YaNgZhAnG-V5 / attention_regulation
[ECCV24] Attention Regulation on T2I Diffusion Models
☆13Updated 2 months ago
Related projects: ⓘ
- ☆12Updated 5 months ago
- CutDiffusion: A Simple, Fast, Cheap, and Strong Diffusion Extrapolation Method☆26Updated 4 months ago
- [CVPR2024] The official implementation of paper Relation Rectification in Diffusion Model☆42Updated last week
- Official pytorch implementation for SingleInsert☆26Updated 5 months ago
- MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning☆52Updated last week
- ☆38Updated 9 months ago
- This is the official repository for "LatentMan: Generating Consistent Animated Characters using Image Diffusion Models" [CVPRW 2024]☆20Updated last month
- Official repo for the paper "Correcting Diffusion Generation through Resampling"☆27Updated 9 months ago
- Official implemention of "Make It Count: Text-to-Image Generation with an Accurate Number of Objects"☆52Updated 3 months ago
- ☆14Updated 11 months ago
- 🔥 [CVPR 2024] The official repo for Zero-Painter!☆54Updated 3 months ago
- [ICLR 2024] Code for FreeNoise based on LaVie☆32Updated 7 months ago
- This proposed dataset ReS in our paper Repositioning The Subject Within Image☆10Updated 6 months ago
- PEA-Diffusion: Parameter-Efficient Adapter with Knowledge Distillation in non-English Text-to-Image Generation☆19Updated 2 months ago
- Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models☆64Updated 3 months ago
- Official PyTorch Implementation of "Giving a Hand to Diffusion Models: a Two-Stage Approach to Improving Conditional Human Image Generati…☆23Updated 6 months ago
- ☆14Updated 8 months ago
- Eye-for-an-eye: Appearance Transfer with Semantic Correspondence in Diffusion Models☆18Updated last week
- ☆17Updated 5 months ago
- ☆60Updated 2 months ago
- Official PyTorch implementation of "λ-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space"☆43Updated 5 months ago
- ☆39Updated 3 months ago
- [ECCV 2024] BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion☆15Updated 2 months ago
- Official implementation of MagicFace: Training-free Universal-Style Human Image Customized Synthesis.☆28Updated 3 weeks ago
- ☆31Updated 3 months ago
- ClassDiffusion: Official impl. of Paper "ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance"☆32Updated 2 months ago
- ☆45Updated 5 months ago
- ☆17Updated 9 months ago
- ☆86Updated 2 months ago
- [ECCV 2024] Noise Calibration: Plug-and-play Content-Preserving Video Enhancement using Pre-trained Video Diffusion Models☆76Updated 2 weeks ago