ml-lab's repositories
LLaMA-Adapter-2
Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
Depth-Anything
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
AnimateAnyone
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
audiocraft
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
autodistill
Images to inference with no labeling (use foundation models to train supervised models)
automuse
Xe's stupid novel generation trickery
ColossalAI
Making large AI models cheaper, faster and more accessible
ComfyUI-AnimateAnyone-Evolved
Improved AnimateAnyone implementation that allows you to use the opse image sequence and reference image to generate stylized video
DB-GPT
Interact your data and environment using the local GPT, no data leaks, 100% privately, 100% security
DreamPose
Official implementation of "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"
gemma.cpp
lightweight, standalone C++ inference engine for Google's Gemma models.
gpt4all
gpt4all: a chatbot trained on a massive collection of clean assistant data including code, stories and dialogue
grok-1
Grok open release
guidance
A guidance language for controlling large language models.
jsonformer
A Bulletproof Way to Generate Structured JSON from Language Models
LLaMA-Adapter
Fine-tuning LLaMA to follow instructions within 1 Hour and 1.2M Parameters
mandala
A powerful and easy to use Python framework for experiment tracking and incremental computing
minimal_outer_ellipsoid
Search the smallest ellipsoid that covers a basic semi-algebraic set through convex optimization
privateGPT
Interact privately with your documents using the power of GPT, 100% privately, no data leaks
shap-e
Generate 3D objects conditioned on text or images
text2room
Text2Room generates textured 3D meshes from a given text prompt using 2D text-to-image models (ICCV2023).