A 100 random, high-res image set, pre-captioned for machine learning (LORA) training.( 217 MB ZIP file, pre-captioned for 512x512, 768x768 and 1024x1024, with captions and base 2048x2048 images included)<hr />Themes include:<ul><li>People</li><li>Transportation</li><li>Landscapes</li><li>Food &amp; Objects</li></ul>Contents:<ul><li>2048x2048 resolution upscaled base images without captions</li><li>1024x1024 resolution images with captions</li><li>768x768 resolution images with captions</li><li>512x512 resolution images with captions</li><li>All stand alone text captions</li></ul>Additional Information:<ul><li>Images have been generated in ComfyUI with SDXL Checkpoint "jib-mix-realistic-xl".Link: <a target="_blank" rel="ugc" href="https://civarchive.com/models/194768/jib-mix-realistic-xl">https://civarchive.com/models/194768/jib-mix-realistic-xl</a>(Generation mostly with plain background for maximum object focus)</li><li>Captions have been added by WD14 captioning and include prompt 'l0r4' as a prompt keyword.(replace this keyword to your liking)</li></ul><ul><li>This dataset has been used to train my "SD 15 Pixelized Art Lora".<a target="_blank" rel="ugc" href="https://civarchive.com/models/523529/sd-15-pixelized-art-lora-style">https://civarchive.com/models/523529/sd-15-pixelized-art-lora-style</a>(Made by putting a pixelization and low res filter on the images of this dataset)</li></ul><hr />Please leave a like and comment if you used this for any (Lora) training.I'd be very interested to view any content being generated from training this content :)

Files with SHA256: 8034c9f59294cc075205cf2780c746aa2c122e481f91176f23ddb5af27fc7f07