This is not my model but it's not uploaded here yet. It's Waifu Diffusion but trained on SD2.1 768 with realism and anime so it's capable of both!For best performance, you must use the WD VAE with WD 1.5. The VAE can be found here: <a target="_blank" rel="ugc" href="https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt">https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt</a>Release Notes:<a target="_blank" rel="ugc" href="https://cafeai.notion.site/WD-1-5-Beta-2-Release-Notes-2852db5a9cdd456ba52fc5730b91acfd">https://cafeai.notion.site/WD-1-5-Beta-2-Release-Notes-2852db5a9cdd456ba52fc5730b91acfd</a>WD 1.5 is released under the Fair AI Public License 1.0-SD<a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/"> </a>(<a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">https://freedevproject.org/faipl-1.0-sd/</a>). If any derivative of this model is made, please share your changes accordingly. Special thanks to ronsor/undeleted (<a target="_blank" rel="ugc" href="https://undeleted.ronsor.com/">https://undeleted.ronsor.com/</a>) for help with the license.

Waifu Diffusion 1.5 Beta 2 Aesthetic (SD2.1)

waifuDiffusion15Beta2_wd15Beta2.safetensors

WD 1.5 beta 2

This is not my model but it's not uploaded here yet. It's Waifu Diffusion but trained on SD2.1 768&nbsp;with realism and anime&nbsp;so it's capable of both!For best performance, you&nbsp;must&nbsp;use the WD VAE with WD 1.5. The VAE can be found here:&nbsp;<a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt">https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt</a>Release Notes:<a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://cafeai.notion.site/WD-1-5-Beta-2-Release-Notes-2852db5a9cdd456ba52fc5730b91acfd">https://cafeai.notion.site/WD-1-5-Beta-2-Release-Notes-2852db5a9cdd456ba52fc5730b91acfd</a>WD 1.5 is released under the Fair AI Public License 1.0-SD<a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://freedevproject.org/faipl-1.0-sd/">&nbsp;</a>(<a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://freedevproject.org/faipl-1.0-sd/">https://freedevproject.org/faipl-1.0-sd/</a>). If any derivative of this model is made, please share your changes accordingly. Special thanks to&nbsp;ronsor/undeleted&nbsp;(<a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://undeleted.ronsor.com/">https://undeleted.ronsor.com/</a>) for help with the license.Example Negative Prompt:lowres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts)), deleted, old, oldest, ((censored)), ((bad aesthetic)), (mosaic censoring, bar censor, blur censor)

Files with SHA256: 3ca00ea7cb1b4d12ab25ffbe16a4c8abb65334ffc196e641f1ea849582d7c622