Pith. sign in

REVIEW 11 cited by

STAR: Scale-wise Text-conditioned AutoRegressive image generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.10797 v4 pith:DI3O6WO5 submitted 2024-06-16 cs.CV

Xiaoxiao Ma , Mohan Zhou , Tao Liang , Yalong Bai , Tiejun Zhao , Biye Li , Huaian Chen , Yi Jin This is my paper
classification cs.CV
keywords generationstarauto-regressiveimagesamplingtimesacrossdetails
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We introduce STAR, a text-to-image model that employs a scale-wise auto-regressive paradigm. Unlike VAR, which is constrained to class-conditioned synthesis for images up to 256$\times$256, STAR enables text-driven image generation up to 1024$\times$1024 through three key designs. First, we introduce a pre-trained text encoder to extract and adopt representations for textual constraints, enhancing details and generalizability. Second, given the inherent structural correlation across different scales, we leverage 2D Rotary Positional Encoding (RoPE) and tweak it into a normalized version, ensuring consistent interpretation of relative positions across token maps and stabilizing the training process. Third, we observe that simultaneously sampling all tokens within a single scale can disrupt inter-token relationships, leading to structural instability, particularly in high-resolution generation. To address this, we propose a novel stable sampling method that incorporates causal relationships into the sampling process, ensuring both rich details and stable structures. Compared to previous diffusion models and auto-regressive models, STAR surpasses existing benchmarks in fidelity, text-image consistency, and aesthetic quality, requiring just 2.21s for 1024$\times$1024 images on A100. This highlights the potential of auto-regressive methods in high-quality image synthesis, offering new directions for the text-to-image generation.

Discussion (0). Sign in to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Next-Scale Autoregressive Models for Text-to-Motion Generation

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    Next-scale autoregressive modeling with cross-scale and in-scale refinements produces SOTA text-to-motion generation by enforcing coarse-to-fine causal hierarchy.

  2. Progressive Checkerboards for Autoregressive Multiscale Image Generation

    cs.CV 2026-02 conditional novelty 6.0 of 10

    A balanced multiscale checkerboard sampling order for autoregressive image generation allows large scale-up factors without quality loss, because only the total number of serial steps matters.

  3. SpectralAR: Spectral Autoregressive Visual Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    An autoregressive image generator that tokenizes images in the DCT frequency domain into nested 1D spectral sequences and generates them coarse-to-fine, reaching 3.02 gFID with 64 tokens on ImageNet-1K.

  4. Multi-scale Image Super Resolution with a Single Auto-Regressive Model

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A single auto-regressive model with hierarchical tokenization and a preference-based loss super-resolves images at multiple scale factors with competitive quality.

  5. HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    HMAR is an image generator that builds each resolution scale from the previous scale and refines it with masked prediction, matching or improving ImageNet FID/IS versus VAR with faster training and inference.

  6. FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models

    cs.CV 2025-12 conditional novelty 5.0 of 10

    Stage-aware pruning of late generation steps, using random projection and cached-feature restoration, speeds up VAR text-to-image models by up to 3.4x with minimal quality loss.

  7. DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer

    cs.CV 2025-07 conditional novelty 5.0 of 10

    DC-AR generates 512x512 images in 12 masked autoregressive steps plus 20 diffusion refinement steps, using a 32x compressed 2D tokenizer, and reports gFID 5.49 on MJHQ-30K.

  8. CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation

    cs.CV 2025-06 conditional novelty 5.0 of 10

    CycleVAR adapts a pretrained visual autoregressive model to unpaired image translation using softmax-relaxed quantization and source-token prefixes, achieving FID scores competitive with CycleGAN-Turbo.

  9. Marrying Autoregressive Transformer and Diffusion with Multi-Reference Autoregression

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A hybrid image generator that uses an autoregressive transformer as an encoder and a diffusion model as a decoder reaches FID 1.42 on ImageNet 256x256, with an iterative multi-reference mode that improves quality over...

  10. Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression

    cs.LG 2025-05 conditional novelty 5.0 of 10

    ScaleKV cuts KV cache memory for Visual Autoregressive text-to-image generation to 10% by classifying layers as drafters or refiners per scale and pruning low-attention tokens while keeping benchmark scores nearly unchanged.

  11. High-Fidelity Functional Ultrasound Reconstruction via A Visual Auto-Regressive Framework

    eess.IV 2025-05 reject novelty 4.0 of 10

    UltraVAR, a visual auto-regressive augmenter for functional ultrasound, reports downstream classification gains that are not proven to come from generation quality.

Pith tools