<h1 id="heading-1421">Knives and time, a damaged LORA</h1><p></p><p><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/eece4eea-735a-407a-92fb-93f3124ab01e/width=525/eece4eea-735a-407a-92fb-93f3124ab01e.jpeg" />This LORA enables you to simulate damage to photography and Canvas. This is a clone of the hugging face model that I published under the same license: <br /><a target="_blank" rel="ugc" href="https://huggingface.co/calm-and-collected/knives_and_time">https://huggingface.co/calm-and-collected/knives_and_time</a></p><p>It can be used for inpainting and text to image generation.</p><p></p><p>Knives and time is a LORA model trained on public domain and CC0 images. The data was collected from wikimedia commons and annotated with a mixture of BLIP annotation and manual annotation.</p><h2 id="heading-1422"></h2><h2 id="heading-1423">Usage</h2><p>The base trigger is katabd.</p><p>For paintings: painting, yellowed, abrasion, scratches, flaking, damage, torn, cut, pierced. For photography: photograph, monochrome, overlit, overexposed, torn, cut.</p><p>I recommend using it combined with an LCM sampler.</p><h2 id="heading-1424"></h2><h2 id="heading-1425">Training</h2><p>The model was trained on the 'knives and time, a damaged dataset' for ~45 minutes resulting in six epochs.</p>

Files with SHA256: 541bac93b352ac156a5b86b327d980f3b8cb27594cb91990734a7dbe4336b04a