XianfengWu01 / LightGenLinks
An Efficient Text-to-Image Generation Pretrain Pipeline
☆118Updated 6 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☆96Updated 3 weeks ago
- Official Repo for Paper "OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision" [ICLR2025]☆128Updated 9 months ago
- Official Implementation of "LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis"☆72Updated 2 months ago
- ☆119Updated 2 months ago
- ☆51Updated 10 months ago
- [CVPR2025 Highlight] PAR: Parallelized Autoregressive Visual Generation. https://yuqingwang1029.github.io/PAR-project☆178Updated 7 months ago
- ☆129Updated 4 months ago
- [ICML 2025] EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM☆68Updated 3 months ago
- Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think!☆120Updated 7 months ago
- GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset☆231Updated 2 months ago
- [NeurIPS 2025] Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆212Updated last month
- Lumos Project: Frontier video unified model research by Alibaba DAMO Academy, including Lumos-1, etc.☆139Updated 3 months ago
- [NeurIPS 2025] IEAP: Image Editing As Programs with Diffusion Models☆102Updated last month
- Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)☆202Updated last month
- [CVPR 2025] PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation☆41Updated 3 months ago
- Subjects200K dataset☆119Updated 9 months ago
- [ICCV 2025] Code & Data for: SuperEdit - Rectifying and Facilitating Supervision for Instruction-Based Image Editing☆159Updated 4 months ago
- Implementation code of the paper MIGE: A Unified Framework for Multimodal Instruction-Based Image Generation and Editing☆69Updated 3 months ago
- [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving☆252Updated 2 months ago
- Concat-ID: Towards Universal Identity-Preserving Video Synthesis☆62Updated 5 months ago
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆159Updated 11 months ago
- [SIGGRAPH ASIA'25] BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing☆21Updated 7 months ago
- STAR: Scale-wise Text-to-image generation via Auto-Regressive representations☆146Updated 8 months ago
- Code for Paper 'Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach'☆33Updated last year
- ☆48Updated 5 months ago
- ☆106Updated 11 months ago
- [ICCV 2025] Code for FreeScale, a tuning-free method for higher-resolution visual generation☆139Updated 2 weeks ago
- Conceptrol: Concept Control of Zero-shot Personalized Image Generation☆43Updated 7 months ago
- (ICCV2025) EEdit⚡: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing☆57Updated last month
- Official implementation of MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis☆86Updated last year