Alternatives and similar repositories for FastVAR

Users that are interested in FastVAR are comparing it to the libraries listed below

• czg1225 / CoDe
  [CVPR 2025] CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient
  ☆108Updated 4 months ago
• bytetriper / LM4LV
  🔥Official PyTorch implementation for "LM4LV: A Frozen Large Language Model for Low-level Vision Tasks".
  ☆54Updated last year
• EternalEvan / FlowIE
  This repository contains the official implementation of "FlowIE: Efficient Image Enhancement via Rectified Flow"
  ☆142Updated last year
• MiracleDance / CAR
  CAR: Controllable AutoRegressive Modeling for Visual Generation
  ☆128Updated last year
• Zehong-Ma / DeCo
  Official repository for “DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation”
  ☆172Updated last month
• CVL-UESTC / Internal-Guidance
  Guiding a Diffusion Transformer with the Internal Dynamics of Itself (IG)
  ☆55Updated last month
• csguoh / ReFIR
  [NeurIPS2024] Overcome hallucination of diffusion restoration models.
  ☆64Updated 9 months ago
• gudaochangsheng / MaskUnet
  [CVPR 2025] Official PyTorch implementation of Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability
  ☆32Updated 7 months ago
• nonwhy / PURE
  [ICCV2025] PyTorch implementation of "Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal …
  ☆115Updated 2 weeks ago
• Adam-duan / DiT4SR
  [ICCV 2025] This is the official PyTorch codes for the paper: "DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution…
  ☆202Updated last month
• quyp2000 / VARSR
  [ICML2025] VARSR: Visual Autogressive Modeling for Image Super Resolution
  ☆164Updated 9 months ago
• TianheWu / VisualQuality-R1
  [NeurIPS 2025 Spotlight] VisualQuality-R1 is the first open-sourced NR-IQA model can accurately describe and rate the image quality.
  ☆153Updated 3 months ago
• VainF / TinyFusion
  [CVPR 2025 Highlight] TinyFusion: Diffusion Transformers Learned Shallow
  ☆159Updated 2 months ago
• lxa9867 / ControlVAR
  This is the official implementation for ControlVAR.
  ☆125Updated last year
• qhfan / MALA
  [ICCV2025 highlight]Rectifying Magnitude Neglect in Linear Attention
  ☆57Updated 6 months ago
• Davinci-XLab / STAR-T2I
  Official implementation of "STAR: Scale-wise Text-to-image generation via Auto-Regressive representations"
  ☆43Updated 11 months ago
• hp-l33 / ARPG
  [ICLR 2026] Autoregressive Image Generation with Randomized Parallel Decoding
  ☆86Updated 2 weeks ago
• zhiyuanyou / DeQA-Score
  [CVPR 2025] Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution
  ☆220Updated last month
• QinpengCui / DoSSR
  [NeurIPS 2024]Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs
  ☆37Updated last year
• Martinser / REG
  [NeurIPS 2025 Oral] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
  ☆244Updated 4 months ago
• NUS-HPC-AI-Lab / Dynamic-Diffusion-Transformer
  ☆92Updated 10 months ago
• shallowdream204 / DiCo
  [NeurIPS 2025 Spotlight] DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling
  ☆61Updated 3 months ago
• qianlong0502 / DKDM
  [CVPR-2025] Official implementations of "DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture".
  ☆33Updated 9 months ago
• vvvvvjdy / SRA
  [ICLR 2026] Self-Representation Alignment for Diffusion Transformers (SRA)
  ☆110Updated 2 weeks ago
• forever208 / DCTdiff
  [ICML 2025] Official code for the paper 'DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space'
  ☆77Updated 6 months ago
• NVlabs / HMAR
  [CVPR 2025] HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation
  ☆61Updated 7 months ago
• yuanzhi-zhu / OFTSR
  [ICLR2026] "OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs"
  ☆37Updated this week
• lwq20020127 / Q-Insight
  Q-Insight is open-sourced at https://github.com/bytedance/Q-Insight. This repository will not receive further updates.
  ☆142Updated 8 months ago
• xtudbxk / GPSToken
  The official code for paper "GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation"
  ☆48Updated 4 months ago
• xie-lab-ml / Weak-to-Strong-Diffusion-with-Reflection
  [ICLR2026] The official code of "Weak-to-Strong Diffusion with Reflection".
  ☆55Updated 2 weeks ago