REVIEW 9 cited by
STAR: Scale-wise Text-conditioned AutoRegressive image generation
Not yet reviewed by Pith; the record is open.
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
STAR: Scale-wise Text-conditioned AutoRegressive image generation
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.
Forward citations
Cited by 9 Pith papers
-
Hierarchical Image Tokenization for Multi-Scale Image Super Resolution
HIT with token overlap plus DPO regularization lets a 300M-param VAR model deliver state-of-the-art multi-scale ISR in one forward pass without external data.
-
VARestorer: One-Step VAR Distillation for Real-World Image Super-Resolution
VARestorer converts a text-to-image VAR model into a fast one-step real-world image super-resolution model via distribution matching distillation and pyramid image conditioning.
-
Prompt-Guided Image Editing with Masked Logit Nudging in Visual Autoregressive Models
Masked Logit Nudging aligns visual autoregressive model logits with source token maps under target prompts inside cross-attention masks, delivering top image editing results on PIE benchmarks and strong reconstruction...
-
Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation
GAR-Font is a global-aware autoregressive framework for multimodal few-shot font generation that adds global tokenization, a language-style adapter, and post-refinement to improve style coherence over patch-based methods.
-
Channel-wise Vector Quantization
CVQ replaces patch-wise vector quantization with channel-wise quantization of feature maps, enabling a next-channel autoregressive model that reports 100% codebook utilization and text-to-image scores of DPG 86.7 and ...
-
Next-Scale Autoregressive Models for Text-to-Motion Generation
Next-scale autoregressive modeling with cross-scale and in-scale refinements produces SOTA text-to-motion generation by enforcing coarse-to-fine causal hierarchy.
-
Next-Scale Autoregressive Models for Text-to-Motion Generation
MoScale introduces a hierarchical next-scale autoregressive framework for text-to-motion generation that achieves state-of-the-art performance by refining motions from coarse to fine temporal resolutions.
-
Progressive Checkerboards for Autoregressive Multiscale Image Generation
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.
-
FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.