coreml stable-diffusion text-to-image

Core ML Converted Model:

<br>

sweetMix-fp16-v21_cn:

Source(s): CivitAI<br>

Sweet-mix v2.1 FP16 VAE

Sweet-mix is the spritual succesor to my older model Colorful-Plus.

What sweet-mix improves compared to my older model is probably everything. Seriously, check it out. I think it's really neat.

MUST-HAVES FOR GREAT IMAGE GENERATION LIKE IN THE SAMPLE IMAGES:

This negative prompt: extra fingers, fewer fingers, bad-hands-5, by bad-artist, (bad eyes:1.2), (misfigured pupils:1.2), (bad clothing:1.3), (undetailed clothing:1.3), ng_deepnegative_v1_75t, verybadimagenegative_v1.3, (nonsensical backrounds:1.2), (bad backrounds:1.2), (bad shadows:1.2), (bad anatomy:1.1)

These textual inversions:

VAE

Clip skip: 2

And a great imagination :)

Tensor.art link - free online generation

Models that went into this merge:

Normal line-up:

Anything-v4.5

AbyssOrangeMix 3

Protogen

CitrineDreamMix (probably)

Peachmixs

Sardonyx-Blend (introduced in v1.1)

Meinahentai (introduced in v1.2)

IvoryOrangemix (introduced in v1.3)

MixPROV4 (introduced in v1.4)

Daintymixhentaimodel (introduced in v1.4)

Jasminiquemix (introduced in v1.5)

Sirenmix (introduced in v1.6)

bbmixluci (introduced in v1.6)

Sardonyx-Blend Redux (introduced in v1.6)

IceRealistic (introduced in v1.6)

Another blend i made consisting of multiple nsfw models (introduced in v1.7)

Calico Mix (introduced in v1.9)

Baka diffusion (introduced in v2.1)

Flat line-up:

Sweet-mix v1.7 (introduced in v1.8-flat)

ACMAR G Mix (introduced in v1.8-flat)

GOTTA MIX (introduced in v1.8-flat)

Anylora screencap (introduced in v2.0-flat)<br><br>

image

image

image

image