How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Yntec/SinkOrSwim", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

Sink Or Swim

A mix of Kitsch-In-Sync v2 and Generate Me! to maximize the SOUL!

Samples and prompts:

Samples 768

(Click for larger)

Top left: pretty cute little girl sitting on a giant lemon themed hamburger, high quality

Top right: Father with little daughter holding Coca Cola. Santa Claus sitting with a pretty cute girl, Art Christmas Theme by Haddon_Sundblom and Gil_Elvgren

Bottom left: Baby girl with a giant basket full of cherries, high quality, grass by wess anderson

Bottom right: an illustration of a baby porcupine with headphones holding an ribbon umbrella in the rain

Original pages:

https://civitai.com/models/142552?modelVersionId=163068 (Kitsch-In-Sync (...and a bag of chips, by Xenos) v2.0)

https://huggingface.co/Yntec/GenerateMe

Recipe:

  • SuperMerger Weight sum Train Difference Use MBW 0,1,1,0,1,0,1,0,0,0,0,1,0,1,1,1,1,1,1,1,0,1,0,0,0,0

Model A:

Kitsch-In-Sync v2

Model B:

Generate Me!

Output Model:

SinkOrSwim

Easter egg:

Sample 512

Downloads last month
15
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for Yntec/SinkOrSwim

Merge model
this model

Spaces using Yntec/SinkOrSwim 54