P-Flow: Prompting Visual Effects Generation

• URL: http://arxiv.org/abs/2603.22091v1
• Date: Mon, 23 Mar 2026 15:21:28 GMT
• Title: P-Flow: Prompting Visual Effects Generation
• Abstract summary: We propose P-Flow, a training-free framework for customizing dynamic visual effects in video generation without modifying the underlying model.<n>P-Flow performs test-time prompt optimization, refining prompts based on the discrepancy between the visual effects of the reference video and the generated output.<n>Experiments demonstrate that P-Flow achieves high-fidelity and diverse visual effect customization and outperforms other models on both text-to-video and image-to-video generation tasks.
• Score: 56.523238949603325
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recent advancements in video generation models have significantly improved their ability to follow text prompts. However, the customization of dynamic visual effects, defined as temporally evolving and appearance-driven visual phenomena like object crushing or explosion, remains underexplored. Prior works on motion customization or control mainly focus on low-level motions of the subject or camera, which can be guided using explicit control signals such as motion trajectories. In contrast, dynamic visual effects involve higher-level semantics that are more naturally suited for control via text prompts. However, it is hard and time-consuming for humans to craft a single prompt that accurately specifies these effects, as they require complex temporal reasoning and iterative refinement over time. To address this challenge, we propose P-Flow, a novel training-free framework for customizing dynamic visual effects in video generation without modifying the underlying model. By leveraging the semantic and temporal reasoning capabilities of vision-language models, P-Flow performs test-time prompt optimization, refining prompts based on the discrepancy between the visual effects of the reference video and the generated output. Through iterative refinement, the prompts evolve to better induce the desired dynamic effect in novel scenes. Experiments demonstrate that P-Flow achieves high-fidelity and diverse visual effect customization and outperforms other models on both text-to-video and image-to-video generation tasks. Code is available at https://github.com/showlab/P-Flow.

Related papers

• Motion Attribution for Video Generation [97.2515042185441]
  We present Motive, a motion-centric, gradient-based data attribution framework.<n>We use it to study which fine-tuning clips improve or degrade temporal dynamics.<n>To our knowledge, this is the first framework to attribute motion rather than visual appearance in video generative models.
  arXiv  Detail & Related papers  (2026-01-13T18:59:09Z)
• Tuning-free Visual Effect Transfer across Videos [91.93897438317397]
  RefVFX is a framework that transfers complex temporal effects from a reference video onto a target video or image in a feed-forward manner.<n>We introduce a large-scale dataset of triplets, where each triplet consists of a reference effect video, an input image or video, and a corresponding output video.<n>We show that RefVFX produces visually consistent and temporally coherent edits, generalizes across unseen effect categories, and outperforms prompt-only baselines in both quantitative metrics and human preference.
  arXiv  Detail & Related papers  (2026-01-12T18:59:32Z)
• PanFlow: Decoupled Motion Control for Panoramic Video Generation [52.47902086091194]
  PanFlow is a novel approach that exploits the spherical nature of panoramas to decouple the highly dynamic camera rotation from the input optical flow condition.<n>To support effective training, we curate a large-scale, motion-rich panoramic video dataset with frame-level pose and flow annotations.
  arXiv  Detail & Related papers  (2025-11-30T11:03:31Z)
• Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising [23.044483059783143]
  Diffusion-based video generation can create realistic videos, yet existing image- and text-based conditioning fails to offer precise motion control.<n>We introduce Time-to-Move (TTM), a training-free, plug-and-play framework for motion- and appearance-controlled video generation.
  arXiv  Detail & Related papers  (2025-11-09T22:47:50Z)
• SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation [56.90807453045657]
  SynMotion is a motion-customized video generation model that jointly leverages semantic guidance and visual adaptation.<n>At the semantic level, we introduce the dual-em semantic comprehension mechanism which disentangles subject and motion representations.<n>At the visual level, we integrate efficient motion adapters into a pre-trained video generation model to enhance motion fidelity and temporal coherence.
  arXiv  Detail & Related papers  (2025-06-30T10:09:32Z)
• Motion Prompting: Controlling Video Generation with Motion Trajectories [57.049252242807874]
  We train a video generation model conditioned on sparse or dense video trajectories.<n>We translate high-level user requests into detailed, semi-dense motion prompts.<n>We demonstrate our approach through various applications, including camera and object motion control, "interacting" with an image, motion transfer, and image editing.
  arXiv  Detail & Related papers  (2024-12-03T18:59:56Z)
• Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model [17.98911328064481]
  Co-speech gestures can achieve superior visual effects in human-machine interaction. We present a novel motion-decoupled framework to generate co-speech gesture videos. Our proposed framework significantly outperforms existing approaches in both motion and video-related evaluations.
  arXiv  Detail & Related papers  (2024-04-02T11:40:34Z)
• FLAME: Free-form Language-based Motion Synthesis & Editing [17.70085940884357]
  We propose a diffusion-based motion synthesis and editing model named FLAME. FLAME can generate high-fidelity motions well aligned with the given text. It can edit the parts of the motion, both frame-wise and joint-wise, without any fine-tuning.
  arXiv  Detail & Related papers  (2022-09-01T10:34:57Z)

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.