mlsanityData to 14 Oct 2026

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

arXiv 2503.11251 ↗First posted 14 Mar 2025cs.CV cs.CLcited by 28

Not on the map. Why?

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.

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

2 of 6 references.

References · 2

  1. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  2. 2023Towards Consistent Video Editing with Text-to-Image Diffusion Modelscited by 34

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 13; 2026: 15.

28 papers.

Sort:

By area:

  1. 2026AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillationcited by 26
  2. 2025CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generationcited by 23
  3. 2025Generative Pre-trained Autoregressive Diffusion Transformercited by 16
  4. 2025VideoMAR: Autoregressive Video Generatio with Continuous Tokenscited by 16
  5. 20254Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generationcited by 14
  6. 2026RISE-Video: Can Video Generators Decode Implicit World Rules?cited by 10
  7. 2025STORYANCHORS: Generating Consistent Multi-Scene Story Frames for Long-Form Narrativescited by 9
  8. 2026PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generationcited by 9
  9. 2026ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generationcited by 8
  10. 2025Planning with Sketch-Guided Verification for Physics-Aware Video Generationcited by 6
  11. 2025ReVision: Refining Video Diffusion with Explicit 3D Motion Modelingcited by 5
  12. 2025ViStoryBench: Comprehensive Benchmark Suite for Story Visualizationcited by 5
16 more
  1. 2026VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editingcited by 5
  2. 2026OmniLottie: Generating Vector Animations via Parameterized Lottie Tokenscited by 3
  3. 2025VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?cited by 2
  4. 2026Audio-Visual Intelligence in Large Foundation Modelscited by 2
  5. 2026CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioningcited by 2
  6. 2025Frame-Level Captions for Long Video Generation with Complex Multi Scenescited by 1
  7. 2026PARE: Pruning and Adaptive Routing for Efficient Video Generationcited by 1
  8. 2025Unified Text-Image-to-Video Generation: A Training-Free Approach to Flexible Visual Conditioningcited by 0
  9. 2025JWB-DH-V1: Benchmark for Joint Whole-Body Talking Avatar and Speech Generation Version 1cited by 0
  10. 2025Preview WB-DH: Towards Whole Body Digital Human Bench for the Generation of Whole-body Talking Avatar Videoscited by 0
  11. 2026VC-Bench: Pioneering the Video Connecting Benchmark with a Dataset and Evaluation Metricscited by 0
  12. 2026GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videoscited by 0
  13. 2026The Price of Consistency: Exploiting Visual Anchors for Multimodal Jailbreaking in Video Generationcited by 0
  14. 2026Complementary Retrieval-Augmented Prompting for Consistent Long-Form Video Generationcited by 0
  15. 2026MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generationcited by 0
  16. 2026VDOT++: Unified Few-Step Video Generation via Unbalanced Optimal Transport Distillationcited by 0