import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Kevin3111/sd-class-butterflies-64", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Model Card for Diffusion Models Class 🧨
这个模型用于生成蝴蝶图像的无条件图像生成扩散模型
Usage 1：
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('Kevin3111/sd-class-butterflies-64')
image = pipeline(num_inference_steps=50).images[0]
image
###################################################################################
如上，直接加载的话会报错（具体原因不清楚，毕竟我也刚开始学习，好多都不懂）：
OSError: Error no file named diffusion_pytorch_model.bin found in directory /root/.cache/huggingface/hub/models/...
可以先下载到本地，然后加载本地路径，这种方式正常（虽然Usage 1也是先下载到本地.cache文件里，再加载）
huggingface-cli download --resume-download --local-dir-use-symlinks False Kevin3111/sd-class-butterflies-64 --local-dir /{your_local_path}/Kevin3111/sd-class-butterflies-64
Usage 2：
from diffusers import DDPMPipeline
model_path = "/{your_local_path}/Kevin3111/sd-class-butterflies-64"
pipeline = DDPMPipeline.from_pretrained(model_path)
image = pipeline(num_inference_steps=50).images[0]
image
- Downloads last month
- 11
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support