\n \n Dataset\n \n :50k AI-generated images from Aibooru and Pixiv + 10k images from Danbooru\n
\n\n
\n\n \n Prompts\n \n
\n\n people, characters, copyright, style, general tags, rating, masterpiece, best quality, good quality, newest\n
\n\n \n Negative Prompts\n \n
\n\n lowres, worst quality, bad quality, bad anatomy, sketch, jpeg artifacts, signature, watermark, old, oldest\n
\n\n
\n\n \n Base model:\n \n \n \n NoobAI-XL (NAI-XL) V-pred-1.0-Version\n \n \n
\n\n Use v-prediction and Zero Terminal SNR.\n
\n\n
\n\n For information on v-prediction and how to use it in ComfyUI, refer to the\n \n NOOBAI XL Quick Guide\n \n by L_A_X.\n
\n\n As of November 20, checkpoints supporting v-prediction are not available for use in stable-diffusion-webui.\n
\n\n Outside of ComfyUI, you can use the\n \n webui's dev branch\n \n (likely requiring a .yaml file for each checkpoint) or\n \n Forge\n \n and\n \n reForge\n \n .\n
\n\n Additionally, make sure to select \"Zero Terminal SNR\" under Settings → Sampler parameters → Noise schedule for sampling.\n
\n\n
\n\n \n Base model:\n \n \n \n NoobAI-XL (NAI-XL) Epsilon-pred 1.1-Version\n \n \n
\n\n
\n\n \n \n v-pred_v0.1\n \n \n
\n\n \n Base model:\n \n \n \n NoobAI-XL (NAI-XL) V-pred-0.6-Version\n \n \n
\n\n
\n\n \n \n v3.0\n \n \n
\n\n \n Base model:\n \n \n \n NoobAI-XL (NAI-XL) Epsilon-pred 1.0-Version\n \n \n
\n\n
\n\n \n \n v2.1\n \n \n
\n\n \n Base model:\n \n \n \n NoobAI-XL\n \n \n \n (\n \n noobaiXLNAIXL_epsilonPred075 x 0.7 + noobaiXLNAIXL_epsilonPred05Version x 0.3)\n
\n\n
\n\n \n \n v2.0\n \n \n
\n\n \n Base model:\n \n \n \n NoobAI-XL (NAI-XL) Epsilon-pred 0.5-Version\n \n \n
\n
\n \n \n v1.0\n \n \n
\n \n Base model:\n \n \n \n Illustrious-XL-v0.1\n \n \n
\n After training, this model merged\n \n Lucereon\n \n into the U-net.\n
\n\n (0,0.3,0.25,0.2,0.15,0.1,0.15,0.2,0.25,0.3,0.3,0,0.05,0.15,0.25,0.3,0.25,0.15,0.05,0)\n
\n\n
\n\n
\n\n
\n \n License\n \n