# Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model

arXiv: https://arxiv.org/abs/2406.15735 · HTML: https://mlsanity.com/paper/2406.15735/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 66 of its 73 references that are in the map.
- First posted on arXiv 22 Jun 2024.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 66)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [Structure and Content-Guided Video Synthesis with Diffusion Models](https://mlsanity.com/paper/2302.03011/) (2023)

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

- [Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation](https://mlsanity.com/paper/2602.02214/) (2026)
- [SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference](https://mlsanity.com/paper/2502.18137/) (2025)
- [SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization](https://mlsanity.com/paper/2411.10958/) (2024)
- [Controllable Video Generation: A Survey](https://mlsanity.com/paper/2507.16869/) (2025)
- [RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers](https://mlsanity.com/paper/2502.15894/) (2025)
- [You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale](https://mlsanity.com/paper/2412.06699/) (2024)
- [Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation](https://mlsanity.com/paper/2605.15141/) (2026)
- [FrameBridge: Improving Image-to-Video Generation with Bridge Models](https://mlsanity.com/paper/2410.15371/) (2024)
- [TVG: A Training-free Transition Video Generation Method with Diffusion Models](https://mlsanity.com/paper/2408.13413/) (2024)
- [Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think](https://mlsanity.com/paper/2503.00948/) (2025)
- [UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers](https://mlsanity.com/paper/2511.20123/) (2025)
- [MotiF: Making Text Count in Image Animation with Motion Focal Loss](https://mlsanity.com/paper/2412.16153/) (2024)
- [AirScape: An Aerial Generative World Model with Motion Controllability](https://mlsanity.com/paper/2507.08885/) (2025)
- [Versatile Transition Generation with Image-to-Video Diffusion](https://mlsanity.com/paper/2508.01698/) (2025)
- [Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance](https://mlsanity.com/paper/2506.08456/) (2025)
- [FlashI2V: Fourier-Guided Latent Shifting Prevents Conditional Image Leakage in Image-to-Video Generation](https://mlsanity.com/paper/2509.25187/) (2025)
- [Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching](https://mlsanity.com/paper/2606.28226/) (2026)
- [SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning](https://mlsanity.com/paper/2603.17426/) (2026)
- [Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models](https://mlsanity.com/paper/2605.19398/) (2026)
- [Physics-Preserving Latent Compression for Zero-Shot Resolution Transfer in 3D Turbulence](https://mlsanity.com/paper/2606.21781/) (2026)
- [Tracking-Guided 4D Generation: Foundation-Tracker Motion Priors for 3D Model Animation](https://mlsanity.com/paper/2512.06158/) (2025)
- [Less is More: Masking Elements in Image Condition Features Avoids Content Leakages in Style Transfer Diffusion Models](https://mlsanity.com/paper/2502.07466/) (2025)
- [ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching](https://mlsanity.com/paper/2512.04904/) (2025)
- [Few-Shot-Based Modular Image-to-Video Adapter for Diffusion Models](https://mlsanity.com/paper/2512.20000/) (2025)
- [3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement](https://mlsanity.com/paper/2606.30514/) (2026)
- [HALLELUAI: A Hallucination-Aware AI System for Ultra-Realistic Image-to-Video Generation at Scale](https://mlsanity.com/paper/2607.22959/) (2026)
- [Conditional Residual Prediction: Improving Autoregressive Video Diffusion without a Bidirectional Teacher](https://mlsanity.com/paper/2610.11479/) (2026)
- [Golden Anchor for Video Generation](https://mlsanity.com/paper/2610.13217/) (2026)

## Abstract (arXiv)

Diffusion models have obtained substantial progress in image-to-video generation. However, in this paper, we find that these models tend to generate videos with less motion than expected. We attribute this to the issue called conditional image leakage, where the image-to-video diffusion models (I2V-DMs) tend to over-rely on the conditional image at large time steps. We further address this challenge from both inference and training aspects. First, we propose to start the generation process from an earlier time step to avoid the unreliable large-time steps of I2V-DMs, as well as an initial noise distribution with optimal analytic expressions (Analytic-Init) by minimizing the KL divergence between it and the actual marginal distribution to bridge the training-inference gap. Second, we design a time-dependent noise distribution (TimeNoise) for the conditional image during training, applying higher noise levels at larger time steps to disrupt it and reduce the model's dependency on it. We validate these general strategies on various I2V-DMs on our collected open-domain image benchmark and the UCF101 dataset. Extensive results show that our methods outperform baselines by producing higher motion scores with lower errors while maintaining image alignment and temporal consistency, thereby yielding superior overall performance and enabling more accurate motion control. The project page: urlhttps://cond-image-leak.github.io/.