# Step-Video-TI2V Technical Report: A State-of-the-Art Text-Driven Image-to-Video Generation Model

arXiv: https://arxiv.org/abs/2503.11251 · HTML: https://mlsanity.com/paper/2503.11251/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 6 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Builds on (most cited first, 2 of 2)

- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Towards Consistent Video Editing with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.17431/) (2023)

## Built on by (most cited first, 28 of 28)

- [AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation](https://mlsanity.com/paper/2605.13724/) (2026)
- [CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation](https://mlsanity.com/paper/2505.15145/) (2025)
- [Generative Pre-trained Autoregressive Diffusion Transformer](https://mlsanity.com/paper/2505.07344/) (2025)
- [VideoMAR: Autoregressive Video Generatio with Continuous Tokens](https://mlsanity.com/paper/2506.14168/) (2025)
- [4Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation](https://mlsanity.com/paper/2506.18839/) (2025)
- [RISE-Video: Can Video Generators Decode Implicit World Rules?](https://mlsanity.com/paper/2602.05986/) (2026)
- [STORYANCHORS: Generating Consistent Multi-Scene Story Frames for Long-Form Narratives](https://mlsanity.com/paper/2505.08350/) (2025)
- [PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation](https://mlsanity.com/paper/2602.04876/) (2026)
- [ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generation](https://mlsanity.com/paper/2602.10113/) (2026)
- [Planning with Sketch-Guided Verification for Physics-Aware Video Generation](https://mlsanity.com/paper/2511.17450/) (2025)
- [ReVision: Refining Video Diffusion with Explicit 3D Motion Modeling](https://mlsanity.com/paper/2504.21855/) (2025)
- [ViStoryBench: Comprehensive Benchmark Suite for Story Visualization](https://mlsanity.com/paper/2505.24862/) (2025)
- [VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing](https://mlsanity.com/paper/2608.05485/) (2026)
- [OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens](https://mlsanity.com/paper/2603.02138/) (2026)
- [VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?](https://mlsanity.com/paper/2512.13281/) (2025)
- [Audio-Visual Intelligence in Large Foundation Models](https://mlsanity.com/paper/2605.04045/) (2026)
- [CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning](https://mlsanity.com/paper/2606.24636/) (2026)
- [Frame-Level Captions for Long Video Generation with Complex Multi Scenes](https://mlsanity.com/paper/2505.20827/) (2025)
- [PARE: Pruning and Adaptive Routing for Efficient Video Generation](https://mlsanity.com/paper/2605.27336/) (2026)
- [Unified Text-Image-to-Video Generation: A Training-Free Approach to Flexible Visual Conditioning](https://mlsanity.com/paper/2505.20629/) (2025)
- [JWB-DH-V1: Benchmark for Joint Whole-Body Talking Avatar and Speech Generation Version 1](https://mlsanity.com/paper/2507.20987/) (2025)
- [Preview WB-DH: Towards Whole Body Digital Human Bench for the Generation of Whole-body Talking Avatar Videos](https://mlsanity.com/paper/2508.08891/) (2025)
- [VC-Bench: Pioneering the Video Connecting Benchmark with a Dataset and Evaluation Metrics](https://mlsanity.com/paper/2601.19236/) (2026)
- [GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos](https://mlsanity.com/paper/2603.14426/) (2026)
- [The Price of Consistency: Exploiting Visual Anchors for Multimodal Jailbreaking in Video Generation](https://mlsanity.com/paper/2609.07216/) (2026)
- [Complementary Retrieval-Augmented Prompting for Consistent Long-Form Video Generation](https://mlsanity.com/paper/2609.37407/) (2026)
- [MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generation](https://mlsanity.com/paper/2609.39147/) (2026)
- [VDOT++: Unified Few-Step Video Generation via Unbalanced Optimal Transport Distillation](https://mlsanity.com/paper/2610.03221/) (2026)

## Abstract (arXiv)

We present Step-Video-TI2V, a state-of-the-art text-driven image-to-video generation model with 30B parameters, capable of generating videos up to 102 frames based on both text and image inputs. We build Step-Video-TI2V-Eval as a new benchmark for the text-driven image-to-video task and compare Step-Video-TI2V with open-source and commercial TI2V engines using this dataset. Experimental results demonstrate the state-of-the-art performance of Step-Video-TI2V in the image-to-video generation task. Both Step-Video-TI2V and Step-Video-TI2V-Eval are available at https://github.com/stepfun-ai/Step-Video-TI2V.