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
Only use for inpainting or outpainting
FAQ
Comments (5)
very nice , are there any tuts where one can learn how to use Prompt and negative Prompts parameters.
thanks
can you upload all versions to hugginface pls :)
could help on colab
Really underrated mix. Excellent results. Can´t stop experimenting. Seems to have a light bias to girls, but unsure about that. Hope to see more of you!
Maybe you should get a Ko-fi Account? Would like to donate some bucks for your work. :)
I think stable diffusion itself has a light bias towards girls
It's an interesting model and got some nice results also with photo-realism and using some TI too. Any plans to update this? it's been some months and with the new models out there, a merge could be very nice :)
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.