Φ-Noise: Training-Free Temporal Video Conditioning via Phase-Based Noise Manipulation

• URL: http://arxiv.org/abs/2605.24509v1
• Date: Sat, 23 May 2026 10:43:40 GMT
• Title: Φ-Noise: Training-Free Temporal Video Conditioning via Phase-Based Noise Manipulation
• Abstract summary: Latent video diffusion models generate videos by transforming Gaussian noise into realistic samples conditioned on text or visual inputs.<n>We propose a training-free approach for motion-conditioned video generation by injecting low-frequency phase information from a reference video directly into the diffusion noise latents.
• Score: 16.367974672253055
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Latent video diffusion models generate videos by progressively transforming Gaussian noise into realistic samples conditioned on text or visual inputs. However, existing conditioning methods often require additional training and computational overhead. Motivated by recent findings on the importance of frequency components in generative models, we propose a simple, training-free approach for motion-conditioned video generation by injecting low-frequency phase information from a reference video directly into the diffusion noise latents. Our method transfers motion cues without modifying the model architecture or inference pipeline. Using several applications, we demonstrate effective control over both appearance and dynamics in generated videos, while achieving competitive or superior results compared to more complex conditioning approaches.

Related papers

• Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning [85.93126001283169]
  We introduce Equilibrium Forcing (EqF), a framework for video denoising generative models without noise level conditioning.<n>This flexibility allows for inference-time algorithms that operate in a closed loop by adapting to feedback from the sample.
  arXiv  Detail & Related papers  (2026-08-11T00:02:32Z)
• Training-Free Motion Customization for Distilled Video Generators with Adaptive Test-Time Distillation [53.877572078307935]
  Distilled video generation models offer fast and efficient but struggle with motion customization when guided by reference videos.<n>We propose MotionEcho, a training-free test-time distillation framework that enables motion customization by leveraging diffusion teacher forcing.
  arXiv  Detail & Related papers  (2025-06-24T06:20:15Z)
• FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation [51.110607281391154]
  FlowMo is a training-free guidance method for enhancing motion coherence in text-to-video models.<n>It estimates motion coherence by measuring the patch-wise variance across the temporal dimension and guides the model to reduce this variance dynamically during sampling.
  arXiv  Detail & Related papers  (2025-06-01T19:55:33Z)
• FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models [9.469635938429647]
  Video Diffusion Models (VDMs) can generate high-quality videos, but often struggle with producing temporally coherent motion.<n>We propose FlowLoss, which directly compares flow fields extracted from generated and ground-truth videos.<n>Our findings offer practical insights for incorporating motion-based supervision into noise-conditioned generative models.
  arXiv  Detail & Related papers  (2025-04-20T08:22:29Z)
• RAGME: Retrieval Augmented Video Generation for Enhanced Motion Realism [73.38167494118746]
  We propose a framework to improve the realism of motion in generated videos.<n>We advocate for the incorporation of a retrieval mechanism during the generation phase.<n>Our pipeline is designed to apply to any text-to-video diffusion model.
  arXiv  Detail & Related papers  (2025-04-09T08:14:05Z)
• AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset [55.82208863521353]
  We propose AccVideo to reduce the inference steps for accelerating video diffusion models with synthetic dataset.<n>Our model achieves 8.5x improvements in generation speed compared to the teacher model.<n>Compared to previous accelerating methods, our approach is capable of generating videos with higher quality and resolution.
  arXiv  Detail & Related papers  (2025-03-25T08:52:07Z)
• Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise [19.422355461775343]
  We enhance video diffusion models by allowing motion control via structured latent noise sampling.<n>We propose a novel noise warping algorithm, fast enough to run in real time, that replaces random temporal Gaussianity with correlated warped noise.<n>The efficiency of our algorithm enables us to fine-tune modern video diffusion base models using warped noise with minimal overhead.
  arXiv  Detail & Related papers  (2025-01-14T18:59:10Z)
• Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency [15.841490425454344]
  We propose an end-to-end audio-only conditioned video diffusion model named Loopy.<n>Specifically, we designed an inter- and intra-clip temporal module and an audio-to-latents module, enabling the model to leverage long-term motion information.
  arXiv  Detail & Related papers  (2024-09-04T11:55:14Z)
• SF-V: Single Forward Video Generation Model [57.292575082410785]
  We propose a novel approach to obtain single-step video generation models by leveraging adversarial training to fine-tune pre-trained models. Experiments demonstrate that our method achieves competitive generation quality of synthesized videos with significantly reduced computational overhead.
  arXiv  Detail & Related papers  (2024-06-06T17:58:27Z)
• Continuous-Time Video Generation via Learning Motion Dynamics with Neural ODE [26.13198266911874]
  We propose a novel video generation approach that learns separate distributions for motion and appearance. We employ a two-stage approach where the first stage converts a noise vector to a sequence of keypoints in arbitrary frame rates, and the second stage synthesizes videos based on the given keypoints sequence and the appearance noise vector.
  arXiv  Detail & Related papers  (2021-12-21T03:30:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.