we’re excited to share that you can now generate images directly with our Illustrious XL models on our official site: [illustrious-xl.ai].
We’ve launched a full image generation platform featuring high-res outputs, natural language prompting, and custom presets — plus, several exclusive models you won’t find on any other hub. Explore our updated model tiers and naming here: [Model Series].
Need help getting started? Check out our generation user guide: [ILXL Image Generation User Guide].
Illustrious XL v1.1 — More natural language focused "refined" model
We introduce Illustrious v1.1 - which is continued from v1.1, with tuned hyperparameter for stabilization. The model shows slightly better character understanding, however with knowledge cutoff until 2024-07.
The model shows slight difference on color balance, anatomy, saturation, with ELO rating 1617,compared to v1.0, ELO rating 1571, in collected for 400 sample responses.
We will continue our journey until v2, v3, and so on!
For better model development, we are collaborating to collect & analyze user needs, and preferences - to offer preference-optimized checkpoints, or aesthetic tuned variants, as well as fully trainable base checkpoints. We promise that we will try our best to make a better future for everyone.
Illustrious v0.1 (huggingface) | OnomaAI TooToon | Terms of use