TL;DR: Added Google’s Gemini 2.5 Flash model with image generation capabilities and polished the chat interface for better user experience.

New Model: Gemini 2.5 Flash with Image Generation

We’ve integrated Google’s latest Gemini 2.5 Flash model that supports both text and image generation in a single conversation. This powerful model can:

  • Generate high-quality images from text prompts
  • Maintain context across text and visual content
  • Process complex multi-modal requests

Getting Started

  1. Start a new conversation in GPTMuse
  2. Select “Gemini 2.5 Flash Image Preview” from the model dropdown
  3. Type your image generation request or upload an image for analysis
  4. Enjoy the seamless text and image capabilities

The model is available now with competitive pricing.