欢迎来到 Anything V3 V4 VAE一个用于 weebs 的潜在扩散模型。该模型旨在通过几个提示来制作高质量、高度详细的动漫风格。与其他动漫风格的稳定扩散模型一样,它也支持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
此模型可以像任何其他稳定扩散模型一样使用。欲了解更多信息, 请看一下Stable Diffusion。
您还可以将模型导出到 ONNX、MPS 和/或 FLAX/JAX。
from diffusers import StableDiffusionPipeline
import torch
model_id = "Linaqruf/anything-v3.0"
branch_name= "diffusers"
pipe = StableDiffusionPipeline.from_pretrained(model_id, revision=branch_name, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "pikachu"
image = pipe(prompt).images[0]
image.save("./pikachu.png")
例子
以下是使用此模型生成的图像的一些示例
动漫女孩:
![图片[1]_【更新】Anything V3.0 V4.0 VAE,出色的SD动漫风格VAE_Qpipi](https://scdn.qpipi.com/2023/06/29ec6f57fe161350.webp)
1girl, brown hair, green eyes, colorful, autumn, cumulonimbus clouds, lighting, blue sky, falling leaves, garden
Steps: 50, Sampler: DDIM, CFG scale: 12
动漫男孩:
![图片[2]_【更新】Anything V3.0 V4.0 VAE,出色的SD动漫风格VAE_Qpipi](https://scdn.qpipi.com/2023/06/2a712d33d5161409.webp)
1boy, medium hair, blonde hair, blue eyes, bishounen, colorful, autumn, cumulonimbus clouds, lighting, blue sky, falling leaves, garden
Steps: 50, Sampler: DDIM, CFG scale: 12
风景:
![图片[3]_【更新】Anything V3.0 V4.0 VAE,出色的SD动漫风格VAE_Qpipi](https://scdn.qpipi.com/2023/06/00486e3901161428.webp)
scenery, shibuya tokyo, post-apocalypse, ruins, rust, sky, skyscraper, abandoned, blue sky, broken window, building, cloud, crane machine, outdoors, overgrown, pillar, sunset
Steps: 50, Sampler: DDIM, CFG scale: 12
💡如有问题或建议,🥳请在社区或评论告诉我们。🎨享受精彩的AI绘画乐趣!
⭕ 使用Qpipi读图提示功能,获取图片TAG Prompt提示 | Stable Diffusion AI绘图软件常见问题解答 | AI绘画新人必备工具指南
© 版权声明
⚠️ 与人分享是一种高尚品德,转载本站图文等内容,请保留出处和链接! BY-SA 4.0
THE END
暂无评论内容