import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("alibaba-pai/pai-diffusion-general-large-zh-controlnet-depth", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Chinese Latent Diffusion Model
我们开源了适配模型 alibaba-pai/pai-diffusion-general-large-zh 的 ControlNet，输入图像的 Depth 特征，进行可控的生成。
- Github: EasyNLP
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
controlnet_id = "alibaba-pai/pai-diffusion-general-large-zh-controlnet-depth"
controlnet = ControlNetModel.from_pretrained(controlnet_id)
model_id = "alibaba-pai/pai-diffusion-general-large-zh"
pipe = StableDiffusionControlNetPipeline.from_pretrained(model_id, controlnet=controlnet)
pipe = pipe.to("cuda")
image = Image.open("depth_image.png")
prompt = "雪地上的帐篷"
image = pipe(prompt, image).images[0]
image.save("result.png")
- Downloads last month
- 3