Introducing Image Generation Mode

Introducing Image Generation Mode

You can now create beautiful high-resolution images in a dedicated space in DecentAI. Just like when chatting, you can select which model you want to use to generate your images, including SDXL, Stable Diffusion 3 or DALL-E 3).

Open source image generation has advanced tremendously in the past year and we are excited to help bring these powerful models to everyone in an intuitive way. From the home page, just tap on “Create Image” to get started.

More transparency, squashed bugs, better performance

We’re all about transparency. If you’re using a mix, DecentAI now tells you which model was selected for each response. This shows how powerful it is to mix different models together! For example, in the image below, you can see that the first response was generated by Qwen2 72B while the second one was generated by Mixtral 8x22B.