A LoRA for Stable Diffusion 1.5 checkpoints, trained to mimic the art style of glyvees. glyvees is an artist known for their stylized fantasy character illustrations. Trained on 2 repeats of 24 images.<h2 id="usage-tips-9nzvkfg8g">Usage Tips</h2><ul><li>The trigger word is "hwglyvees".</li><li>Most standard NAI-based checkpoints should be compatible with the LoRA. <a target="_blank" rel="ugc" href="https://civarchive.com/models/9942/abyssorangemix3-aom3">AOM3</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/23900?modelVersionId=95489">AnyLoRA</a> seem to work the best.</li><li>Use Booru tags when prompting.</li><li>LoRA strength should be 1.0 to 1.2. If the style doesn't bleed enough, strength can go up to 1.5, but this may cause artifacts. Female characters may become more androgynous/masculine.</li><li>Any DPM++ sampler at 512x768 base resolution. Hires fix is not required.</li><li>Optionally use certain tags to emphasize the style; try "no mouth, no nose, animal hood"</li></ul><h2 id="remarks-hmiyltg5a">Remarks</h2><ul><li>Stable Diffusion XL/Pony versions are on my bucket list; I don't have enough VRAM to train these LoRA types yet. Be patient!</li><li>It's ideal to use img2img, inpainting and controlnet techniques to get good images, you won't get perfect images from generations alone.</li></ul>

Files with SHA256: df17ea88a8c1afe855fb1ed3a9e652c05d38c68992633f0ab0ae578d9805c918