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

arXiv: https://arxiv.org/abs/2607.04553 · HTML: https://mlsanity.com/paper/2607.04553/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 5 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model](https://mlsanity.com/paper/2211.02001/) (2022)
- [Seedance 1.0: Exploring the Boundaries of Video Generation Models](https://mlsanity.com/paper/2506.09113/) (2025)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [Power Hungry Processing: Watts Driving the Cost of AI Deployment?](https://mlsanity.com/paper/2311.16863/) (2023)
- [How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference](https://mlsanity.com/paper/2505.09598/) (2025)
- [Energy Considerations of Large Language Model Inference and Efficiency Optimizations](https://mlsanity.com/paper/2504.17674/) (2025)
- [Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis](https://mlsanity.com/paper/2411.01156/) (2024)
- [Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference](https://mlsanity.com/paper/2503.08311/) (2025)
- [Measuring the environmental impact of delivering AI at Google Scale](https://mlsanity.com/paper/2508.15734/) (2025)
- [Holistically Evaluating the Environmental Impact of Creating Language Models](https://mlsanity.com/paper/2503.05804/) (2025)
- [Life-Cycle Emissions of AI Hardware: A Cradle-To-Grave Approach and Generational Trends](https://mlsanity.com/paper/2502.01671/) (2025)
- [Benchmarking Energy Efficiency of Large Language Models Using vLLM](https://mlsanity.com/paper/2509.08867/) (2025)
- [Video Killed the Energy Budget: Characterizing the Latency and Power Regimes of Open Text-to-Video Models](https://mlsanity.com/paper/2509.19222/) (2025)
- [Eliminating VAE for Fast and High-Resolution Generative Detail Restoration](https://mlsanity.com/paper/2602.10630/) (2026)

## Abstract (arXiv)

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.