mlsanityData to 7 Oct 2026

Adaptive Routing of Text-to-Image Generation Requests Between Large Cloud Model and Light-Weight Edge Model

arXiv 2411.13787 ↗First posted 21 Nov 2024cs.CV cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Large text-to-image models demonstrate impressive generation capabilities; however, their substantial size necessitates expensive cloud servers for deployment. Conversely, light-weight models can be deployed on edge devices at lower cost but often with inferior generation quality for complex user prompts. To strike a balance between performance and cost, we propose a routing framework, called RouteT2I, which dynamically selects either the large cloud model or the light-weight edge model for each user prompt. Since generated image quality is challenging to measure and compare directly, RouteT2I establishes multi-dimensional quality metrics, particularly, by evaluating the similarity between the generated images and both positive and negative texts that describe each specific quality metric. RouteT2I then predicts the expected quality of the generated images by identifying key tokens in the prompt and comparing their impact on the quality. RouteT2I further introduces the Pareto relative superiority to compare the multi-metric quality of the generated images. Based on this comparison and predefined cost constraints, RouteT2I allocates prompts to either the edge or the cloud. Evaluation reveals that RouteT2I significantly reduces the number of requesting large cloud model while maintaining high-quality image generation.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 34 of its 46 references that are in the map. First posted on arXiv 21 Nov 2024.

Builds on

34 of 46 references.

References · 34

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  6. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  7. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  8. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  9. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  10. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  11. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,163
  12. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
22 more
  1. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  2. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 847
  3. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  4. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  5. 2023Adversarial Diffusion Distillationcited by 741
  6. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 633
  7. 2022Mixture-of-Experts with Expert Choice Routingcited by 611
  8. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  9. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 354
  10. 2023Q-Diffusion: Quantizing Diffusion Modelscited by 266
  11. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227
  12. 2024RouterBench: A Benchmark for Multi-LLM Routing Systemcited by 222
  13. 2023Large Language Model Routing with Benchmark Datasetscited by 166
  14. 2023Holistic Evaluation of Text-To-Image Modelscited by 160
  15. 2023Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Modelscited by 141
  16. 2023Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoningcited by 140
  17. 2023Iterative Prompt Learning for Unsupervised Backlit Image Enhancementcited by 107
  18. 2024Learning Multi-dimensional Human Preference for Text-to-Image Generationcited by 102
  19. 2023Temporal Dynamic Quantization for Diffusion Modelscited by 81
  20. 2024LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insightscited by 65
  21. 2024MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantizationcited by 42
  22. 2023Mixture of Tokens: Continuous MoE through Cross-Example Aggregationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2026GenRouter: Unified Workflow Routing for Agentic Image Generationcited by 4
  2. 2025Collaborative Learning of On-Device Small Model and Cloud-Based Large Model: Advances and Future Directionscited by 2