Starred repositories
Robust Speech Recognition via Large-Scale Weak Supervision
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.
Exploitation Framework for Embedded Devices
[CVPR 2023] SadTalker:Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild
lgandx / Responder
Forked from SpiderLabs/ResponderResponder is a LLMNR, NBT-NS and MDNS poisoner, with built-in HTTP/SMB/MSSQL/FTP/LDAP rogue authentication server supporting NTLMv1/NTLMv2/LMv2, Extended Security NTLMSSP and Basic HTTP authenticat…
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
Responder is a LLMNR, NBT-NS and MDNS poisoner, with built-in HTTP/SMB/MSSQL/FTP/LDAP rogue authentication server supporting NTLMv1/NTLMv2/LMv2, Extended Security NTLMSSP and Basic HTTP authenticat…
Foundational model for human-like, expressive TTS
Open Source framework for voice and multimodal conversational AI
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
SponsorBlock client for all YouTube TV clients.
Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning
[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.
MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators
The official implementation of HierSpeech++
📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion
HumanML3D: A large and diverse 3d human motion-language dataset.
Official implementation of "LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching"
Keylogging server and client that uses DNS tunneling/exfiltration to transmit keystrokes through firewalls.
[Arxiv-2024] MotionLLM: Understanding Human Behaviors from Human Motions and Videos
patientx / ComfyUI-Zluda
Forked from comfyanonymous/ComfyUIThe most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface. Now ZLUDA enhanced for better AMD GPU performance.
A ComfyUI extension that allows you to use some LLM templates provided by Ollama, such as Gemma, Llava (multimodal), Llama2, Llama3 or Mistral