instantX-research / IP-Adapter-for-SD3
More suitable IP-Adapter for the DiT architecture
☆28Updated 7 months ago
Alternatives and similar repositories for IP-Adapter-for-SD3:
Users that are interested in IP-Adapter-for-SD3 are comparing it to the libraries listed below
- Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers☆49Updated 4 months ago
- ☆21Updated 8 months ago
- Official PyTorch Implementation of "Giving a Hand to Diffusion Models: a Two-Stage Approach to Improving Conditional Human Image Generati…☆26Updated 11 months ago
- ☆51Updated 9 months ago
- an unofficial implementation of dreamtuner☆24Updated 11 months ago
- ☆34Updated last month
- we propose to generate a series of geometric shapes with target colors to disentangle (or peel off ) the target colors from the shapes. B…☆55Updated 4 months ago
- MuDI: Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models (NeurIPS 2024)☆82Updated last month
- ☆39Updated 2 months ago
- This repo contains the code for PreciseControl project [ECCV'24]☆54Updated 4 months ago
- ☆80Updated 7 months ago
- ☆91Updated 5 months ago
- InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation 🔥☆86Updated 7 months ago
- [CVPR`2024, Oral] Attention Calibration for Disentangled Text-to-Image Personalization☆93Updated 10 months ago
- Pytorch Implementation of "SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation"(CVPR 2024)☆105Updated 6 months ago
- ☆38Updated 5 months ago
- Unofficial implementation of Layer Diffuse in diffusers☆26Updated 10 months ago
- [CVPR 2024] Tackling the Singularities at the Endpoints of Time Intervals in Diffusion Models☆65Updated 10 months ago
- ☆47Updated last month
- [ICLR2025] ClassDiffusion: Official impl. of Paper "ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance"☆36Updated 3 weeks ago
- Decoupled Textual Embeddings for Customized Image Generation (AAAI 2024)☆22Updated 11 months ago
- experimental implementation of Consistory☆19Updated 7 months ago
- [ECCV2024] Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models☆41Updated 7 months ago
- ☆110Updated 4 months ago
- code for paper "Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models"☆41Updated last year
- MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance (ACM MM2024)☆118Updated 3 months ago
- Implementation of P+: Extended Textual Conditioning in Text-to-Image Generation☆49Updated last year
- Official code for CustAny: Customizing Anything from A Single Example☆40Updated 2 months ago
- Magic Mirror: ID-Preserved Video Generation in Video Diffusion Transformers☆102Updated last month