AyoniMix版本AyoniMix V3 (ID: 6765)

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

描述:

New version with more stylization to it and capable of even higher detail more easily. I used merge block to try and get some of the styling of Pastel-Mix and the lighting effects from AbyssOrange while simultaneously toning down the "glow" effect of the latter.

All example images were generated without any hypernetworks, embeds, loras, or inpainting. Everything was genned with high res fix set to 1.5 resize with latent upscale, then upscaled again using SD upscale in img2img.

Used SD 1.5 VAE

I'd highly recommend Pastel-Mix, it has a fantastic style to it and prompting a great looking image is super easy.

https://civitai.com/models/5414/pastel-mix-stylized-anime-model

训练词语: