Official implementation of the paper "Watermark Anything with Localized Messages"

InstantIR: Blind Image Restoration with Instant Generative Reference 🔥

Fast and accurate automatic speech recognition (ASR) for edge devices

A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation

MLLM for On-Demand Spatial-Temporal Understanding at Arbitrary Resolution

Codebase for Aria - an Open Multimodal Native MoE

Machine Learning Engineering Open Book

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Official repository for Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.

Cog inference for flux models

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

An unofficial implementation for "CoSeR: Bridging Image and Language for Cognitive Super-Resolution (CVPR 2024)"

A little repo to render objaverse objects with blender

This script allows you to download objects from Objverse by a specific tag.

🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

A markdown version emoji cheat sheet

No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents

[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment

fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

PyQt6 1st try

Brand new TTS solution

📷 EasyPhoto | Your Smart AI Photo Generator.

SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement

🧡 Next generation information browser.

[NeurIPS 2023] Official code of "One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization"

Code for "Real3D: Scaling Up Large Reconstruction Models with Real-World Images"