This lora was trained for 90 epochs using onetrainer on a dataset of 63 high-res frames from Twin Peaks, Mulholland Drive, Blue Velvet etc. It focused on color grading, so no trigger words are required. For caption-based prompting I use qwen captioner to generate prompts for examples. Works normally on 1.0-1.2, you can mix it with another realism loras as well.<a rel="ugc" href="https://huggingface.co/olesheva/DavidLynch-Qwen-LoRA"><span style="background-color:oklch(0.9902 0.004 106.47);color:oklch(0.3039 0.04 213.68);font-family:fkGroteskNeue, ui-sans-serif, system-ui, -apple-system, &quot;system-ui&quot;, &quot;Segoe UI&quot;, Roboto, &quot;Helvetica Neue&quot;, Arial, &quot;Noto Sans&quot;, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;, &quot;Segoe UI Symbol&quot;, &quot;Noto Color Emoji&quot;, &quot;Hiragino Sans&quot;, &quot;PingFang SC&quot;, &quot;Apple SD Gothic Neo&quot;, &quot;Yu Gothic&quot;, &quot;Microsoft YaHei&quot;, &quot;Microsoft JhengHei&quot;, Meiryo;font-size:16px">Hugging Face</a>

Files with SHA256: 07911cfb1ff9b1535b1bdc17cfae3d86f773fd19cc493b30f64f3105691326ef