# Multi-scenario adaptation

This project provides a quantized version of Dobby-Mini-Unhinged-Plus-Llama-3.1-8B, aiming to make knowledge accessible to everyone.

Penny - 1.7B is a quantized version of a large language model dedicated to making knowledge accessible to everyone.

A model focused on converting image content into text information, with wide application value.

DMind-1-mini is a lightweight text generation model suitable for various natural language processing tasks.

The first real-time high-quality video generation model based on DiT architecture, capable of generating 1216×704 resolution videos at 30fps

The quantized version of Huihui AI's Qwen3-4B model, aiming to make knowledge more widely accessible to the public.

A license plate detection model fine-tuned based on YOLOv11, optimized for license plate recognition tasks and supporting multiple model variants.

A high-quality photorealistic image generation model based on Stable Diffusion XL, capable of generating detail-rich, photorealistic images from text descriptions.

This is a hybrid model based on the merging of multiple high-quality models, focusing on Chinese text generation and dialogue tasks.

OuteTTS is a text-to-speech (TTS) model focused on the Turkish language, based on a 500M parameter scale, capable of converting Turkish text into natural speech.

Spark-TTS is an advanced text-to-speech system that leverages the powerful capabilities of large language models (LLMs) to achieve highly accurate and naturally fluent speech synthesis.

An automatic speech recognition model fine-tuned on Vietnamese speech data based on openai/whisper-small, improving Vietnamese transcription accuracy and robustness

BRIA RMBG v2.0 is a state-of-the-art background removal model, designed for efficiently separating foreground and background in various types of images, suitable for non-commercial use.

Image depth estimation model based on Latent Bridging Matching (LBM) technology, achieving rapid image transformation through latent space bridging

D-FINE is a powerful real-time object detection model that achieves excellent positioning accuracy by redefining the bounding box regression task in the DETR model.

A Thai female voice text-to-speech (TTS) model based on the VITS architecture, supporting high-quality Thai speech synthesis.

A quantized version based on Alibaba NLP/gte-Qwen2-1.5B-instruct, primarily used for sentence similarity computation and text embedding tasks.

This is a Thai-optimized text-to-speech (TTS) model, particularly suitable for generating female podcast-style voices.

This is an end-to-end automatic speech recognition system trained using the SpeechBrain framework, employing the Conformer architecture on 25,000 hours of English speech data.

This is a Thai female voice text-to-speech (TTS) model, fine-tuned based on the VITS architecture, supporting high-quality Thai speech synthesis.

This is a Thai text-to-speech (TTS) model based on the VITS architecture, specifically fine-tuned for male voice.

AIM-v2 is an image encoder model based on the timm library, suitable for image feature extraction tasks.

A text-to-image generation model based on LoRA technology, specializing in generating specific styles of automotive images

An efficient generative model that supports the conversion from image text to text and is suitable for various application scenarios.

Stable Diffusion is a latent text-to-image diffusion model capable of generating realistic images based on any text input.

COLD2 is a PyTorch-based fill-mask model specifically designed to address missing words in e-commerce search queries.

Leading text-to-speech (TTS) model trained on 700,000 hours of multilingual audio data

The .gguf quantized version of FLUX.1-schnell for text-to-image conversion tasks

A large language model fine-tuned from the gemma-2-9b-it model using the Weighted Preference Optimization (WPO) method, enhancing the effectiveness of off-policy preference optimization.

DINOv2 is a visual feature extraction model developed by Facebook Research team, achieving powerful image representation capabilities through self-supervised learning.

Mistral 7B is a large language model launched by Mistral AI with 7 billion parameters. It is designed for high efficiency and performance and is suitable for real-time application scenarios that require quick responses.

The most powerful realistic image restoration model currently, focusing on hyper-realism and aesthetic balance

Open-source model based on MIT license, specific details currently unavailable

YOLOv10 is a real-time end-to-end object detection model developed by Tsinghua University's MIG Lab, offering efficient detection performance and lightweight deployment capabilities.

An efficient background removal model developed by BRIA AI, suitable for separating foreground and background in various types of images

A Russian speech recognition model fine-tuned based on OpenAI Whisper-large-v3, optimized for Russian recognition performance

Open-source model based on the Apache-2.0 license

A text generation model specifically designed for generating prompts for text-to-image models, optimized for performance and storage using PyTorch and safetensors technology.

The GGUF quantized version of the Gemma-2b-it model, suitable for local inference and supporting text generation tasks.