<h3 id="training-experiment-with-a-single-image-fz0286nll">Training Experiment with a Single Image</h3>If you're interested: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/3021/one-image-is-all-you-need">One Image Is All You Need | Civitai</a>This model was not trained on real imagery of a living, or deceased, person, or depicts a character portrayed by a real-life actor or actress.Image used in training:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6a86f0f3-8212-43eb-a0c4-e6a1da41704f/width=525/6a86f0f3-8212-43eb-a0c4-e6a1da41704f.jpeg" />Experience with PuliDI couldn't get any satisfying results with PuliD, no matter how much tweaking I did. So, I decided to train with just one image to see if I could get decent results.Results &amp; ObservationsI'm actually very satisfied with the results. Of course, there are some differences compared to LoRAs trained on multiple images:<ul><li>It doesn’t work as well with overtrained LoRAs.</li><li>Most likely more stiff with facial expressions</li></ul>Flexibility SettingsFeb 26: Actually just set the strength to what you think is right, it depends on what you're doing. You can go up to 1.<ul><li>For more flexibility: Set strength to 0.7 and use the trigger word "ry4n".</li><li>For more likeness: Set strength to 0.85 and use it without "ry4n".</li></ul>CFG Settings<ul><li>Without any LoRAs: Set CFG to 2.7-2.9.</li><li>When using this with other LoRAs: Set CFG to 2.7-3.3. I usually keep it near 3. Really depends on what im doing.</li></ul>Trigger Word Considerations<ul><li>I include "light gray eyes" in the trigger, but sometimes it’s better not to use it because it can push the image too much.</li><li>Example: When using this LoRA with an ahegao LoRA, I don’t recommend including "light gray eyes" in the prompt.</li><li>Note: "Light gray eyes" wasn't actually a caption in the dataset—it’s just something that helps.</li></ul>

Files with SHA256: d42d731e18d7dc5a0be29420ae622f1e2f079c23e3584c2121f2e2a3c2087461