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

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

Work in progress.

This model never got a chance to shine, being eclipsed by the DreamlikeDiffusion, DreamlikeAnime and DreamlikePhotoReal2 models, called "obsolete" and pulled under the rug, with some people being unable to use it in modern software that rejects the ckpt format. Until now as I'm releasing the safetensors version. DreamlikePhotoreal.safetensors has the 840KVAE baked in for better details and contrast.

Check its license at the original page: https://huggingface.co/dreamlike-art/dreamlike-photoreal-1.0

Downloads last month
17
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support