This LoRA is meant to generate more accurate images of the most recent Ford Bronco. It's my first LoRA and first Civitai submission so feedback is definitely welcome! Here's how it was trained:<ul><li>Used kohya on a Windows machine with a 10GB 3080</li><li>Class: SUV</li><li>Instance: frdbrnc</li><li>36 sources images mostly resized to 1152x768 using birme.net</li><li>Used GIT captioning with hand-edits to add things like "3/4 view", "side view", "front view", "hard top", "soft top", "top down" and also added "ford bronco" to each caption file.</li><li>Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/4201/realistic-vision-v60-b1">Realistic Vision V6.0 B1 - V5.1 (VAE) | Stable Diffusion Checkpoint | Civitai</a></li><li>60 repeats, 6 Epochs</li></ul>Tips:<ul><li>I get great results with DPM++ SDE Karras, 4-6 CFG, 30-70 steps</li><li>0.6 LoRA strength</li><li>768x512 or 768x768 helps ensure you don't get a cropped vehicle</li><li>Seems to play nicely with other LoRAs</li><li>RealisticVision, revAnimated, and CyberRealistic seem to like it</li><li>A simple "ford bronco" produces good results but experiment with adding the instance/class strings of 'frdbrnc' and/or 'SUV' as well</li></ul>Other Notes:<ul><li>Only problem seems to be a halfway interpretation of a grille guard bar. Just experiment with different step counts and it should go away without too much trouble. </li></ul>

Files with SHA256: 6539934820d8a67caaac00d26c96a3d0f44fceab8e6ebc6c814e817aa9be88a4