kpsss34/Zitster

I trained this model with a Custom diffuser library with a dataset of over 5000 images. I thought it wasn't good enough for my needs, but due to budget constraints, I've paused development for a while. This model is NSFW-compatible and has revealed some things that were still unclear on the base model.

import torch
from diffusers import ZImagePipeline

pipe = ZImagePipeline.from_pretrained(
    "kpsss34/Zitster",
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=False,
)
pipe.to("cuda")
# pipe.enable_model_cpu_offload()

prompt = "a naked woman ..."

image = pipe(
    prompt=prompt,
    height=1024,
    width=1024,
    num_inference_steps=9,
    guidance_scale=0.0,
    generator=torch.Generator("cuda").manual_seed(42),
).images[0]

image.save("example.png")