# Non-commercial Use

RapBank is a dataset focused on rap music, collecting a large number of rap songs from YouTube and offering a meticulously designed data preprocessing workflow. This dataset is significant for the field of music generation as it provides a wealth of rap music content that can be used for training and testing music generation models. The RapBank dataset includes 94,164 song links, successfully downloaded 92,371 songs, totaling 5,586 hours of music, covering 84 different languages, with English songs accounting for the majority, approximately two-thirds of the total duration.

RMBG-2.0 is a background removal model developed by BRIA AI, aimed at effectively separating the foreground and background in images. The model is trained on a curated dataset including general stock images, e-commerce, gaming, and advertising content, making it suitable for commercial use and capable of driving large-scale content creation for enterprises. Its accuracy, efficiency, and versatility are comparable to leading open-source models. RMBG-2.0 is available as source code for non-commercial use.

Fish Agent V0.1 3B is a groundbreaking speech-to-speech model capable of capturing and generating environmental audio information with unprecedented accuracy. The model utilizes a non-semantic tagging architecture, eliminating the need for traditional semantic encoders/decoders. Additionally, it is a cutting-edge text-to-speech (TTS) model trained on 700,000 hours of multilingual audio content. As a continuation of the Qwen-2.5-3B-Instruct pre-trained version, it has been trained on 200 billion speech and text tags. The model supports eight languages, including English and Chinese, with approximately 300,000 hours of training data for each of these languages and around 20,000 hours for others.

FLUX.1-dev-LoRA-One-Click-Creative-Template is an image generation model trained with LoRA, provided by Shakker-Labs. This model focuses on creative photo generation, transforming user text prompts into imaginative images. It employs advanced text-to-image generation technology, making it ideal for users who need to quickly produce high-quality images. The model is hosted on the Hugging Face platform, allowing for convenient deployment and use. Non-commercial use is free, whereas commercial use requires adherence to the relevant licensing agreements.

AWPortrait-FL is a refined advanced portrait generation model built on FLUX.1-dev, trained using the AWPortrait-XL dataset and nearly 2000 high-quality fashion photography images. This model shows significant improvements in composition and details, enabling the generation of more delicate and realistic skin textures in portraits. It was trained by DynamicWang on AWPlanet.

AlphaFold Server is an online service based on the AlphaFold3 model that can generate high-precision predictions of the structures of proteins, DNA, RNA, ligands, ions, etc., and can simulate chemical modifications of proteins and nucleic acids. Developed in collaboration between Google DeepMind and Isomorphic Labs, it is of great significance in the fields of scientific research and biopharmaceuticals. Particularly in non-commercial uses, it provides a powerful tool for predicting and analyzing biomolecular structures.