blurgyy / CoMPaSSLinks
[ICCV 2025] Enhancing spatial understanding in text-to-Image diffusion models
☆90Updated 3 months ago
Alternatives and similar repositories for CoMPaSS
Users that are interested in CoMPaSS are comparing it to the libraries listed below
Sorting:
- Code for CineScale, higher-resolution video generation based on Wan☆179Updated 3 months ago
- 🔥🔥 Official Repo of UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward☆174Updated 3 months ago
- Official Implementation of DRA-Ctrl (Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis)☆120Updated 4 months ago
- https://little-misfit.github.io/GRAG-Image-Editing/☆114Updated 3 weeks ago
- OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models☆144Updated 3 months ago
- ☆227Updated 5 months ago
- ☆91Updated 5 months ago
- Calligrapher: Freestyle Text Image Customization☆295Updated 3 months ago
- ☆75Updated last month
- ☆96Updated last month
- Official implementation of "Normalized Attention Guidance"☆175Updated 5 months ago
- High-Quality Text-to-Video Generation with Alpha Channel☆300Updated last week
- Pose Extraction & Rendering for SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representat…☆120Updated this week
- UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios☆85Updated last week
- ☆112Updated 7 months ago
- SynCD: Generating Multi-Image Synthetic Data for Text-to-Image Customization (ICCV 2025)☆150Updated 2 months ago
- Lynx: Towards High-Fidelity Personalized Video Generation☆296Updated 2 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…☆118Updated 5 months ago
- Official implementation for "Story2Board: A Training‑Free Approach for Expressive Storyboard Generation"☆211Updated 4 months ago
- CogVideoX-LoRAs is a centralized repository for all LoRA models created for CogVideoX, filling the gap for a unified sharing space. With …☆81Updated last year
- Scaling Zero-Shot Reference-to-Video Generation☆58Updated last week
- ☆106Updated 3 months ago
- We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while a…☆83Updated this week
- [Arxiv'25] IC-Custom: Diverse Image Customization via In-Context Learning☆158Updated 3 months ago
- [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☆233Updated 2 weeks ago
- Official implementation for "DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion".☆318Updated 3 weeks ago
- ☆79Updated 9 months ago
- This is the official implementation of "T-LoRA: Single Image Diffusion Model Customization Without Overfitting"☆125Updated 5 months ago
- Mobius: Text to Seamless Looping Video Generation via Latent Shift☆168Updated 7 months ago
- The official implementation of ”RepVideo: Rethinking Cross-Layer Representation for Video Generation“☆123Updated 10 months ago