P-Flow: Prompting Visual Effects Generation

Rui Zhao; Mike Zheng Shou

cs.CVMar 23, 2026

P-Flow: Prompting Visual Effects Generation

Authors: Rui Zhao, Mike Zheng Shou

Organizations: Show Lab, National University of Singapore

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.

Figures & tables

Figure 1: It is hard for humans to craft text prompts that precisely control video generation models to generate desired visual effects across diverse scenes, while P - F l o w automatically refines prompts to achieve consistent and realistic visual effects.

Figure 2: Overview of the proposed P - F l o w framework.

	Image-to-Video			Text-to-Video			Overall
	FID-VID $\downarrow$	FVD $\downarrow$	Dyn. Degree $\uparrow$	FID-VID $\downarrow$	FVD $\downarrow$	Dyn. Degree $\uparrow$	FID-VID $\downarrow$	FVD $\downarrow$	Dyn. Degree $\uparrow$
Wan 2.1 [ 69 ]	34.62	994.70	0.33	42.32	1535.43	0.28	38.47	1265.07	0.31
HunyuanVideo [ 32 ]	36.53	1169.9	0.51	38.35	1362.35	0.34	37.44	1266.13	0.43
VFX Creator ( Training-Based ) [ 44 ]	29.92	752.95	0.63	–	–	–	–	–	–
Wan 2.1 + HF ( Training-Free )	33.12	989.42	0.54	42.21	1632.10	0.59	75.33	1310.76	0.57
HunyuanVideo + HF ( Training-Free )	33.85	1035.49	0.70	36.54	1266.79	0.62	35.20	1151.14	0.66

Table 1: Quantitative comparisons for both image-to-video and text-to-video generation settings. Note that VFX Creator supports only image-to-video generation.

Figure 3: Qualitative comparison on image-to-video generation with different visual effects. The prompts shown beneath each row represent the actual input to each model. As VFX Creator is optimized for short phrase inputs, such prompts are provided to ensure a fair and consistent evaluation.

Model 1	Preference (Model 1 V.S. Model 2)	Model 2
P - F l o w -I2V	80% V.S. 20%	Wan 2.1-I2V
P - F l o w -I2V	84% V.S. 16%	HunyuanVideo-I2V
P - F l o w -I2V	58% V.S. 42%	VFX Creator
P - F l o w -T2V	75% V.S. 25%	Wan 2.1-T2V
P - F l o w -T2V	81% V.S. 19%	HunyuanVideo-T2V

Table 2: Human evaluation results (%) comparing P - F l o w against baseline models in Image-to-Video (I2V) and Text-to-Video (T2V) generation. Note: Model order was randomized during evaluation.

Figure 4: Qualitative comparison on image-to-video generation with different visual effects. The prompts shown beneath each row represent the actual input to each model.

Figure 5: Optimization trajectory of P - F l o w . Starting from a simple base prompt, P - F l o w iteratively refines the text prompt based on the visual feedback (we showcase the iteration 1 → 3 → 5), leading to progressively more accurate alignment between the generated video and the target “squish” visual effect.

Modules			Image-to-Video			Text-to-Video			Overall
Noise-Enhance	Logic-Context	Visual-Context (i-1)	FID-VID $\downarrow$	FVD $\downarrow$	Dyn. Degree $\uparrow$	FID-VID $\downarrow$	FVD $\downarrow$	Dyn. Degree $\uparrow$	FID-VID $\downarrow$	FVD $\downarrow$	Dyn. Degree $\uparrow$
✗	✗	✗	33.42	1089.23	0.64	39.85	1321.70	0.61	36.64	1205.47	0.63
✓	✗	✗	32.80	961.78	0.69	36.74	1182.42	0.66	34.77	1072.10	0.68
✓	✗	✓	30.45	861.52	0.83	34.05	1044.67	0.78	32.25	953.10	0.81
✓	✓	✓	29.32	784.51	0.94	32.93	980.75	0.87	31.13	882.63	0.91

Table 3: Ablation study of P - F l o w on both image-to-video and text-to-video generation.

Setting	FID-VID $\downarrow$	FVD $\downarrow$	Dyn. Degree $\uparrow$
w/o SVD Projection ( $\rho_{s}=0.0,\rho_{m}=1.0$ )	33.25	1052.80	0.58
Random Noise Only ( $\alpha=0.0$ )	32.74	923.67	0.73
Enhanced Noise ( $\alpha=0.001,\rho_{s}=0.1,\rho_{m}=0.9$ )	29.32	784.51	0.94
Enhanced Noise ( $\alpha=0.01,\rho_{s}=0.1,\rho_{m}=0.9$ )	29.21	803.35	0.88

Table 4: Analysis of noise prior enhancement components.

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 6: Image-to-Video Generation Results.

Figure 7: Text-to-Video Generation Results.

Controllable Video Generation

Controllable video generation steers how videos look, move, and change over time using user-provided instructions and structured controls.

See all 300 papers

EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation
Mar 6, 2026Shiyuan Yang, Ruihuang Li, Jiale Tao +3Controllable Video Generation Video-Reference Video Generation
Tencent Hunyuan · City University of Hong Kong
Custom Forcing: Training-Free Subject Customization for Autoregressive Video Generation
Oct 2, 2026Yunseung Ok, Hyunsoo Kim, Minseo Kim +1Identity-Preserving Video Generation Streaming Video Generation
Kyung Hee University · The University of Texas at Austin
Diverse Motion Customization via Control-based Dynamic Optimization
Oct 6, 2026Youngyoon Choi, Kihyun Kim, Jeongwoo Shin +1Video Diffusion Models Controllable Video Generation
Seoul National University · AIM Intelligence

Mar 6, 2026J/K move · Enter open · S save

EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation

Shiyuan Yang, Ruihuang Li, Jiale Tao, Shuai Shao+2

Tencent Hunyuan · City University of Hong Kong

Controllable Video Generation Video-Reference Video Generation Video Diffusion Models

Open paper AskPDF arXiv

Visual effects (VFX) are essential for enhancing the expressiveness and creativity of video content, yet producing high-quality effects typically requires expert knowledge and costly production pipelines. Existing AIGC systems face significant challenges in VFX generation due to the scarcity of effect-specific data and the inherent difficulty of modeling supernatural or stylized effects. Moreover, these approaches often require per-effect fine-tuning, which severely limits their scalability and generalization to novel VFX. In this work, we present EffectMaker, a unified reasoning-generation framework that enables reference-based VFX customization. EffectMaker employs a multimodal large language model to interpret high-level effect semantics and reason about how they should adapt to a target subject, while a diffusion transformer leverages in-context learning to capture fine-grained visual cues from reference videos. These two components form a semantic-visual dual-path guidance mechanism that enables accurate, controllable, and effect-consistent synthesis without per-effect fine-tuning. Furthermore, we construct EffectData, the largest high-quality synthetic dataset containing 130k videos across 3k VFX categories, to improve generalization and scalability. Experiments show that EffectMaker achieves superior visual quality and effect consistency over state-of-the-art baselines, offering a scalable and flexible paradigm for customized VFX generation. Project page: https://effectmaker.github.io

Abstract

Controllable Video Generation

Explore similar work

EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation

Custom Forcing: Training-Free Subject Customization for Autoregressive Video Generation

Diverse Motion Customization via Control-based Dynamic Optimization