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("zmy-org/pixel_f2")
prompt = "(masterpiece, top quality, best quality), pixel,pixel art,1girl,full body, "
image = pipe(prompt).images[0]pixel_f2
- Prompt
- (masterpiece, top quality, best quality), pixel,pixel art,1girl,full body,
Model description
可以配合其他lora来玩！也可以出像素场景！权重0.5就行！ 画人像素推荐512X768，高清修复1.5.重绘幅度0.4,再高就没有像素感了。 画建筑推荐768X768,高清修复1.2 触发关键词：pixel
Trigger words
You should use pixel 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
- 14
Model tree for zmy-org/pixel_f2
Base model
stabilityai/stable-diffusion-xl-base-1.0