import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("alvdansen/manga-soup")
prompt = "A cyborg girl with metallic limbs and a holographic interface projected from her wrist, wearing a sleek, silver bodysuit"
image = pipe(prompt).images[0]Manga Soup
- Prompt
- A cyborg girl with metallic limbs and a holographic interface projected from her wrist, wearing a sleek, silver bodysuit
- Negative Prompt
- bad, messy, ugly
- Prompt
- A woman with bright pink hair styled in a bob cut
- Prompt
- A young man with tousled brown hair and green eyes, wearing a casual hoodie and jeans, sitting at a coffee shop with a laptop
- Negative Prompt
- bad, messy, ugly
- Prompt
- A tiny dragon with butterfly wings, perched on a daisy
Model description
Honestly, just another variation on a cartoon style that has some anime and manga inspo behind it. I think this one does better with shorter prompts.
This is for fun and research - if you would like commercial access please contact me.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 6
Model tree for alvdansen/manga-soup
Base model
stabilityai/stable-diffusion-xl-base-1.0