lihaoyun6 / FlashVSR_plusLinks
Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional decoder.
☆94Updated 2 months ago
Alternatives and similar repositories for FlashVSR_plus
Users that are interested in FlashVSR_plus are comparing it to the libraries listed below
Sorting:
- HunyuanVideo Keyframe Control Lora is an adapter for HunyuanVideo T2V model for keyframe-based video generation☆168Updated 10 months ago
- ☆91Updated 6 months ago
- DreamID-V: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer☆497Updated 3 weeks ago
- [NeurIPS 2024] Generalizable Implicit Motion Modeling for Video Frame Interpolation☆377Updated 8 months ago
- Official implementation of MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement☆285Updated 3 weeks ago
- [AAAI2025] DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder☆141Updated 8 months ago
- Mobius: Text to Seamless Looping Video Generation via Latent Shift☆170Updated 8 months ago
- ☆83Updated 2 months ago
- Official implementation of "Normalized Attention Guidance"☆178Updated 7 months ago
- Official Pytorch Implementation for "Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising"☆329Updated last month
- Official code for our ICCV2025 paper "SDMatte: Grafting Diffusion Models for Interactive Matting"☆172Updated 5 months ago
- ☆79Updated 11 months ago
- [ICLR2026] SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training☆623Updated last week
- [SIGGRAPH 2025] Official code of the paper "Cobra: Efficient Line Art COlorization with BRoAder References". Cobra：利用更广泛参考图实现高效线稿上色☆240Updated last month
- ☆39Updated last month
- ☆235Updated 8 months ago
- Any-to-Bokeh is a novel one-step video bokeh framework that converts arbitrary input videos into temporally coherent, depth-aware bokeh e…☆122Updated 6 months ago
- SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation☆569Updated last month
- We achieves high-quality first-frame guided video editing given a reference image, while maintaining flexibility for incorporating additi…☆321Updated 5 months ago
- musubi-tuner modified to tune image2video/video infilling☆33Updated last year
- Official Implementation of DRA-Ctrl (Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis)☆118Updated 5 months ago
- The official code implementation of the paper "OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data."☆426Updated 7 months ago
- High-Quality Text-to-Video Generation with Alpha Channel☆328Updated last month
- ☆94Updated last year
- FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers☆498Updated 5 months ago
- ☆71Updated last year
- Community trainer for Lightricks' LTX Video model 🎬 ⚡️☆396Updated 3 weeks ago
- Pose Extraction & Rendering for SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representat…☆175Updated last month
- ☆99Updated 2 months ago
- ☆53Updated 9 months ago