[SD 2.1 768][LORA]TO8's High Key LORA (SD1.5/SD2.1-768) sd2.1-768
<p>This LORA model is trained using the technique described in <a target="_blank" rel="ugc" href="https://www.crosslabs.org//blog/diffusion-with-offset-noise">https://www.crosslabs.org//blog/diffusion-with-offset-noise</a></p><p></p><p>Use it to produce beautiful high-key images that SD just wasn't capable of creating until now.</p><p></p><p>It requires Kohya's SD Additional Networks extension.</p><p></p><p>Sample images were generated using <a target="_blank" rel="ugc" href="https://huggingface.co/IlluminatiAI/Illuminati_Diffusion_v1.0">Illuminati Diffusion v1.0</a></p><p></p><p>The LORA was trained using Kohya's LORA Dreambooth script, on SD2.1-768 and SD1.5 with a dataset of 53 high-key, high-quality photographs.</p><p></p><p>Model weights can be used to affect the 'blown-out' lighting.</p><img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2caa9eec-db15-4343-1025-f8a0c180ed00/width=525" /><p>SD 1.5 version coming soon.</p>
页:
[1]