 2K resolution, SwiftI2V achieves performance comparable to end-to-end baselines while reducing total GPU-time by 202x. Particularly, it enables practical 2K I2V generation on a single datacenter GPU (e.g., H800) or consumer GPU (e.g., RTX 4090).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image-to-Video Generation on VBench-I2V (2K resolution)](<https://www.sota2.com/research/sota/image-to-video-generation-on-vbench-i2v-2k-resolution.md>): Image-to-Video Generation; VBench-I2V 2K resolution; Total Score: 6.4244.

- [Image-to-Video Generation on 81-frame 2K video 2560 × 1408 (Efficiency)](<https://www.sota2.com/research/sota/image-to-video-generation-on-81-frame-2k-video-2560-1408-efficiency.md>): Image-to-Video Generation; 81-frame 2K video 2560 × 1408; Peak Memory Usage (GB): 33.5.

- [Image-to-Video Generation on VBench-I2V 63-sample (test)](<https://www.sota2.com/research/sota/image-to-video-generation-on-vbench-i2v-63-sample-test.md>): Image-to-Video Generation; VBench-I2V 63-sample (test); Total Score: 6.4284.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.06356>)

[PDF](<https://arxiv.org/pdf/2605.06356.pdf>)

[Implementation](<https://github.com/HKUST-LongGroup/SwiftI2V>)