XianfengWu01 / LightGenLinks
An Efficient Text-to-Image Generation Pretrain Pipeline
☆130Updated 9 months ago
Alternatives and similar repositories for LightGen
Users that are interested in LightGen are comparing it to the libraries listed below
Sorting:
- An official implementation of EvoSearch: Scaling Image and Video Generation via Test-Time Evolutionary Search☆101Updated 4 months ago
- Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"☆177Updated last week
- Official implementation of Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning☆223Updated this week
- Edit-R1: Reinforce Image Editing with Diffusion Negative-Aware Finetuning and MLLM Implicit Feedback☆228Updated 2 weeks ago
- ☆124Updated 5 months ago
- [NeurIPS 2025] IEAP: Image Editing As Programs with Diffusion Models☆112Updated 4 months ago
- STAR: Scale-wise Text-to-image generation via Auto-Regressive representations☆148Updated 11 months ago
- Official Implementation of "LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis"☆78Updated 5 months ago
- GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset☆244Updated 5 months ago
- [NeurIPS 2025] Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆214Updated 4 months ago
- Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think!☆121Updated 11 months ago
- [ICCV 2025] The official implementation of "Neighboring Autoregressive Modeling for Efficient Visual Generation"☆58Updated 10 months ago
- ☆53Updated last year
- [CVPR 2025] PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation☆44Updated 7 months ago
- Official Repo for Paper "OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision" [ICLR2025]☆141Updated last year
- ☆109Updated last year
- [CVPR2025 Highlight] PAR: Parallelized Autoregressive Visual Generation. https://yuqingwang1029.github.io/PAR-project☆184Updated 10 months ago
- Concat-ID: Towards Universal Identity-Preserving Video Synthesis☆65Updated 9 months ago
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆165Updated last year
- [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving☆269Updated 6 months ago
- ☆132Updated 7 months ago
- Subjects200K dataset☆129Updated last year
- EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling☆211Updated last week
- [ICLR 2025] IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation☆203Updated 11 months ago
- (ICCV2025) EEdit⚡: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing☆60Updated 4 months ago
- ☆53Updated 9 months ago
- Official implementation of MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis☆86Updated last year
- This is the official repository for the paper "FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehe…☆121Updated 2 weeks ago
- Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)☆266Updated 2 months ago
- [ICCV2025] The code of our work "Golden Noise for Diffusion Models: A Learning Framework".☆195Updated 6 months ago