mlsanityData to 7 Oct 2026

1.58-bit FLUX

arXiv 2412.18653 ↗First posted 24 Dec 2024cs.CV cs.AI cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

We present 1.58-bit FLUX, the first successful approach to quantizing the state-of-the-art text-to-image generation model, FLUX.1-dev, using 1.58-bit weights (i.e., values in {-1, 0, +1}) while maintaining comparable performance for generating 1024 x 1024 images. Notably, our quantization method operates without access to image data, relying solely on self-supervision from the FLUX.1-dev model. Additionally, we develop a custom kernel optimized for 1.58-bit operations, achieving a 7.7x reduction in model storage, a 5.1x reduction in inference memory, and improved inference latency. Extensive evaluations on the GenEval and T2I Compbench benchmarks demonstrate the effectiveness of 1.58-bit FLUX in maintaining generation quality while significantly enhancing computational efficiency.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 31 of its 63 references that are in the map. First posted on arXiv 24 Dec 2024.

Builds on

31 of 63 references.

References · 31

  1. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  2. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  3. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  4. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  5. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  6. 2019Learned Step Size Quantizationcited by 604
  7. 2021A White Paper on Neural Network Quantizationcited by 453
  8. 2023OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Modelscited by 403
  9. 2023LLM-QAT: Data-Free Quantization Aware Training for Large Language Modelscited by 320
  10. 2024The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bitscited by 289
  11. 2023SqueezeLLM: Dense-and-Sparse Quantizationcited by 285
  12. 2024Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generationcited by 249
19 more
  1. 2024QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Servingcited by 200
  2. 2023BitNet: Scaling 1-bit Transformers for Large Language Modelscited by 175
  3. 2024SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Modelscited by 161
  4. 2024EfficientQAT: Efficient Quantization-Aware Training for Large Language Modelscited by 123
  5. 2024Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Modelscited by 113
  6. 2024ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationcited by 110
  7. 2024Q-DiT: Accurate Post-Training Quantization for Diffusion Transformerscited by 91
  8. 2023EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Modelscited by 77
  9. 2024PTQ4DiT: Post-training Quantization for Diffusion Transformerscited by 77
  10. 2024MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantizationcited by 42
  11. 2024BitsFusion: 1.99 bits Weight Quantization of Diffusion Modelcited by 37
  12. 2024EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Modelscited by 23
  13. 2023Efficient Quantization Strategies for Latent Diffusion Modelscited by 16
  14. 2024HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantizationcited by 15
  15. 2024Timestep-Aware Correction for Quantized Diffusion Modelscited by 13
  16. 2024VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformerscited by 12
  17. 2024PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantizationcited by 11
  18. 20241-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUscited by 9
  19. 2024Low-Bitwidth Floating Point Quantization for Efficient High-Quality Diffusion Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 24; 2026: 7.

31 papers.

Sort:

By area:

  1. 2025Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generationcited by 71
  2. 2025Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokenscited by 48
  3. 2025ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantizationcited by 44
  4. 2025Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generationcited by 38
  5. 2025Training-Free Efficient Video Generation via Dynamic Token Carvingcited by 33
  6. 2025FlowTok: Flowing Seamlessly Across Text and Image Tokenscited by 31
  7. 2025From One to More: Contextual Part Latents for 3D Generationcited by 26
  8. 2025Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generationcited by 16
  9. 2025Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformerscited by 13
  10. 2025Text-to-Image Diffusion Models Cannot Count, and Prompt Refinement Cannot Helpcited by 12
  11. 2025Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Modelscited by 12
  12. 2025OmniPSD: Layered PSD Generation with Diffusion Transformercited by 11
19 more
  1. 2026SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Modelscited by 10
  2. 2026A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokenscited by 9
  3. 2025Deeply Supervised Flow-Based Generative Modelscited by 8
  4. 2025Diffusion Classifiers Understand Compositionality, but Conditions Applycited by 7
  5. 2025HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generationcited by 7
  6. 2025Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Modelscited by 6
  7. 2026Frequency-Aware Flow Matching for High-Quality Image Generationcited by 6
  8. 2025Trans-Adapter: A Plug-and-Play Framework for Transparent Image Inpaintingcited by 5
  9. 2025DFVEdit: Conditional Delta Flow Vector for Zero-shot Video Editingcited by 3
  10. 2025Investigation of Accuracy and Bias in Face Recognition Trained with Synthetic Datacited by 2
  11. 2025DeCoT: Decomposing Complex Instructions for Enhanced Text-to-Image Generation with Large Language Modelscited by 1
  12. 2025IRIS: Intrinsic Reward Image Synthesiscited by 1
  13. 2025WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokenscited by 1
  14. 2026When Do Diffusion Models learn to Generate Multiple Objects?cited by 1
  15. 2025Ternarization of Vision Language Models for use on edge devicescited by 0
  16. 2025ID-Card Synthetic Generation: Toward a Simulated Bona fide Datasetcited by 0
  17. 2026Synergizing Understanding and Generation with Interleaved Analyzing-Drafting Thinkingcited by 0
  18. 2026RT-Lynx: Putting GEMM Sparsity in the Right Place for Diffusion Modelscited by 0
  19. 2026Realizing Native INT8 Compute for Diffusion Transformers on Consumer GPUs: A Fused INT8 GEMM Kernel for Ideogram 4.0cited by 0