Welcome to Illuminati Diffusion v1.1! This state-of-the-art text-to-image diffusion model is fine-tuned to produce high-quality, aesthetically pleasing synthetic images. Based on Stable Diffusion 2.1, it offers enhanced depth, contrast, and color, thanks to extensive training on a diverse dataset.
Key Features and Updates:
Model Version: Built on the robust Stable Diffusion 2.1 framework, ensuring top-notch performance and compatibility.
ControlNet Support: Enhanced functionality with ControlNet integration. Get the details and instructions at ControlNet SD2.1 on Hugging Face.
Essential Downloads: To fully utilize the model, download these critical negative embeds along with the main file, and add them to your AUTOMATIC1111 webui embeddings folder:
Optimal Image Settings: For best results, use settings between 768-1024 / 1152 for some seeds and prompts. Occasionally, 1280x768 or 768x1280 may also yield excellent outcomes.
User Guidance: Check out example images for inspiration. This fully finetuned model doesn't require specific trigger words. Feel free to experiment with various prompts and settings.
License Flexibility: Under the CreativeML OpenRAIL-M license, there are no restrictions on the use of the Illuminati Diffusion v1.1 model. Feel free to use it for both personal and commercial projects.
Usage Freedom: Host or use the model on any platform, commercial or non-commercial. The model is designed for wide accessibility and versatility.
Commercial Use: Outputs generated from the model can be freely used for commercial purposes, regardless of team size or project scope.