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
FAQ
Comments (7)
Looks great, I look forward to testing it out later tonight!
Very interesting! i look forward to testing this out! Thank you for sharing.
If you can, would love to have the full unpruned size if you have it, to try running Dreambooth on this wonderful looking model. Thank you!
I kept having errors adding the float 32 (unpruned) version on here, so I uploaded it to huggingface: https://huggingface.co/Ayoni/AyoniMix_V2/blob/main/AyoniMix%20V2%20Float32.safetensors
Thank you!
Honestly the best all-in-one model right now