Recurrent Interface Network Pytorch
lucidrains
Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in Pytorch
OPENAGENTSKILL / DIRECTORY
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
81–96 / 397
Candidates in this shortlist, not the full registry. GitHub stars belong to repositories, not individual skills.
Results: 397
lucidrains
Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in Pytorch
momori777
破限本地AI女友后宫,openclaw/claude code+画图语音向量数据库+live2D+桌宠+酒馆角色卡导入+前端,QQ+Telegram双通道,8G显存可跑🩵uncensored Fully offline AI girlfriends harem Openclaw/Claude code+Local LLM+GPT-So…
newideas99
Open Dungeon — the first easy-to-use, fully local AI roleplay app. Story and inline scene images generated 100% on your machine (Gemma 4 QAT via Ollama(and others) + FLU…
Chen-Yang-Liu
[IEEE GRSM 2025 🔥] "Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model"
ddalcu
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.
gudaochangsheng
[CVPR 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis
zai-org
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
Breakthrough
:movie_camera: Python and OpenCV-based scene cut/transition detection program & library.
Tencent-Hunyuan
HunyuanVideo-1.5: A leading lightweight video generation model
AILab-CVC
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models
fudan-generative-vision
[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
Doubiiu
[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors
TMElyralab
MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising
MetalPetal
A GPU accelerated image and video processing framework built on Metal.
Tencent-Hunyuan
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation