app.py

from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
from diffusers import UniPCMultistepScheduler
import gradio as gr
import torch

# Constants
low_threshold = 100
high_threshold = 200

# Models
controlnet_pose = ControlNetModel.from_pretrained(
    "lllyasviel/sd-controlnet-openpose", torch_dtype=torch.float16
)
controlnet_canny = ControlNetModel.from_pretrained(
    "lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16
)

pipe = StableDiffusionControlNetPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5", 
    controlnet=[controlnet_pose,controlnet_canny], 
    safety_checker=None, torch_dtype=torch.float16
)
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)

# This command loads the individual model components on GPU on-demand. So, we don't
# need to explicitly call pipe.to("cuda").
pipe.enable_model_cpu_offload()

# xformers
pipe.enable_xformers_memory_efficient_attention()

# Generator seed,
generator = torch.manual_seed(0)

def generate_images(pose_image, canny_image, prompt):
    output = pipe(
        prompt,
        [pose_image, canny_image],
        generator=generator,
        num_images_per_prompt=3,
        num_inference_steps=20,
    )
    all_outputs = []
    all_outputs.append(pose_image)
    all_outputs.append(canny_image)
    for image in output.images:
        all_outputs.append(image)
    return all_outputs


gr.Interface(
    generate_images,
    inputs=[
        gr.Image(type="pil"),
        gr.Image(type="pil"),
        gr.Textbox(
            label="Enter your prompt",
            max_lines=1,
            placeholder="best quality, extremely detailed, a girl wearing white dress",
        ),
    ],
    outputs=gr.Gallery().style(grid=[2], height="auto"),
    title="Generate controlled outputs with Mult-ControlNet and Stable Diffusion using 🤗Diffusers",
    description="This Space uses pose lines and canny edged image as the additional conditioning. Please refer to the \"Examples\" for what kind of images are appropriate.",
    examples=[["sample_pose_body.png", "sample_canny_hand.png", "best quality, extremely detailed"]],
    allow_flagging=False,
).launch(enable_queue=True)