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("leonel4rd/Comicflux")
prompt = "UNICODE\u0000\u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000c\u0000o\u0000m\u0000i\u0000c\u0000_\u0000S\u0000D\u0000X\u0000L\u0000_\u0000v\u00001\u0000:\u00000\u0000.\u00005\u0000>\u0000,\u0000 \u0000(\u0000a\u0000n\u0000i\u0000m\u0000e\u0000 \u0000c\u0000o\u0000l\u0000o\u0000r\u0000i\u0000n\u0000g\u0000:\u00000\u0000.\u00008\u0000)\u0000,\u0000 \u0000l\u0000a\u0000n\u0000d\u0000s\u0000c\u0000a\u0000p\u0000e\u0000,\u0000 \u0000m\u0000a\u0000n\u0000g\u0000a\u0000_\u0000a\u0000r\u0000t\u0000,\u0000 \u0000i\u0000n\u0000i\u0000p\u0000h\u0000i\u0000z\u0000i\u0000,\u0000 \u0000o\u0000e\u0000k\u0000a\u0000k\u0000i\u0000,\u0000 \u0000c\u0000i\u0000t\u0000y\u0000,\u0000 \u0000s\u0000h\u0000i\u0000b\u0000u\u0000y\u0000a\u0000 \u0000\\\u0000(\u0000t\u0000o\u0000k\u0000y\u0000o\u0000\\\u0000)\u0000,\u0000 \u0000"
image = pipe(prompt).images[0]Comicflux
- Prompt
- UNICODE<lora:comic_SDXL_v1:0.5>, (anime coloring:0.8), landscape, manga_art, iniphizi, oekaki, city, shibuya \(tokyo\),
Trigger words
You should use anime coloring to trigger the image generation.
You should use manga_art to trigger the image generation.
You should use iniphizi to trigger the image generation.
You should use oekaki to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 1
Model tree for leonel4rd/Comicflux
Base model
stabilityai/stable-diffusion-xl-base-1.0