Search the full model catalog.

Qwen2.5-Coder-32B-Instruct is a powerful code-focused large language model with 32 billion parameters, fine-tuned for coding and instruction-based tasks. It excels in code generation, code completion, and understanding complex programming instructions across multiple languages.

Gemma-2-2B is a compact large language model by Google, featuring 2 billion parameters and optimized for instruction-based and multilingual tasks. It provides efficient natural language processing, making it suitable for a variety of AI-driven applications with lower computational requirements.

Gemma-2-9B is an advanced large language model by Google, featuring 9 billion parameters and designed for multilingual and instruction-following tasks. It delivers high-quality performance in complex natural language understanding and generation across various domains.

Meta-Llama 3-8B-Instruct is a state-of-the-art large language model with 8 billion parameters, optimized for instruction-based tasks. It excels in understanding and generating natural language, making it ideal for a wide range of AI-driven applications.

Mistral-7B-Instruct-v0.3 is a highly efficient large language model with 7 billion parameters, fine-tuned for instruction-following tasks. It delivers strong performance across a range of applications, offering reliable responses and enhanced task comprehension.

Llama 3.1-8B-Instruct is an advanced large language model designed for instruction-based tasks and fine-tuned for improved user interaction. With 8 billion parameters, it offers enhanced accuracy and versatility across various AI applications.

Qwen 2.5 is the large language model of Qwen, offering advanced natural language understanding and generation capabilities. It’s designed to handle complex tasks with high accuracy, making it ideal for diverse AI applications.

Meet with Wiro AI's Turkish Large Language Model (LLM)! A robust language model with more Turkish language and culture support!

This face anonymization tool detects and obscures faces in images.

This is FLUX.1-dev-fp8 v1.0 model.

BLIP-2 creates captions or detailed descriptions for images. This is BLIP-2 model, leveraging Flan T5-xl.

BLIP is a model that is able to perform various multi-modal tasks including visual question answering and image captioning. This is the blip image captioning large model.

BLIP is a model that is able to perform various multi-modal tasks including visual question answering and image captioning. This is the blip image captioning base model.

This is an FLUX1.0 image to image tool.

FLUX.1 Fill Dev is a model designed to fill areas within existing images based on text descriptions.

LoRA training is a low-rank adaptation technique used to fine-tune FLUX models, enabling personalized model outputs with minimal computational overhead.

Convert the video data into textual descriptions.

Convert the video data into textual descriptions.