Hoshikuchi
Hoshilicious-IllustXL
🫡👈➕🫵🟰❤️
An anime-based Stable Diffusion model (base model: Illustrious XL) built as a testing ground for creating "damsel in distress (DID)" and "soft bondage" illustrations. The focus is on making it easy to use while delivering consistent results.
This model incorporates various gag concepts, binding techniques, and restraint scenarios, such as rope bondage, tape bondage. It also supports context-specific props or settings (still coming soon), enhancing its ability to the theme, and aims to balance these specific features with strong general-purpose capabilities.
Changelog || FAQ || Huggingface
Parameters
Default positive prompt:
masterpiece, best quality, very aesthetic, Default negative prompt:
lowres, bad quality, worst quality, very displeasing, bad anatomy, sketch, jpeg artifacts, signature, watermark, Steps: 28
CFG: 5-6
Sampler: euler_a
Hires Fix and Adetailer are recommended!
Please check the example pictures and Changelog for more details. Suggestions are always welcome! If you have tips for further improvements, I’d love to hear them—I’m still learning and growing!
If you’d like to support the development of this project, you can contribute through my Ko-fi page, which is always open. I also accept direct PayPal donations if that’s more convenient.
A big thank you to the AI Waifu DID Discord community for their invaluable help and support so far~
Disclaimer: This Model is intended for creative expression and entertainment purposes only. It does not depict or endorse any harmful, offensive, or inappropriate content. I do not support or condone any such content.
What is Hoshilicious-IllustXL?
Hoshilicious-IllustXL is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user Hoshikuchi. Derived from the powerful Stable Diffusion (Illustrious) model, Hoshilicious-IllustXL has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that Hoshilicious-IllustXL is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, bondage, base model.
With a rating of 0 and over 0 ratings, Hoshilicious-IllustXL is a popular choice among users for generating high-quality images from text prompts.
Can I download Hoshilicious-IllustXL?
Yes! You can download the latest version of Hoshilicious-IllustXL from here.
How to use Hoshilicious-IllustXL?
To use Hoshilicious-IllustXL, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like Hoshilicious-IllustXL, check out our crash course in AI image generation.
Popularity
Info
Version v1.0-epsilon: 1 File
About this version: v1.0-epsilon
Hoshilicious-IllustXL-v1-epsilon
Fixing VAE related problem when adetailer turned on, which could show a visible color different between spot where it's being adetailed (at least on my test, seems to be working just fine now)
The previously added gags concept has been enhanced, should be consistently fine now
The "lip outline" concept might get weaker, I'm still looking for a way on how to implement it without making it biased to always showing lip outline, worst case, I'll just make a LoRA for it
Adding "rubber bondage" concept, accompanied with "[color] bodysuit" and "gagged", "over the nose gag" or "over the mouth gag"
Improvement on "tied to chair" concept
2 Versions
Go ahead and upload yours!
