AniMerge - Pony XL

Only on Mage, all my models are always available in preview: https://www.mage.space/play/c52ad2e5dc64445989432a3babda7455

My personal page for donation (and where you can buy my model in early preview): Samael1976 Ko-fi page

What's new: I tried to improve the images at all focal levels (portrait, cowbow shot and full body shot). I'm not 100% satisfied yet, but some progress has been made compared to the previous version.

Best CONFIGURATION that I found

VAE: a special VAE is already included, you don't need it - (Thanx to nuaion)Upscaler: 4x-Ultrasharp or 4X NMKD SuperscaleClip skip: 2Width: 768Height: 1344CFG: 5.5Steps: 30Sampling favorite method: DPM++ 2M SDE (More Realistic, but slow) or DPM++ 2M (Less Realistic, but FASTER)Scheduler: KarrasEXAMPLE OF GENERAL PROMPT:POSITIVE PROMPT: score_9, score_8_up, score_7_up, (Type of Shoot), (Subject), the description, (background), more detailsEXAMPLE: score_9, score_8_up, score_7_up, Raw Photo, Cowboy Shot, yorha no. 2 type b, short white hair, black dress, hairband, black gloves, clothing cutout, cleavage cutout, puffy sleeves, long sleeves, black hairband, feather-trimmed sleeves, juliet sleeves, mole under mouth, holding katana, black thighhighs, turtleneck, sunset, rubble in the background, depth of field, dynamic angle, photo realistic:1.4, realistic skin:1.4, fashion photography, sharp, analog film grain, hyperdetailed:1.15NEGATIVE PROMPT: score_6, score_5, score_4, cartoon, painting, illustration, 3D rendering, CG, ugly, old, fat, wide hips, curvy, topless, nude, naked, nsfw, child

I finally found out what causes aDetailer errors and image errors: it's parentheses()

So if you want to avoid face or image generation errors, avoid using (or use them as little as possible) on both the positive and negative prompts

SPECIAL NOTE: I recommend, change the default setting of ADetailer to 0.45 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