The most powerful local music generation model that outperforms most commercial alternatives
Repositories
sdbds repositories
ACE-Step: A Step Towards Music Generation Foundation Model
APISR: Anime Production Inspired Real-World Anime Super-Resolution (CVPR 2024)
Official Implementations for Paper - AniDoc: Animation Creation Made Easier
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
Official implementation of AnimateDiff.
Code and data for ICCV23 work "Deep Geometrized Cartoon Line Inbetweening"
Official implementations for paper: Anydoor: zero-shot object-level image customization
A plugin for Hearthstone Deck Tracker that helps drafting Hearthstone arena decks.
Open-source unified multimodal model
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.
Reverse-engineered the BazaarPlusPlus.dll plugin using decompilation tools, analyzed its internal architecture, and implemented custom enhancements to optimize and extend the card recommendation algorithm.
[arXiv'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation
Official repository for "Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment"
AI画像生成でキャラクターの扱いをしくみ化してフレームワークにしてみる
Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.