General Update & Notes Regarding Unauthorized Breach, Generation Issues

Over the past week, you may have noticed delays in text generation, maintenance on Custom AI Modules, and general instability issues. These events are related to the recent internal security breach. Usually, we scale up operations automatically and quickly with fluctuating generation demand throughout the day.

Hope everyone is having a good time with the release so far! Servers seem to have had a few hiccups along the way, but the team is watching attentively!

We noted some comments and highly recommend adding these tags to your prompt if you are experiencing troubles: If the quality is lackluster, add:
``masterpiece`` or ``high quality`` to your prompt, this will pull higher quality vector data and should instantly improve your results.

NovelAI's Image Generation, #NovelAIDiffusion is live on novelai.net now!

NovelAI Diffusion Anime image generation is uniquely tailored to give you a creative tool to visualize your visions without limitations, allowing you to paint the stories of your imagination. We decided to release #NovelAIDiffusion models as standalone releases:

NovelAI Diffusion Anime (Curated)
Good baseline quality and predictable subject matter.

NovelAI Diffusion Anime (Full)
The expanded training set allows for a wider variety of generations.

Greetings, NovelAI community!
As many of you are aware, we are currently developing NovelAI’s Image Generation feature, and it has been quite some time.

Let’s get to the reasons for the delay. We really want to bring you the best and most capable experience we can in true NovelAI fashion, unlike other commercially-available applications for the Stable Diffusion Image Model that implement very conservative NSFW filters.

We found a way to apply eisting #NovelAI technology to #stablediffusion image generation in order to be better at #furry & #fursona #aiart creations! The new #furry & #fursona tech based on #stablediffusion created by the #NovelAI team is wild.