wusize / Harmon
Code Release of Harmonizing Visual Representations for Unified Multimodal Understanding and Generation
☆25Updated this week
Alternatives and similar repositories for Harmon:
Users that are interested in Harmon are comparing it to the libraries listed below
- ☆38Updated last year
- Unified layout planning and image generation☆13Updated 2 weeks ago
- ReNeg: Learning Negative Embedding with Reward Guidance☆31Updated 3 months ago
- Official Implementation of VideoDPO☆76Updated 2 months ago
- Sora Generates Videos with Stunning Geometrical Consistency☆49Updated last year
- Diffusion Powers Video Tokenizer for Comprehension and Generation (CVPR 2025)☆66Updated last month
- [ICLR 2025] IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model☆27Updated 4 months ago
- [Neurips 2024] Video Diffusion Models are Training-free Motion Interpreter and Controller☆34Updated last month
- A framework named B^2-DiffuRL for RL-based diffusion model fine-tuning.☆19Updated 2 weeks ago
- [ICLR 2024] Official implementation of the paper "Toss: High-quality text-guided novel view synthesis from a single image"☆22Updated 10 months ago
- Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation (ICCV 2023)☆64Updated last year
- Autoregressive Image Generation with Randomized Parallel Decoding☆35Updated last week
- FQGAN: Factorized Visual Tokenization and Generation☆46Updated this week
- Official implementation of Next Block Prediction: Video Generation via Semi-Autoregressive Modeling☆26Updated last month
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆63Updated last month
- [NeurIPS 2024 D&B Track] Official Repo for "LVD-2M: A Long-take Video Dataset with Temporally Dense Captions"☆53Updated 5 months ago
- ICCV2023-Diffusion-Papers☆109Updated last year
- Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).☆60Updated last month
- Official implementation of MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis☆83Updated 8 months ago
- Curated list of recent visual autoregressive (VAR) modeling works☆29Updated 2 weeks ago
- Code for Scaling Language-Free Visual Representation Learning (WebSSL)☆115Updated this week
- ☆14Updated 3 weeks ago
- ☆27Updated 2 months ago
- ☆58Updated last year
- ☆23Updated last month
- Code for [CVPR 2025] ROICtrl: Boosting Instance Control for Visual Generation☆104Updated 3 weeks ago
- ☆29Updated last year
- Official implementation of LaVin-DiT☆27Updated 2 months ago
- ☆21Updated last year
- [CVPR 2025] Open implementation of "RandAR"☆81Updated 2 weeks ago