Tool tag: Latest

HunyuanImage 3.0

Tencent's 80B-parameter MoE image model, released September 28, 2025. Natively multimodal and autoregressive, under a restricted community license.

Wan2.1 (Alibaba)

Alibaba's open-weights video foundation model, Apache 2.0 licensed and widely supported via ComfyUI. Superseded by Wan2.2, which is also open-weights.

Minimax (Hailuo AI)

MiniMax's AI video generation platform known for exceptional physical motion quality and fast generation speeds for high-fidelity cinematic video clips.

Cline

Open-source autonomous AI coding agent for VS Code. Reads files, writes code, runs terminal commands, and uses MCP to control local development environments.

Luma Dream Machine

Luma AI's video generation platform. Ray3 was the first video model to reason about a shot before generating it, and the first to output native 16-bit HDR.

Kling AI

Kuaishou's AI video platform, known for realistic human motion and high-fidelity image-to-video conversion. Now running the Kling 3.0 model family.

DeepSeek

DeepSeek's AI platform offering frontier-class reasoning and coding at disruptive prices with a powerful free web interface and high-speed API endpoints.

Ollama

Run powerful open-weight AI models locally with one command. Provides OpenAI-compatible APIs and GPU acceleration for Apple Silicon and Linux hardware.

Ideogram

AI image generator specifically designed for typography and graphic design with industry-leading text rendering accuracy and color palette control.

NotebookLM

Google's AI research assistant that grounds all answers exclusively in your uploaded sources, providing cited, source-locked insights without hallucinations.