import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("parsee-mizuhashi/mangaka", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Mangaka
Stable Diffusion model designed for generating anime/manga panels.
- Developed/Trained by: Parsee Mizuhashi
- Trained on: yGPU cluster (1xRTX 3060)
- Finetuned from model: hnnng-dx
Tips:
- Follow hnnng-dx's prompting tips,
- Add
greyscale monochrometo prompts.
- Downloads last month
- 54