<a target="_blank" rel="ugc" href="https://civarchive.com/articles/13148/note-about-working-with-the-ponyv6-model">[ NOTE 📌] about working with the PonyV6 model.</a>Weight: 0:8-1<ul><li>Weight: 0:8 - in my opinion, this allows you to follow the text more accurately in promt, but the style is not very accurately conveyed.</li><li>Weight: 0:95 - almost perfectly conveys the style.</li><li>Weight: 0:98 - a result that satisfies me in terms of style transfer.</li></ul>⚠️ Dear friends, do not be offended if your generated image that does not match the style is removed from the examples.ANDXL v1.0 - artist's style: Trigger: andxlWeight: 0:8<ol><li>Prompt: score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up,</li><li>Negative prompt:<ol><li>none</li><li>3D, simple background, score_6, score_5, score_4, censored, monochrome, text, watermark,(worst quality, low quality), blurry face, clipping, bad face, deformed hands, (bad hands), bad feet, extra toes, extra fingers, heels, strabismus.</li></ol></li></ol>TEMXL v1.0 - weight: 0:8<ul><li>Prompt: score_9, score_8_up, score_7_up, score_6_up,</li><li>Negative prompt: none - any negative word can ruin the style.Note: for some reason, the image generation on the site in this style does not match what you see.</li></ul>SPMXL v1.0<ul><li>In certain situations, employ a single quality tag of score_9.Negative prompt:</li><li>score_5_up, score_4_up, 3d</li><li>score_5_up, score_4_up, 3d, blender, (outline:2)In some cases, avoid using negative words to convey style.</li></ul>INCNXL v1.0 - this is one of the branches of Incase<ul><li>This is one of the branches of Incase, which was created with different dim and alpha parameters to test how the size of the output data affects after training.</li><li>There are 3 files of different sizes in the archive.Negative prompt:</li><li>score_6_up, score_5_up, score_4_up, 3d</li><li>3d, blender</li></ul>

Style's - P6...

Files with SHA256: 192bd5c4c8f6e0dc799f83f2a88c7a17f9b19b48cd9305c7eec2e6dfd25d97b2