AniMerge - Pony XL

You can find my model in MAGE:<a target="_blank" rel="ugc" href="https://www.mage.space/play/da17e5d1d19e369e1526473d6e3f32fe">https://www.mage.space/play/da17e5d1d19e369e1526473d6e3f32fe</a>-&gt; I have to admit that it was harder than expected to do this AniMerge, to find the most correct settings it took me 4 days of attempts and over 2000 images created.In the end I have to say that it is giving me satisfaction and I have reached that level of semi-realism that I had set myself. The downside is that in the prompting it is a bit "hard".Having said that I leave you the settings.SPECIAL NOTE: I recommend, change the default setting of ADetailer to 0.5 the denoising strength and as resolution 768x768 px.VERY IMPORTANT: If in your prompt there is a conflict (like, for example, [full body photo] and in another part there is [face photo], or something that the model can't understand, this can cause image generation to fail. So, pay close attention to your prompts<ul><li>VAE: a special VAE is already included, you don't need it - (Thanx to <a target="_blank" rel="ugc" href="https://civitai.com/user/nuaion">nuaion</a>)<ul><li>Clip skip: 2 (still testing)</li><li>CFG: 5.5~6</li><li>Steps: 30</li><li>Sampling favorite method: DPM++ 2M</li><li>Scheduler: SGM Uniform</li><li>EXAMPLE OF GENERAL PROMPT:POSITIVE PROMPT: score_9, score_8_up, score_7_up, (RAW photo), (type of shot)(Subject), [the description], (background), more details.</li><li>NEGATIVE PROMPT: score_6, score_5, score_4, cartoon, painting, illustration, 3D rendering, CG, Unreal engine, fake, plastic, doll, ugly, old, fat, grayscale</li><li>EXAMPLE: (RAW photo), (upper body photo), (Native American Woman), 20yo, slim, skinny, adorned with traditional regalia and feathers, standing, (Canyon background), (intricate details), (dynamic angle), (cinematic lights), seductive, innocent, (realistic skin:1.4), slim, skinny, detailed Native American tribal dress, sharp, (analog film grain)</li></ul></li></ul>

animergePonyXL_v10.safetensors

v1.0

Files with SHA256: d410f21a4d64bbbddae5f80185ae50fe76eae7d62aaab72a07a41cdfc3980a5a