stable-diffusion text-to-image art

HARDblend

A versatile photorealistic NSFW capable model which is great at generating high quality portraits. It is a finetuned model trained on ~500 portrait images merged with Hassanblend, Aeros, RealisticVision1.2, Delibrate, SxD, f222.

Usage

Use stability ai VAE or bakedinVAE version for better results.

RAW samples image

Help us to be able to create models of professional standards. Consider supporting us on Patreon / Ko-fi / Paypal.

Demo

We support a Gradio Web UI to run HARDblend : Open In Spaces

License

This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies :