bornfly-detachment / asymmetric_magvitv2
In 2024, the strongest open-source implementation of asymmetric magvit_v2 supports inference code but excludes VQVAE. It supports the joint encoding of images and videos, accommodating arbitrary video lengths and resolutions. It surpasses all open-source models in FID and FVD, with 4z and 16z models available on huggingface.
☆113Updated last month
Related projects: ⓘ
- Vico: Compositional Video Generation as Flow Equalization☆45Updated 2 months ago
- ☆23Updated last year
- Code for FreeTraj, a tuning-free method for trajectory-controllable video generation☆85Updated last month
- Pytorch Implementation of "SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation"(CVPR 2024)☆87Updated last month
- ☆39Updated 2 months ago
- Official code for 💫CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching☆122Updated 4 months ago
- 🏞️ Official implementation of "Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition"☆98Updated 4 months ago
- T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation☆36Updated 3 weeks ago
- Implementation of ColorizeDiffusion☆17Updated last month
- T2VScore: Towards A Better Metric for Text-to-Video Generation☆76Updated 5 months ago
- Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models☆64Updated 3 months ago
- PartCraft: Crafting Creative Objects by Parts (ECCV2024)☆75Updated last week
- [SIGGRAPH 2024] Motion I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling☆87Updated 2 months ago
- Implementation of InstructEdit☆66Updated 10 months ago
- Code for ICLR 2024 paper "Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators"☆87Updated 7 months ago
- Code Release for the paper "Make-A-Story: Visual Memory Conditioned Consistent Story Generation" in CVPR 2023☆37Updated last year
- [SIGGRAPH Asia 2024] Painting process generating using diffusion models☆46Updated last month
- [ICLR 2024] Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach Link: https://arxiv.o…☆65Updated 5 months ago
- DreamGaussian with 2D-GS☆10Updated 4 months ago
- ClassDiffusion: Official impl. of Paper "ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance"☆32Updated 2 months ago
- [CVPR`2024, Oral] Attention Calibration for Disentangled Text-to-Image Personalization☆77Updated 5 months ago
- CutDiffusion: A Simple, Fast, Cheap, and Strong Diffusion Extrapolation Method☆26Updated 4 months ago
- ☆168Updated 2 months ago
- [CVPR 2024] Official PyTorch implementation of FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition☆89Updated 3 weeks ago
- [CVPR 2023] GLeaD: Improving GANs with A Generator-Leading Task☆32Updated last year
- ☆54Updated 3 months ago
- Official implementation for "LOVECon: Text-driven Training-free Long Video Editing with ControlNet"☆36Updated 10 months ago
- STAR: Scale-wise Text-to-image generation via Auto-Regressive representations☆107Updated 3 months ago
- Navigate dreamscapes with a click – your chosen point guides the drone’s flight in a thrilling visual journey.☆37Updated 8 months ago
- Official GitHub repository for the Text-Guided Video Editing (TGVE) competition of LOVEU Workshop @ CVPR'23.☆68Updated 10 months ago
- [CVPR2024] Official code for Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation☆74Updated 5 months ago