This is a blend of models that I've been working on for a while, with the primary goal of creating realistic character portraits in a variety of genres, but it's a well-rounded model that's been good at everything I've thrown at it. It's probably not very good at anime, but if that's what you're after there are plenty of other models to choose from.This model inherits the <a target="_blank" rel="ugc" href="https://huggingface.co/spaces/CompVis/stable-diffusion-license">CreativeML Open RAIL-M</a> and <a target="_blank" rel="ugc" href="https://huggingface.co/dreamlike-art/dreamlike-photoreal-2.0/blob/main/LICENSE.md">Dreamlike License</a>. By downloading, you agree to both.No need to use a VAE. The model has vae-ft-mse-840000-ema-pruned.ckpt baked in. I also strongly recommend using the following negative embeddings: <a rel="ugc" href="https://huggingface.co/JPPhoto/neg-sketch-2/tree/main">neg-sketch-2</a> by JPPhoto and <a rel="ugc" href="https://huggingface.co/dwringer/neg-anime/tree/main">neg-anime</a> by dwringer.The example images were done with InvokeAI. If you want to reproduce them with a1111, you'll need to convert the syntax.

verisimilitude

This is a complete rebuild. Like the original version, it likes lower CFG scales and higher high-res optimization strength. All example images use the <a rel="ugc" href="https://huggingface.co/JPPhoto/neg-sketch-2/tree/main">neg-sketch-2</a> and <a rel="ugc" href="https://huggingface.co/dwringer/neg-anime/tree/main">neg-anime</a> negative embeddings for enhanced realism (also strongly recommended on earlier versions). I also routinely use a low-weight, unstructured blend, which both helps with realism and seems to increase coherence at higher resolutions (see example images)

Files with SHA256: 79939acf903f81b7d3a0a6697fd6490ecc658eb5fe8fa4e89ed7c51fbb36e3e8