Generative AI (GenAI): Difference between revisions

Revision as of 12:04, 7 October 2026

Generative AI models are used in multiple ways in the Tygron Platform by AI Agents.

List of open weight Large Language Models (LLM) models available to Chat Agents.

Gemma4 (Speed): Gemma4 model^[1] optimized for fast reactions.
Qwen3.8 (Quality): Qwen3.8 model^[2] optimized for quality needed for coding and TQL.

These models help the LLM's to identify features in images from the interface or e.g. Overlay exports.

These models can create new or edit existing images that can be used in Design Agents.

The Tygron Platform supports multiple open-source models, for example Gemma4^[1] and Mistral^[3].
The LLM also has access to several Model Context Protocol (MCP) tools ^[4] in order to interact with this WIKI and your Project.
All models run Tygron Cloud Computing servers, with no links to external hosting and follow strict AI Rules.

↑ ^1.0 ^1.1 Gemma4 ∙ Found at: https://deepmind.google/models/gemma/gemma-4/ ∙ (last visited: 2026-06-29)
↑ Cite error: Invalid <ref> tag; no text was provided for refs named ref-Qwen3.8
↑ Mistral ∙ Found at: https://mistral.ai/news/vibe-remote-agents-mistral-medium-3-5/ ∙ (last visited: 2026-06-29)
↑ MCP ∙ Found at: https://modelcontextprotocol.io/docs/getting-started/intro ∙ (last visited: 2026-06-29)

Cite error: <ref> tag with name "ref-LLM" defined in <references> is not used in prior text.

@@ Line 1: / Line 1: @@
-Generative AI is used in multiple ways in the {{software}}.
+Generative AI models are used in multiple ways in the {{software}} by [[AI Agent]]s.
-===Generative AI===
+===Large Language Models===
-{{main |Generative AI (GenAI)}}
+List of open weight Large Language Models (LLM) models available to Chat Agents.
-List of open source [[Generative AI (GenAI)|Generative AI]] models available to the Chat Channel Agents:
 * '''Gemma4 (Speed)''': Gemma4 model{{ref|Gemma4}} optimized for fast reactions.
 * '''Qwen3.8 (Quality)''': Qwen3.8 model{{ref|Qwen3.8}} optimized for quality needed for coding and [[TQL]].
-==AI Agents==
+===Vision Models===
-[[AI Agent]]s consist of a Large Language Models (LLM){{ref|LLM}} [[Neural Network]] in combination with Vision and a set of Tools to interact with the Project or answer documentation questions. Using a [[Chat Channel]] you can interact with an AI Agent.
+These models help the LLM's to identify features in images from the interface or e.g. Overlay exports.
+===Diffusion Models===
+These models can create new or edit existing images that can be used in Design Agents.
 {{article end