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/HassanBlend1512VAE", dtype=torch.bfloat16, device_map="cuda")

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

Hassan 1.5.1.2

This model with the MoistMixV2 VAE baked in.

Sample and prompt:

Sample

concept art of CUTE girl in a pixel, chibi character, DETAILED EYES, key visual, summer day, magazine ad, 1940, iconic, highly detailed, digital painting, artstation, concept art, sharp focus, in harmony with nature, streamlined, hyperrealism by makoto shinkai and akihiko yoshida and wlop

Original page:

https://civitai.com/models/1173?modelVersionId=4635 (download the Full 6GB file at https://civitai.com/api/download/models/4635?type=Model&format=PickleTensor&size=full&fp=fp16 - the prunned ones are broken and caused all the 1 star reviews)

Downloads last month
31
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Spaces using Yntec/HassanBlend1512VAE 56