The result of many merges aimed toward making extremely highly detailed images. This can do realistic content, but I prefer to make stylized stuff so that aspect has not been extensively tested.
All example images were generated without any hypernetworks, loras, or inpainting. Everything was genned without high res fix, then upscaled using SD upscale in img2img.
Used SD 1.5 VAE
Unpruned float 32 version of AyoniMix V2 on huggingface:
https://huggingface.co/Ayoni/AyoniMix_V2/blob/main/AyoniMix%20V2%20Float32.safetensors
Description
I strongly recommend using badprompt v2 and easynegative, as I made this model mix with those two embeds in mind. I made a mix of examples with and without them. I'll upload more when I get a chance, been having trouble all day with the uploads failling.
https://huggingface.co/datasets/Nerfgun3/bad_prompt/blob/main/bad_prompt_version2.pt
https://huggingface.co/datasets/gsdf/EasyNegative/blob/main/EasyNegative.safetensors