Davinci-XLab / STAR-T2I
Official implementation of "STAR: Scale-wise Text-to-image generation via Auto-Regressive representations"
☆28Updated last month
Alternatives and similar repositories for STAR-T2I:
Users that are interested in STAR-T2I are comparing it to the libraries listed below
- Official GitHub repository for the Text-Guided Video Editing (TGVE) competition of LOVEU Workshop @ CVPR'23.☆75Updated last year
- This is the official implementation for ControlVAR.☆102Updated 4 months ago
- ICCV2023-Diffusion-Papers☆109Updated last year
- FQGAN: Factorized Visual Tokenization and Generation☆47Updated 3 weeks ago
- [CVPR 2024] InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization☆56Updated 10 months ago
- [CVPR2025] Official PyTorch implementation of "Optical-Flow Guided Prompt Optimization for Coherent Video Generation (Motion Prompt)"☆19Updated last month
- [NeurIPS 2024] Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation☆64Updated 5 months ago
- Code Release of Harmonizing Visual Representations for Unified Multimodal Understanding and Generation☆64Updated last week
- The official repository of "Spectral Motion Alignment for Video Motion Transfer using Diffusion Models".☆27Updated 4 months ago
- Official Implementation of VideoDPO☆84Updated 3 months ago
- CAR: Controllable AutoRegressive Modeling for Visual Generation☆114Updated 4 months ago
- a collection of awesome autoregressive visual generation models☆72Updated this week
- Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation (ICCV 2023)☆64Updated last year
- ☆20Updated 2 weeks ago
- “FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching” FlowAR employs a simplest scale design and is compatible with an…☆105Updated 3 months ago
- [CVPR 2025 (Oral)] Open implementation of "RandAR"☆107Updated last month
- [Neurips 2024] Video Diffusion Models are Training-free Motion Interpreter and Controller☆36Updated last week
- Implementation of the paper "MaskBit: Embedding-free Image Generation from Bit Tokens"☆63Updated last week
- "SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow", Yuanzhi Zhu, Xingchao Liu, Qiang Liu☆48Updated 4 months ago
- [NeurIPS 2023] Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator☆96Updated last year
- Frequency Autoregressive Image Generation with Continuous Tokens☆56Updated last month
- Official source codes of "TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation" (ICLR 2025)☆45Updated 3 months ago
- ☆19Updated this week
- ☆39Updated last year
- Official implementation of MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis☆83Updated 9 months ago
- [NeurIPS 2024] COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing☆23Updated 4 months ago
- PyTorch implementation of DiffMoE, TC-DiT, EC-DiT and Dense DiT☆71Updated this week
- [CVPR 2025 Oral] Alias-free Latent Diffusion Models (official implementation)☆74Updated last month
- [ICLR 2024] Official PyTorch/Diffusers implementation of "Object-aware Inversion and Reassembly for Image Editing"☆85Updated 7 months ago
- Code for D-DiT☆23Updated 3 weeks ago