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/Cryptids", dtype=torch.bfloat16, device_map="cuda")

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

Cryptids

The Cryptids LoRA by RIXYN at 1.0 strength merged in the HellSKitchen model to maximize its style! It has the MoistMixV2VAE baked in.

So it's mixed with two models, HELLmix by Barons and Kitsch-In-Sync by iamxenos.

Comparison:

Comparison

(Click for larger)

Sample and prompt:

Sample

Masterpiece, Best Quality, highres, fantasy, official art, kitten, grass, sky, scenery, Fuji 85mm, fairytale illustration, colored sclera, black eyes, perfect eyes, happy, cute, cat, whiskers, pawpads, claws, furry, plush, soft, perfect, tail, christmas lights, christmas tree, christmas ornaments, warmth

Model comparison:

4 models compared

(Click for larger)

Sample image by digiplay:

Sample

8k Angel sky

Original pages:

https://civitai.com/models/64766/cryptids?modelVersionId=69407 (Cryptids LoRA)

https://civitai.com/models/142552?modelVersionId=163068 (Kitsch-In-Sync)

https://huggingface.co/Yntec/HELLmix

https://huggingface.co/Yntec/HellSKitchen

Downloads last month
46
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for Yntec/Cryptids

Merge model
this model
Finetunes
1 model
Merges
1 model

Spaces using Yntec/Cryptids 47