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

Painted Miniature

retrained with lion and improved captions.The outputs are more realistic and stable. The weight is 0.5-0.8. A model comparison is added.

Files with SHA256: 5bf44127b906a21a1e2c98d2a8245b288f2306825589715db362f49232d2f371