感谢Linaqruf提供的model card供参考。
欢迎使用Anything V4 - 一个为日本动漫爱好者设计的latent diffusion模型。这个模型旨在仅用少数几个提示词就能生成高质量、高细节的动漫风格。与其他动漫风格的Stable Diffusion模型一样,它还支持danbooru标签来生成图像。
例如: 1girl, white hair, golden eyes, beautiful eyes, detail, flower meadow, cumulonimbus clouds, lighting, detailed sky, garden
我感觉V4.5版本效果更好。该模型也在这个repo中,你可以尝试一下。
from modelscope.utils.constant import Tasks
from modelscope.pipelines import pipeline
import cv2
pipe = pipeline(task=Tasks.text_to_image_synthesis,
model='dienstag/anything-v4.0',
model_revision='v4.0')
prompt = 'masterpiece, best quality, 1girl, white hair, medium hair, cat ears, closed eyes, looking at viewer, :3, cute, scarf, jacket, outdoors, streets'
output = pipe({'text': prompt})
cv2.imwrite('result.png', output['output_imgs'][0])
以下是该模型生成的一些样例
Anime Girl:
masterpiece, best quality, 1girl, white hair, medium hair, cat ears, closed eyes, looking at viewer, :3, cute, scarf, jacket, outdoors, streets
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7
Anime Boy:
1boy, bishounen, casual, indoors, sitting, coffee shop, bokeh
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7
Scenery:
scenery, village, outdoors, sky, clouds
Steps: 50, Sampler: DPM++ 2S a Karras, CFG scale: 7
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: