# Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

arXiv: https://arxiv.org/abs/2410.13863 · HTML: https://mlsanity.com/paper/2410.13863/

## Key facts

- Cited by 147 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 58 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Builds on (most cited first, 30 of 49)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)

## Built on by (most cited first, 30 of 147)

- [Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis](https://mlsanity.com/paper/2412.04431/) (2024)
- [Diffusion Transformers with Representation Autoencoders](https://mlsanity.com/paper/2510.11690/) (2025)
- [HPSv3: Towards Wide-Spectrum Human Preference Score](https://mlsanity.com/paper/2508.03789/) (2025)
- [WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2503.07265/) (2025)
- [Randomized Autoregressive Visual Generation](https://mlsanity.com/paper/2411.00776/) (2024)
- [Long-Context Autoregressive Video Modeling with Next-Frame Prediction](https://mlsanity.com/paper/2503.19325/) (2025)
- [Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities](https://mlsanity.com/paper/2505.02567/) (2025)
- [RandAR: Decoder-only Autoregressive Visual Generation in Random Orders](https://mlsanity.com/paper/2412.01827/) (2024)
- [PixNerd: Pixel Neural Field Diffusion](https://mlsanity.com/paper/2507.23268/) (2025)
- [Harmonizing Visual Representations for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2503.21979/) (2025)
- [TIIF-Bench: How Does Your T2I Model Follow Your Instructions?](https://mlsanity.com/paper/2506.02161/) (2025)
- [DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation](https://mlsanity.com/paper/2511.19365/) (2025)
- [GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation](https://mlsanity.com/paper/2504.02782/) (2025)
- [DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation](https://mlsanity.com/paper/2502.03930/) (2025)
- [NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale](https://mlsanity.com/paper/2508.10711/) (2025)
- [SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer](https://mlsanity.com/paper/2412.10958/) (2024)
- [UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens](https://mlsanity.com/paper/2505.14671/) (2025)
- [Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model](https://mlsanity.com/paper/2505.23606/) (2025)
- [Unified Autoregressive Visual Generation and Understanding with Continuous Tokens](https://mlsanity.com/paper/2503.13436/) (2025)
- [Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens](https://mlsanity.com/paper/2501.07730/) (2025)
- [InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation](https://mlsanity.com/paper/2511.04675/) (2025)
- [Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads](https://mlsanity.com/paper/2412.00127/) (2024)
- [VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model](https://mlsanity.com/paper/2501.12327/) (2025)
- [CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning](https://mlsanity.com/paper/2505.17006/) (2025)
- [Autoregressive Models in Vision: A Survey](https://mlsanity.com/paper/2411.05902/) (2024)
- [Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling](https://mlsanity.com/paper/2507.17801/) (2025)
- [Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis](https://mlsanity.com/paper/2412.01819/) (2024)
- [FlowTok: Flowing Seamlessly Across Text and Image Tokens](https://mlsanity.com/paper/2503.10772/) (2025)
- [STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis](https://mlsanity.com/paper/2506.06276/) (2025)
- [Taming Teacher Forcing for Masked Autoregressive Video Generation](https://mlsanity.com/paper/2501.12389/) (2025)

## Abstract (arXiv)

Scaling up autoregressive models in vision has not proven as beneficial as in large language models. In this work, we investigate this scaling problem in the context of text-to-image generation, focusing on two critical factors: whether models use discrete or continuous tokens, and whether tokens are generated in a random or fixed raster order using BERT- or GPT-like transformer architectures. Our empirical results show that, while all models scale effectively in terms of validation loss, their evaluation performance -- measured by FID, GenEval score, and visual quality -- follows different trends. Models based on continuous tokens achieve significantly better visual quality than those using discrete tokens. Furthermore, the generation order and attention mechanisms significantly affect the GenEval score: random-order models achieve notably better GenEval scores compared to raster-order models. Inspired by these findings, we train Fluid, a random-order autoregressive model on continuous tokens. Fluid 10.5B model achieves a new state-of-the-art zero-shot FID of 6.16 on MS-COCO 30K, and 0.69 overall score on the GenEval benchmark. We hope our findings and results will encourage future efforts to further bridge the scaling gap between vision and language models.