Lights, Camera, Carbon: Architectural Scaling Laws for Video Generation Energy Consumption

• URL: http://arxiv.org/abs/2607.04553v1
• Date: Sun, 05 Jul 2026 23:58:29 GMT
• Title: Lights, Camera, Carbon: Architectural Scaling Laws for Video Generation Energy Consumption
• Abstract summary: We present a framework for estimating the energy consumption of text-to-video (T2V) and text-to-video-audio (T2VA) models.<n> Forward, it predicts energy from generation parameters and architectural principles; backward, it recovers architectural scaling behavior from observed inference times.<n>This approach offers a standardized, empirically and theoretically grounded framework for sustainability benchmarking across T2V models and architectures.
• Score: 4.930883100315264
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We present a bidirectional framework for estimating the energy consumption of text-to-video (T2V) and text-to-video-audio (T2VA) models from architectural first principles and observable generation parameters such as resolution and duration, requiring no access to weights, model size, or implementation details. Forward, it predicts energy from generation parameters and architectural principles; backward, it recovers architectural scaling behavior from observed inference times, with accuracy serving as a criterion for architectural validity. Building on the established compute-bound nature of video diffusion models, we demonstrate that each model's energy profile obeys theoretically derived scaling laws, decomposing into quadratic and linear terms whose coefficients directly reflect the underlying architectural complexity. Validated across six open-source models spanning 8.3B-27B parameters and three GPU configurations, this decomposition achieves below 3% MAPE across all architectures. This approach offers a standardized, empirically and theoretically grounded framework for sustainability benchmarking across T2V models and architectures.

Related papers

• CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic Materials [61.546562658308005]
  We propose QE-Catalytic-V2, a unified graph--text multimodal large language model for catalytic materials.<n>It integrates property prediction and inverse design within the same model and shared representation space.<n>Under this unified framework, QE-Catalytic-V2 can not only perform reliable property prediction but also generate and screen physically feasible CIF candidates.
  arXiv  Detail & Related papers  (2026-05-17T04:31:46Z)
• Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective [91.23306722968509]
  Generalizable feed-forward 3D reconstruction has witnessed rapid development in recent years.<n>Existing feed-forward approaches share similar high-level architectural patterns.<n>We propose a novel taxonomy centered on model design strategies that are agnostic to the output format.
  arXiv  Detail & Related papers  (2026-04-15T16:07:18Z)
• BuildMamba: A Visual State-Space Based Model for Multi-Task Building Segmentation and Height Estimation from Satellite Images [0.6773121102591491]
  BuildMamba is a unified multi-task framework designed to exploit the linear-time global modeling of visual state-space models.<n>It achieves an IoU of 0.93 and RMSE of 1.77m on DFC23 benchmark, surpassing state-of-the-art by 0.82m in height estimation.
  arXiv  Detail & Related papers  (2026-03-09T15:56:42Z)
• Learning Transient Convective Heat Transfer with Geometry Aware World Models [41.969427056765014]
  This paper introduces a geometry aware world model architecture, derived from a video generation architecture (LongVideoGAN) to learn transient physics.<n>We evaluate this approach on a 2D transient computational fluid dynamics (CFD) problem involving convective heat transfer from buoyancy-driven flow coupled to a heat flow in a solid structure.
  arXiv  Detail & Related papers  (2026-01-29T18:24:24Z)
• Energy Scaling Laws for Diffusion Models: Quantifying Compute and Carbon Emissions in Image Generation [50.21021246855702]
  We propose an adaptation of Kaplan scaling laws to predict GPU energy consumption for diffusion models based on computational complexity (FLOPs)<n>Our approach decomposes diffusion model inference into text encoding, iterative denoising, and decoding components, with the hypothesis that denoising operations dominate energy consumption due to their repeated execution across multiple inference steps.<n>Our results validate the compute-bound nature of diffusion inference and provide a foundation for sustainable AI deployment planning and carbon footprint estimation.
  arXiv  Detail & Related papers  (2025-11-21T08:12:47Z)
• Video Understanding by Design: How Datasets Shape Architectures and Insights [47.846604113207206]
  Video understanding has advanced rapidly, fueled by increasingly complex datasets and powerful architectures.<n>This survey is the first to adopt a dataset-driven perspective, showing how motion complexity, temporal span, hierarchical composition, and multimodal richness impose inductive biases that models should encode.
  arXiv  Detail & Related papers  (2025-09-11T05:06:30Z)
• Explainable Dual-Attention Tabular Transformer for Soil Electrical Resistivity Prediction: A Decision Support Framework for High-Voltage Substation Construction [0.0]
  This research introduces a novel dual-attention transformer architecture for predicting soil electrical resistivity.<n>The proposed architecture achieves superior predictive performance (Mean Absolute Percentage Error: 0.63%) compared to recent state of the art models.<n>We developes a web-based application implementing this model to provide engineers with an accessible decision support framework.
  arXiv  Detail & Related papers  (2025-03-17T04:30:32Z)
• S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video [13.510513575340106]
  Reconstructing dynamic articulated objects from a singular monocular video is challenging, requiring joint estimation of shape, motion, and camera parameters from limited views. We propose Synergistic Shape and Skeleton Optimization (S3O), a novel two-phase method that efficiently learns parametric models including visible shapes and underlying skeletons. Our experimental evaluations on standard benchmarks and the PlanetZoo dataset affirm that S3O provides more accurate 3D reconstruction, and plausible skeletons, and reduces the training time by approximately 60% compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-05-21T09:01:00Z)
• RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks [93.18404922542702]
  We present a novel video generative model designed to address long-term spatial and temporal dependencies. Our approach incorporates a hybrid explicit-implicit tri-plane representation inspired by 3D-aware generative frameworks. Our model synthesizes high-fidelity video clips at a resolution of $256times256$ pixels, with durations extending to more than $5$ seconds at a frame rate of 30 fps.
  arXiv  Detail & Related papers  (2024-01-11T16:48:44Z)
• Scaling Pre-trained Language Models to Deeper via Parameter-efficient Architecture [68.13678918660872]
  We design a more capable parameter-sharing architecture based on matrix product operator (MPO) MPO decomposition can reorganize and factorize the information of a parameter matrix into two parts. Our architecture shares the central tensor across all layers for reducing the model size.
  arXiv  Detail & Related papers  (2023-03-27T02:34:09Z)

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.