This project provides the quantized GGUF version of the Wan 2.2 distilled model developed by the LightX2V team, specifically designed for image-to-video and video generation tasks. This version is optimized to work with tools such as ComfyUI-GGUF, providing efficient inference performance.

MultimodalGguf

This is a LoRA (Low-Rank Adaptation) model trained based on the Qwen-Image model, specifically designed for text-to-image generation tasks. This project is trained using AI Toolkit and can convert text descriptions into high-quality images, supporting use in various image generation tools.

MultimodalDiffusers

kontext-dusk-3-lora is a LoRA image generation model trained based on the FLUX.1-Kontext-dev base model, specifically designed to generate images in the style of the twilight blue hour. This model is triggered by specific trigger words and supports the use of multiple mainstream AI image generation tools.

Computer VisionDiffusers

pejawan22-lora is a LoRA model trained based on AI technology, specifically designed for generating specific images and can be integrated with various AI tools. Images are generated by the trigger word 'peja'.

MultimodalDiffusers

This is a LoRA model trained based on AI Toolkit by Ostris, specifically designed for text-to-video conversion tasks. This model is fine-tuned based on the Wan2.2-T2V-A14B base model and supports multiple AI tools and frameworks.

MultimodalDiffusers

my_qwennud-lora is a LoRA model trained using specific tools based on Qwen-Image-Edit-2509. It is specifically designed for image generation and editing tasks, trained with the AI Toolkit by Ostris, and can be used in conjunction with various mainstream AI tools.

MultimodalDiffusers

f3rnanda_wan22-lora is a LoRA model trained based on AI Toolkit by Ostris, specifically designed for image-to-video generation tasks. This model uses Wan2.2-I2V-A14B as the base model and supports use in various AI tools, including mainstream platforms such as ComfyUI and AUTOMATIC1111.

Computer VisionDiffusers

This is the GGUF quantized version of Alibaba's Qwen series large language model with 8 billion parameters, designed for advanced reasoning, intelligent agent behavior, and multilingual tasks, and can be used with llama.cpp and compatible tools.

Natural Language ProcessingGgufMultiple Languages

This is a text-to-image generation model based on the Civitai platform, capable of converting text descriptions into high-quality images. The model supports optimization through quantization tools and is suitable for creative design and visual content generation.

Computer VisionGguf

Foundation-Sec-8B-Instruct is an 8-billion-parameter instruction-tuned language model specifically designed for network security applications. Based on the Llama-3.1-8B architecture, it has excellent instruction-following capabilities and professional knowledge in network security. It supports local deployment and can help organizations build AI security tools, reducing reliance on cloud services.

Natural Language ProcessingTransformersEnglish

This is the GGUF format quantized version of the black-forest-labs/FLUX.1-Krea-dev model, specifically designed for text-to-image generation tasks. The model is optimized through the GGUF format and can be used in specific tools and libraries, suitable for non-commercial image generation applications.

MultimodalGgufEnglish

Devstral is an intelligent large language model specifically designed for software engineering tasks, developed in collaboration by Mistral AI and All Hands AI. It excels at using tools to explore code repositories, edit multiple files, and provides strong support for software engineering agents.

Natural Language ProcessingSafetensorsMultiple Languages

Jan-nano is a compact language model with 4 billion parameters designed specifically for deep research tasks, supporting seamless collaboration with MCP servers and integration of research tools.

Natural Language ProcessingGguf

The pre-ranker is a cross-encoder-based text ranking model designed to optimize the function call process of large language models by narrowing down the corpus of available tools for improved efficiency.

Natural Language ProcessingSafetensorsEnglish

CursorCore is a series of open-source models designed specifically for AI-assisted programming, aiming to support functions such as automatic editing and inline chat, and replicate the core capabilities of closed-source AI-assisted programming tools like Cursor. This model is fine-tuned based on Qwen2.5-Coder-1.5B, and achieves programming assistance functions by aligning programming instruction generation data.

Natural Language ProcessingTransformersOther

gte-small GGUF is a quantized version of the General Text Embeddings (GTE) model trained by Alibaba DAMO Academy. It uses the BERT framework and is specifically designed for text embedding tasks. This model offers multiple quantization levels and supports various downstream tasks such as information retrieval and semantic text similarity calculation. It is compatible with tools like llama.cpp and LM Studio.

Natural Language ProcessingSentence-transformersEnglish

AI-generated image detection model developed by Sumsub, specifically designed to identify synthetic images created by tools like Stable Diffusion

Computer VisionPytorch

This is an image classification model based on the PyTorch framework and generated using HuggingPics tools, specifically designed for recognizing rare dog breeds.

Computer VisionTransformers

This is an image classification model based on the PyTorch framework and generated using HuggingPics tools, specifically designed for gender classification tasks.

Computer VisionTransformers

A text classification model for automatically filtering false positive password findings, designed to work with credential mining tools

Natural Language ProcessingTransformersEnglish