waifu-diffusion 基于latent diffusion模型打造,使用大量高质量动漫图片微调而来。
masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, watercolor, night, turtleneck
这个模型是开放的,所有人都可以使用,CreativeML OpenRAIL-M许可证进一步规定了权利和使用。CreativeML OpenRAIL许可证规定了:
该模型可用于娱乐目的和生成艺术助手。
from modelscope.utils.constant import Tasks
from modelscope.pipelines import pipeline
import cv2
pipe = pipeline(task=Tasks.text_to_image_synthesis,
model='dienstag/waifu-diffusion',
model_revision='v1.4')
prompt = '1girl, aqua eyes, baseball cap, blonde hair, closed mouth, earrings, green background, hat, hoop earrings, jewelry, looking at viewer, shirt, short hair, simple background, solo, upper body, yellow shirt'
output = pipe({'text': prompt, 'guidance_scale': 6})
cv2.imwrite('result.png', output['output_imgs'][0])
感谢 Stability AI 和 Novel AI 的杰出贡献,使得这个项目成功完成。
使用Discord联系我们: Discord server.