Gemini
Google's multimodal AI assistant for research, writing, coding, and agentic tasks across Google apps

SwarmUI is a free, open-source web interface for running AI image, video, and audio generation models locally, aimed at both beginners and advanced users who want accessible power tools and extensibility.
SwarmUI is a free, open-source web interface for running AI image, video, and audio generation models, designed for both beginners who want a guided experience and advanced users who need raw control over their workflows.
SwarmUI, formerly known as StableSwarmUI, presents itself as a modular web user interface for AI generation. It supports image models such as Krea 2, Stable Diffusion, and Flux, video models including MiniMax H3, Wan, and LTX-2, and some audio models like ACE-Step. The project states that it will continue adding new models as they are released to the public. This breadth means users can work across media types without switching between separate tools.
The interface is built around two primary tabs. The Generate tab offers a guided experience with a range of features intended to make generation straightforward, and the project recommends it as an ideal starting point for most users. The Comfy Workflow tab exposes the unrestricted raw graph for advanced users who want full control. Even those advanced users have reason to return to the Generate tab for convenience features such as the image editor, automatic workflow generation, and power tools like the Grid Generator.
SwarmUI is in Almost-Release status. According to the project, most tasks have excellent tooling available, but a few areas remain to be perfected. One key feature target not yet implemented is native LLM-assisted prompting; an extension exists for it, but the project intends to support LLM control natively in the future. The project welcomes contributions and recommends reaching out before submitting a pull request, as specific plans or work in progress may already exist.
SwarmUI can be installed on Windows using an installer script, though Windows 10 users may need to install Git and the .NET 8 SDK first. The project also provides a Google Colab notebook for trying it out, with a warning that Colab does not necessarily allow remote WebUIs, particularly for free accounts. For cloud GPU deployment, there are templates for Runpod and Vast.ai, the latter maintained by a third-party contributor. First startup on cloud providers may take several minutes.
SwarmUI supports user-built extensions and can install some custom node packs, each with its own license notices. The core project is under the MIT license, but some usages may be affected by GPL variant licenses of connected projects, and any models used carry their own licenses. This matters for users who plan to redistribute or build commercially on top of the tool.
The project maintains a Discord community for discussion, support, and announcements, along with a feature announcements thread and documentation in the repository's docs folder. The official website is SwarmUI.net. Those interested in contributing can find guidelines in the Contributing document.
SwarmUI is positioned as an ideal UI for most users, beginners and pros alike. Beginners will appreciate the Generate tab's accessible feature set, while advanced users can drop into the Comfy Workflow tab for unrestricted graph editing. The combination of a guided interface, raw workflow access, and support for multiple media types makes it a practical choice for anyone who wants a single, extensible front end for local or cloud-based AI generation.
SwarmUI is 100% free and open source forever, according to the project's GitHub page. No paid tiers or pricing plans are mentioned.
Features, pricing and availability may change. Always verify details on the official website. Maintained by steven · Last updated Oct 16, 2026 →
Google's multimodal AI assistant for research, writing, coding, and agentic tasks across Google apps
LlamaIndex builds document parsing and extraction software plus open-source tools for AI applications, helping teams turn enterprise documents into usable data for AI agents and workflows.
Flowith is an agentic AI workspace that combines a whiteboard-style canvas, access to 40+ image and video models, and mini apps for design, e-commerce, and social content.
Fine-tune open models faster with far less memory