import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("JasonWen/0.3nai-7G_plus_0.7rock-e27", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]融合了7G的novel AI anime full latest和fluffyrock-576-704-832-960-1088-lion-low-lr-e27
配比为0.3nai+0.7rock_e27
分为5.57G、2.13G、3.85G、7.7G四个大小档次，他们其实都是一样的，出图没有任何区别
用来作为训练LoRA的底模，可以既学到Danbooru的tag，又学到e621的tag，做到了对融合模型的兼容性
哪个大小的文件训练几乎都是一样的
- Downloads last month
- 20
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support