Alternatives and similar repositories for TinyFusion

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

• czg1225 / CoDe
  [CVPR 2025] CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient
  ☆108Updated 3 months ago
• NUS-HPC-AI-Lab / Dynamic-Diffusion-Transformer
  ☆91Updated 9 months ago
• hp-l33 / ARPG
  Autoregressive Image Generation with Randomized Parallel Decoding
  ☆81Updated 2 months ago
• YuqingWang1029 / PAR
  [CVPR2025 Highlight] PAR: Parallelized Autoregressive Visual Generation. https://yuqingwang1029.github.io/PAR-project
  ☆184Updated 9 months ago
• tang-bd / fuse-dit
  [CVPR 2025] Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis
  ☆129Updated 7 months ago
• byeongjun-park / DTR
  [ICLR 2024] Official pytorch implementation of "Denoising Task Routing for Diffusion Models"
  ☆24Updated last year
• vvvvvjdy / SRA
  (SRA) No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves
  ☆101Updated 5 months ago
• mit-han-lab / lpd
  Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation
  ☆80Updated 5 months ago
• Zehong-Ma / DeCo
  Official repository for “DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation”
  ☆139Updated last week
• csguoh / FastVAR
  [ICCV2025]Generate one 2K image on single 24GB 3090 GPU!
  ☆81Updated 3 months ago
• MiracleDance / CAR
  CAR: Controllable AutoRegressive Modeling for Visual Generation
  ☆127Updated last year
• lxa9867 / ControlVAR
  This is the official implementation for ControlVAR.
  ☆126Updated last year
• horseee / learning-to-cache
  [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
  ☆116Updated last year
• KlingTeam / DiffMoE
  Official PyTorch implementation of DiffMoE, TC-DiT, EC-DiT and Dense DiT
  ☆156Updated 2 months ago
• krennic999 / STAR
  STAR: Scale-wise Text-to-image generation via Auto-Regressive representations
  ☆148Updated 10 months ago
• daixiangzi / VAR-CLIP
  Implements VAR+CLIP for text-to-image (T2I) generation
  ☆146Updated 11 months ago
• Martinser / REG
  [NeurIPS 2025 Oral] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
  ☆231Updated 2 months ago
• PKU-YuanGroup / WF-VAE
  [CVPR 2025🔥] Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model
  ☆187Updated 7 months ago
• hustvl / DiG
  [CVPR 2025] DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
  ☆175Updated 9 months ago
• AdaCache-DiT / AdaCache
  Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"
  ☆163Updated last year
• ThisisBillhe / ZipAR
  [ICML 2025] This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality…
  ☆53Updated 9 months ago
• OliverRensu / xAR
  This repository includes the official implementation of our paper "Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generat…
  ☆241Updated 2 months ago
• forever208 / DCTdiff
  [ICML 2025] Official code for the paper 'DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space'
  ☆73Updated 4 months ago
• xie-lab-ml / Weak-to-Strong-Diffusion-with-Reflection
  The official code of "Weak-to-Strong Diffusion with Reflection".
  ☆55Updated 7 months ago
• hp-l33 / AiM
  Official PyTorch Implementation of "Scalable Autoregressive Image Generation with Mamba"
  ☆141Updated 11 months ago
• NVlabs / HMAR
  [CVPR 2025] HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation
  ☆59Updated 5 months ago
• LINs-lab / UCGM
  [Preprint] UCGM: Unified Continuous Generative Models
  ☆171Updated 7 months ago
• yu-rp / Dimple
  Dimple, the first Discrete Diffusion Multimodal Large Language Model
  ☆114Updated 5 months ago
• YuchuanTian / U-DiT
  [NeurIPS 2024] The official code of "U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers"
  ☆228Updated last year
• CompVis / discrete-interpolants
  The official implementation of "[MASK] is All You Need"
  ☆127Updated 5 months ago