<h3 id="heading-878">Make a better picture!</h3>This LoRA will enhance your image in the following ways:<ol><li>More details. You will notice that eyes, skin and hair have more details.</li><li>Sharpening. The image will have a sharper, crisper feel.</li><li>Better Composition! This LoRA was trained on professional photographs, which were cropped to improve composition. That helps in improving the composition.</li></ol>This LoRA was trained in the following way:<ol><li>Images were downloaded from Pexels website. The images were carefully selected to be sharp and have high details.</li><li>These images were cropped to improve composition and remove extra objects.</li><li>The images were processed. This meant image sharpening and enhancing image saturation wherever needed.</li><li>The images captions were generated using the KohyaSS Gui. I captioned the images two times, once using the BLIP model and the WD14 model. Then I merged the captions using a python script.</li><li>I used KohyaSS GUI to train the LoRA. Since I have a RTX 3060, I was barely able to train a LoRA by following the excellent tutorial by <a target="_blank" rel="ugc" href="https://civarchive.com/user/SECourses">https://civarchive.com/user/SECourses</a></li><li>I tested the LoRA with ComfyUI.</li></ol>

Better Picture, More Details LoRA

SDXLHighDetail_v6-000005.safetensors

v6.4

v1.0

This LoRA will enhance your image in the following ways:<ol><li>More details. You will notice that eyes, skin and hair have more details.</li><li>Sharpening. The image will have a sharper, crisper feel.</li><li>Better Composition! This LoRA was trained on professional photographs, which were cropped to improve composition. That helps in improving the composition.</li></ol>How to use itJust include the LoRA with the SDXL Base model, and use:Clip Skip: 1, ENSD -1This LoRA was trained in the following way:<ol><li>Images were downloaded from Pexels website. The images were carefully selected to be sharp and have high details.</li><li>These images were cropped to improve composition and remove extra objects.</li><li>The images were processed. This meant image sharpening and enhancing image saturation wherever needed.</li><li>The images captions were generated using the KohyaSS Gui. I captioned the images two times, once using the BLIP model and the WD14 model. Then I merged the captions using a python script.</li><li>I used KohyaSS GUI to train the LoRA. Since I have a RTX 3060, I was barely able to train a LoRA by following the excellent tutorial by https://civitai.com/user/SECourses</li><li>I tested the LoRA with ComfyUI.</li></ol>

Files with SHA256: b44103ed90583614597e4daf45f5ba7c875e4565fcbfe9c830068b669dca2c13