GAP-LAB-CUHK-SZ / LoFALinks
Official implementation of "LoFA: Learning to Predict Personalized Prior for Fast Adaptation of Visual Generative Models".
☆32Updated last week
Alternatives and similar repositories for LoFA
Users that are interested in LoFA are comparing it to the libraries listed below
Sorting:
- ☆93Updated last week
- ☆227Updated 6 months ago
- 👋 Dataset and Benchmark code for EgoEdit☆106Updated 2 months ago
- ☆133Updated 10 months ago
- A Unified Visual Generator with Interleaved OmniModal Context☆180Updated this week
- ☆58Updated 3 months ago
- ☆36Updated last month
- DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder☆179Updated 4 months ago
- Official code for VINCIE: Unlocking In-context Image Editing from Video☆48Updated 5 months ago
- ☆317Updated 2 weeks ago
- Official PyTorch implementation of the paper "FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing"☆76Updated 2 months ago
- Generate image at any resolution.☆43Updated 4 months ago
- Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO☆92Updated 2 months ago
- RePlan: Reasoning-Guided Region Planning for Complex Instruction-Based Image Editing☆59Updated last month
- Animate Any Character in Any World☆89Updated last month
- VideoCoF: Unified Video Editing with Temporal Reasoner☆138Updated last month
- Vision Bridge Transformer at Scale☆138Updated 2 months ago
- ☆35Updated last month
- Official repo for paper "Video-As-Prompt: Unified Semantic Control for Video Generation"☆365Updated last week
- [ICCV2025] DCM: Dual-Expert Consistency Model for Efficient and High-Quality Video Generation☆202Updated 8 months ago
- [Arxiv'25] IC-Custom: Diverse Image Customization via In-Context Learning☆160Updated 4 months ago
- This is the project for 'Any2Caption', Interpreting Any Condition to Caption for Controllable Video Generation☆49Updated 10 months ago
- Long-range camera-conditioned scene generation from one single image.☆106Updated last month
- PlayerOne: Egocentric World Simulator☆184Updated 8 months ago
- ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback☆121Updated 4 months ago
- ☆130Updated last month
- One-shot and Few-shot 3D Editing without Per-Scene Optimization☆167Updated 5 months ago
- [ICLR 2026] Light-X: Generative 4D Video Rendering with Camera and Illumination Control☆166Updated 2 months ago
- The official code of Yume☆607Updated 3 weeks ago
- Official repo of "MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing“☆77Updated last month