metadata
license: mit
How to run
This pipeline should be run together with https://huggingface.co/warp-diffusion/wuerstchen:
import torch
from diffusers import WuerstchenDecoderPipeline, WuerstchenPriorPipeline
device = "cuda"
dtype = torch.float16
num_images_per_prompt = 2
prior_pipeline = WuerstchenPriorPipeline.from_pretrained(
"warp-diffusion/wuerstchen-prior", torch_dtype=dtype
).to(device)
decoder_pipeline = WuerstchenDecoderPipeline.from_pretrained(
"warp-diffusion/wuerstchen", torch_dtype=dtype
).to(device)
caption = "A captivating artwork of a mysterious stone golem"
negative_prompt = ""
prior_output = prior_pipeline(
prompt=caption,
height=1024,
width=1024,
negative_prompt=negative_prompt,
guidance_scale=4.0,
num_images_per_prompt=num_images_per_prompt,
)
decoder_output = decoder_pipeline(
image_embeddings=prior_output.image_embeddings,
prompt=caption,
negative_prompt=negative_prompt,
num_images_per_prompt=num_images_per_prompt,
guidance_scale=0.0,
output_type="pil",
).images