diffusers-Text-to-image

from diffusers import ControlNetModel, AutoPipelineForText2Image
from diffusers.utils import load_image
import torch

controlnet = ControlNetModel.from_pretrained(
	"lllyasviel/control_v11p_sd15_openpose", torch_dtype=torch.float16, variant="fp16"
).to("cuda")
pose_image = load_image("https://huggingface.co/lllyasviel/control_v11p_sd15_openpose/resolve/main/images/control.png")

pipeline = AutoPipelineForText2Image.from_pretrained(
	"runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16, variant="fp16"
).to("cuda")
generator = torch.Generator("cuda").manual_seed(31)
image = pipeline("Astronaut in a jungle, cold color palette, muted colors, detailed, 8k", image=pose_image, generator=generator).images[0]
image

guidance_scale这个值不能太大也不可以太小，太小时具有更多的创造力，太大时将更加逼近提示，默认是7.5，值太大了会出现伪影。







此处的embedding是通过 Compel 库得到的

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16").to("cuda")
pipeline.unet = torch.compile(pipeline.unet, mode="reduce-overhead", fullgraph=True)