Search the full model catalog.

Moondream3 is a cutting-edge vision-language model that delivers advanced visual reasoning with built-in object detection, pointing, and OCR capabilities—bringing fast, cost-effective, and scalable inference to real-world applications.

Moondream3 is a cutting-edge vision-language model that delivers advanced visual reasoning with built-in object detection, pointing, and OCR capabilities—bringing fast, cost-effective, and scalable inference to real-world applications.

OpenAI GPT-OSS-20B model.

Qwen3-30B-A3B model.

Qwen3-30B-A3B-Thinking-2507 model.

Qwen3-32B model.

Qwen3-Coder-30B-A3B-Instruct model.

Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains without the need for fine-tuning.

Puts one or two faces into a scene it generates from your prompt, or into a photo you upload. In a two-person photo it can replace just the left or the right person.

Mixed dataset LLM Information Security v1.5 - Incident Response v1.3.1 - Threat Hunting v1.3.2 - Ethical Exploit Development v2.0 - Purple Team Tactics v1.3 - Reverse Engineering v2.0

Fast LoRA training is a technique used to fine-tune FLUX models, enabling personalized model outputs with fast.

SkyReels V1 is the first and most advanced open-source human-centric video model.

DeepSeek-VL2 delivers accurate and fast answers to your questions about images, making visual question answering effortless and reliable.

NSFW video detection automatically analyzes video content to identify inappropriate or explicit material, ensuring compliance with content policies and a safe viewing environment.

Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.

VideoLLaMA3-2B is a model designed for video understanding.

VideoLLaMA3-2B-Image is a model designed for image understanding.

Qwen2.5-14B-Instruct is a large language model by Alibaba’s Qwen team, optimized for instruction-following tasks with 14 billion parameters. It offers strong reasoning, multilingual capabilities, and efficient performance, making it suitable for chatbots, content creation, and various AI-driven applications.

Qwen2.5-32B-Instruct is a powerful large language model developed by Alibaba’s Qwen team, designed for instruction-following tasks with enhanced reasoning and natural language understanding capabilities. Optimized for efficiency and accuracy, it supports multi-turn conversations and complex queries, making it suitable for applications such as chatbots, content generation, and AI assistants.

Sana is a text-to-image framework that can efficiently generate images up to 4096 × 4096 resolution.