This model lets you add faces to things. The model may produce slightly scary or cursed results sometimes, be warned!<h2 id="usage-ye41m7ckl">Usage</h2>Use the trigger word: "Pareidolia" along with the LoRA to activate it.Example prompt: Pareidolia a pizza that looks like a face &lt;lora:Pareidolia:1&gt;I've found that most settings work well with this model. No special samplers or CFG-scale.The model may work without this prompting structure, but this is how it was trained and how I get good results.The model works best with square image ratios, but can also work in others.Note:I may be using the following extensions in the reference images: FreeU or ADetailer / Face Editor. I may also be using a specific Hires Checkpoint (swaps to another model when doing the hires steps). If your results don't match mine exactly, this may explain why.<h2 id="tips-and-tricks-pr2ypji7l">Tips and tricks</h2>Below are some tips and tricks for how to get even more out of the model.<ul><li>Keep your prompt simple.</li><li>Add suffixes mentioning that you want something to look like something, see list below:</li></ul><pre><code>... that looks like a face
a face made out of ....
... with a smiling face on it
... with a face on it</code></pre><a target="_blank" rel="ugc" href="https://civarchive.com/articles/2138/lora-training-data-upload-to-civitai">Link to Training Data</a>Like it?<a target="_blank" rel="ugc" href="https://ko-fi.com/mnemic">https://ko-fi.com/mnemic</a><a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/mnemic">https://www.buymeacoffee.com/mnemic</a>

Pareidolia Concept SDXL - Is that a face I see?

PareidoliaSDXL.safetensors

Pareidolia Concept Training Data v1.zip

v1.0

This model lets you add faces to things. The model may produce slightly scary or cursed results sometimes, be warned!<h2 id="usage-ye41m7ckl">Usage</h2>Use the trigger word: "Pareidolia" along with the LoRA to activate it.Example prompt: Pareidolia a pizza that looks like a face &lt;lora:Pareidolia:1&gt;I've found that most settings work well with this model. No special samplers or CFG-scale.The model may work without this prompting structure, but this is how it was trained and how I get good results.The model works best with square image ratios, but can also work in others.Note:I may be using the following extensions in the reference images: FreeU or ADetailer / Face Editor. I may also be using a specific Hires Checkpoint (swaps to another model when doing the hires steps). If your results don't match mine exactly, this may explain why.<h2 id="tips-and-tricks-pr2ypji7l">Tips and tricks</h2>Below are some tips and tricks for how to get even more out of the model.<ul><li>Keep your prompt simple.</li><li>Add suffixes mentioning that you want something to look like something, see list below:</li></ul><pre><code>... that looks like a face
a face made out of ....
... with a smiling face on it
... with a face on it</code></pre><a target="_blank" rel="ugc" href="https://civitai.com/articles/2138/lora-training-data-upload-to-civitai">Link to Training Data</a>Like it?<a target="_blank" rel="ugc" href="https://ko-fi.com/mnemic">https://ko-fi.com/mnemic</a><a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/mnemic">https://www.buymeacoffee.com/mnemic</a>

Files with SHA256: f021728d3b0ef9a89075a31925a0c36e827f8dd7ee882e8ef2c8a01ee76c8d30