{ "model_id": 543369, "model_name": "Mikoshi [Pony]", "model_description": "
\n \n \n \n \n Best settings:\n \n \n \n \n
\n\n \n \n Sampling Method:\n \n Euler A or Euler A SGMUniform\n \n -\n \n \n you can mess around with this\n
\n\n \n \n Sampling Steps:\n \n 20 ~ 60\n \n depending on your sampling method\n
\n\n \n \n Hires. fix:\n \n Enabled\n \n
\n\n \n \n Hires Steps:\n \n 15 ~ 30\n \n
\n\n \n \n Upscaler:\n \n 4x_NMKD-YandereNeoXL_200k\n \n - You can test others.\n
\n\n \n \n Denoise Strength:\n \n 0.4\n \n
\n\n \n \n Upscale by:\n \n Preferably x2\n \n
\n\n \n \n CFG Scale:\n \n 6 ~ 9.5\n \n
\n\n \n \n Clip Skip:\n \n \n \n 2\n \n
\n\n
\n\n \n \n \n \n Important:\n \n \n \n \n
\n\n \n \n Positive prompt\n \n \n must contain:\n \n \n score_9,score_8_up,score_7_up,\n \n \n
\n\n \n \n Negative prompt\n \n \n can be empty or contain the default pony negatives.\n
\n\n
\n\n The promting format from Pony Diffusion V6 works well:\n
\nscore_9, score_8_up, score_7_up, just describe what you want, tag1, tag2
\n\n If you haven't already, I highly reccomend reading through the\n \n Pony Diffusion V6 XL model description.\n \n
\n\n
\n\n
\n\n I use\n \n Forge\n \n as my main UI because it has so many optimizations for running XL/Pony models on lower end GPU's despite me having an RTX 4090, generations are alot smoother. I'm not sure how this model performs on other UI's.\n
\n\n
\n\n I haven't done much testing. If there is anything amiss, please let me know. Feedback is always appreciated :).\n
\n\n Post results and, most importantly, have fun!\n
\n", "model_url": "https://civitai.com/models/543369", "model_type": "Checkpoint", "model_tags": [ "anime", "base model", "girls", "ponyxl", "ponyv6" ], "download_link": "https://civitai.com/api/download/models/822931", "preview_image_url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f1a7fa5b-d5b2-49fb-8ff5-3798dd04a0df/width=450/28526922.jpeg", "model_version_id": null, "model_version_download_link": null, "model_version_image_url": null }