许可证: 其他 许可证名称: stabilityai-ai-community 许可证链接: LICENSE.md 语言:

• 英文 基础模型:
• stabilityai/stable-diffusion-3.5-medium 管道标签: 文本生成图像

TensorArt Stable Diffusion 3.5 Medium ControlNet Canny

使用SD3.5M

import torch
from diffusers import StableDiffusion3ControlNetPipeline
from diffusers import SD3ControlNetModel
from diffusers.utils import load_image

controlnet = SD3ControlNetModel.from_pretrained("tensorart/SD3.5M-Controlnet-Canny")
pipe = StableDiffusion3ControlNetPipeline.from_pretrained(
    "stabilityai/stable-diffusion-3.5-medium",
    controlnet=controlnet
)
pipe.to("cuda", torch.float16)

control_image = load_image("https://huggingface.co/tensorart/SD3.5M-Controlnet-Canny/resolve/main/asset/canny.png")
prompt = "一只眼睛"
negative_prompt = "低质量，最差质量，变形，扭曲，畸形，动态模糊，动态伪影，融合的手指，不良解剖结构，奇怪的手，丑陋，单色"

image = pipe(
    prompt, 
    num_inference_steps=30,
    negative_prompt=negative_prompt, 
    control_image=control_image, 
    guidance_scale=4.5,
    controlnet_conditioning_scale=0.8
).images[0]
image.save('image.jpg')

使用TensorArt的SD3.5M Turbo

import torch
from diffusers import StableDiffusion3ControlNetPipeline
from diffusers import SD3ControlNetModel
from diffusers.utils import load_image

controlnet = SD3ControlNetModel.from_pretrained("tensorart/SD3.5M-Controlnet-Canny")
pipe = StableDiffusion3ControlNetPipeline.from_pretrained(
    "tensorart/stable-diffusion-3.5-medium-turbo",
    controlnet=controlnet
)
pipe.to("cuda", torch.float16)

control_image = load_image("https://huggingface.co/tensorart/SD3.5M-Controlnet-Canny/resolve/main/asset/canny.png")
prompt = "一只眼睛"
negative_prompt = "低质量，最差质量，变形，扭曲，畸形，动态模糊，动态伪影，融合的手指，不良解剖结构，奇怪的手，丑陋，单色"

image = pipe(
    prompt, 
    num_inference_steps=8,
    negative_prompt=negative_prompt, 
    control_image=control_image, 
    guidance_scale=1.5,
    controlnet_conditioning_scale=0.8
).images[0]
image.save('image.jpg')

联系方式

• 网站: https://tensor.art https://tusiart.com
• 开发团队: TensorArt