<a target="_blank" rel="ugc" href="https://forms.gle/A9ZmSzRdZrqfVWpx6">Open to Requests</a>A LoRa trained on 4225 images from the mobile game Fire Emblem Heroes. Works well at 1.0 weight, mixes with other LoRa as well, see sample images. I would like to give a huge thanks to Lazy on the discord for all their help with DAdaptation and LoRa training in general. Check out their guide: <a target="_blank" rel="ugc" href="https://civarchive.com/models/77908/lora-lazy-dadaptation-guide">https://civarchive.com/models/77908/lora-lazy-dadaptation-guide</a> The LoRa generally produces art with a style like "full body, standing, black background" My prompt for the sample images was straight forward: Prompt: masterpiece, best quality, &lt;lora:FEH_Concept_v2:1&gt;, black background, simple background, 1girl/1boy, standing, full body, etc... Negative: (worst quality, lowres), blurry, bokeh, depth of field, error, text, speech bubble, artist name, signature, border, sketch I primarily used Hassaku model (NSFW) <a target="_blank" rel="ugc" href="https://civarchive.com/models/2583?modelVersionId=62528">https://civarchive.com/models/2583?modelVersionId=62528</a>, but any NAI-based model should work. The magical particles can be somewhat controlled, see sample images. Weapons are very hit or miss. You can also generate 2 people, 2girls/2boys. v1.0 had problems so don't ask about it (you can see in the sample images)

Fire Emblem Heroes (FEH) Style/Concept

FEH_Concept_v2.safetensors

v2.0

&lt;p&gt;&lt;a target=&#34;_blank&#34; rel=&#34;ugc&#34; href=&#34;https://forms.gle/A9ZmSzRdZrqfVWpx6&#34;&gt;&lt;strong&gt;Open to Requests&lt;/strong&gt;&lt;/a&gt;&lt;/p&gt;&lt;p&gt;A LoRa trained on 4225 images from the mobile game Fire Emblem Heroes.&lt;br /&gt;Works well at 1.0 weight, mixes with other LoRa as well, see sample images.&lt;br /&gt;&lt;br /&gt;&lt;strong&gt;I would like to give a huge thanks to Lazy on the discord for all their help with DAdaptation and LoRa training in general. Check out their guide: &lt;/strong&gt;&lt;a target=&#34;_blank&#34; rel=&#34;ugc&#34; href=&#34;https://civitai.com/models/77908/lora-lazy-dadaptation-guide&#34;&gt;&lt;strong&gt;https://civitai.com/models/77908/lora-lazy-dadaptation-guide&lt;/strong&gt;&lt;/a&gt;&lt;br /&gt;&lt;br /&gt;The LoRa generally produces art with a style like &#34;full body, standing, black background&#34;&lt;br /&gt;&lt;br /&gt;My prompt for the sample images was straight forward:&lt;br /&gt;&lt;br /&gt;Prompt:&lt;strong&gt;&lt;br /&gt;&lt;em&gt;masterpiece, best quality, &amp;lt;lora:FEH_Concept_v2:1&amp;gt;, black background, simple background, 1girl/1boy, standing, full body, etc...&lt;/em&gt;&lt;br /&gt;&lt;br /&gt;&lt;/strong&gt;Negative: &lt;strong&gt;&lt;br /&gt;&lt;em&gt;(worst quality, lowres), blurry, bokeh, depth of field, error, text, speech bubble, artist name, signature, border, sketch&lt;/em&gt;&lt;/strong&gt;&lt;em&gt;&lt;br /&gt;&lt;/em&gt;&lt;br /&gt;I primarily used Hassaku model (NSFW) &lt;a target=&#34;_blank&#34; rel=&#34;ugc&#34; href=&#34;https://civitai.com/models/2583?modelVersionId=62528&#34;&gt;https://civitai.com/models/2583?modelVersionId=62528&lt;/a&gt;, but any NAI-based model should work.&lt;br /&gt;&lt;br /&gt;The magical particles can be somewhat controlled, see sample images.&lt;br /&gt;Weapons are very hit or miss.&lt;br /&gt;You can also generate 2 people, 2girls/2boys.&lt;br /&gt;&lt;br /&gt;&lt;br /&gt;v1.0 had problems so don&#39;t ask about it (you can see in the sample images)&lt;/p&gt;

Files with SHA256: b2e117d3173a24a7f5fe96d193bfc0a84aedba4df7512ddbe245c37cf4cbf5dd