coreml stable-diffusion text-to-image

Core ML Converted Model:

Note: This model does not have the unet split into chunks.

AnalogDream3D:

Source(s): CivitAI

It is a Remix Model of the following amazing models:

Analog_diffusion

Dreamlike_photoreal

3DKX_v1.0B

It strongly enhanced the photorealistic power from Analog and DreamLike, and with a good merged method for 3DKX_v1, it come out with the ability for higher resolution ouputs like 1024*768 and more+ !!

you can try to use it to output some of scene,it can handled a lot of describition like hugging and kiss.

I think ,by this merged method, we might try to UPGRADE a large numbers of old model to a higher resolution output level. I also try this recipe with other models, some works, some failed.