# ScalablePromptus: Scalable and High-Fidelity Prompt-Based Video Streaming

arXiv: https://arxiv.org/abs/2607.26106 · HTML: https://mlsanity.com/paper/2607.26106/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 12 of 12)

- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing](https://mlsanity.com/paper/2011.15126/) (2020)
- [Neural Video Compression with Diverse Contexts](https://mlsanity.com/paper/2302.14402/) (2023)
- [Neural Video Compression with Feature Modulation](https://mlsanity.com/paper/2402.17414/) (2024)
- [Video Compression With Rate-Distortion Autoencoders](https://mlsanity.com/paper/1908.05717/) (2019)
- [Learning Ordered Representations with Nested Dropout](https://mlsanity.com/paper/1402.0915/) (2014)
- [CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streaming](https://mlsanity.com/paper/2211.08428/) (2022)
- [Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP](https://mlsanity.com/paper/2406.17639/) (2024)
- [Reparo: Loss-Resilient Generative Codec for Video Conferencing](https://mlsanity.com/paper/2305.14135/) (2023)
- [Boosting neural video codecs by exploiting hierarchical redundancy](https://mlsanity.com/paper/2208.04303/) (2022)
- [Addressing degeneracies in latent interpolation for diffusion models](https://mlsanity.com/paper/2505.07481/) (2025)

## Abstract (arXiv)

Prompt-based video streaming transmits compact semantic prompts instead of pixel-level content for generative reconstruction, enabling ultra-low-bitrate communication. However, the state-of-the-art Promptus framework is vulnerable to network fluctuation, where partially received prompts lead to catastrophic quality collapse. We propose ScalablePromptus, which enhances Promptus with semantic and color-aware prompt inversion, spherical linear interpolation for intermediate frames, and--most critically--a dropout training strategy that produces rank-ordered prompt representations. This allows the receiver to reconstruct meaningful video from arbitrarily truncated prompts without any adaptation. Under stable networks, ScalablePromptus achieves modest quality gains. Under lossy conditions, it reduces the performance degradation caused by truncation by 82%-95% compared to the baseline, making prompt-based streaming robust enough for real-world deployment.