[SD 1.5][LORA]Painted Miniature v3.0
<p>A lora model dedicates to generate painted miniature figurine. The lora model is trained with SD1.5 base model. The example images are generated with <a target="_blank" rel="ugc" href="https://civitai.com/models/5062/clarity"><strong>Clarity </strong></a>and <a target="_blank" rel="ugc" href="https://civitai.com/models/3816/protogen-x53-photorealism-official-release"><strong>Protogen x5.3 (Photorealism)</strong></a><strong> </strong>ckpt models. It should work fine with other fine tune SD1.5 originated ckpt models.</p><h3>User suggestions:</h3><p>The following setup gives me satisfied outputs.</p><p>trigger words: painted miniature, pmini style, on a base (optional: to add a plate under miniatures' feet)</p><p>lora weight: 0.6-0.8</p><p>Sampler: Euler a for 100 steps</p><p>W*H: 768*1024</p><p>CFG scale: 5-7</p><p>Negative emb. (optional): <a target="_blank" rel="ugc" href="https://huggingface.co/datasets/Nerfgun3/bad_prompt"><strong>bad_prompt</strong></a></p><p>Hires. fix: R-ESRGAN General WDN 4xV3, steps 20, denoising strength 0.4</p><h3>Prompt example 1: miniatures in themed background</h3><p><u>positive prompt</u>: a <strong>painted miniature</strong> of a male human thief <strong>on a base</strong>, in a lost ruin, <strong>pmini style</strong>, character design, studio lighting, (extremely detailed 8k wallpaper), Intricate, High Detail figurine, Sharp focus, dramatic, photorealistic art <<strong>lora:Painted_Miniature_i_v3.0:0.6</strong>></p><p><u>negative prompt</u>: headpiece, (bad_prompt:0.8), cartoon, (bad art:1.2), (deformed:1.2),(close up:1.2),(b&w:1.2),blurry, (duplicate:1.3), (mutilated:1.2), (out of frame:1.2),blurry, (disfigured:1.3), closed eyes</p><p></p><h3>Prompt example 2: high detailed miniatures in plain background</h3><p><u>positive prompt</u>: <strong>pmini style</strong>, <strong>painted miniature</strong> of male human thief, character design, Intricate, High Detail, Sharp focus, dramatic, photorealistic art <strong><lora:Painted_Miniature_i_v3.0:0.6></strong></p><p><u>negative prompt</u>: headpieces, cartoon, (bad art:1.2), (b&w:1.2),blurry, closed eyes, nsfw</p>
页:
[1]