app.py

from PIL import Image
import gradio as gr
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, UniPCMultistepScheduler
import torch
torch.backends.cuda.matmul.allow_tf32 = True

controlnet = ControlNetModel.from_pretrained("JFoz/dog-cat-pose", torch_dtype=torch.float16)

pipe = StableDiffusionControlNetPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    controlnet=controlnet,
    torch_dtype=torch.float16,
    safety_checker=None,
)

pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)

pipe.enable_xformers_memory_efficient_attention()
pipe.enable_model_cpu_offload()
pipe.enable_attention_slicing()

def infer(
        prompt,
        negative_prompt,
        conditioning_image,
        num_inference_steps=30,
        size=768,
        guidance_scale=7.0,
        seed=1234,
):

    conditioning_image_raw = Image.fromarray(conditioning_image)
    #conditioning_image = conditioning_image_raw.convert('L')

    g_cpu = torch.Generator()

    if seed == -1:
        generator = g_cpu.manual_seed(g_cpu.seed())
    else:
        generator = g_cpu.manual_seed(seed)

    output_image = pipe(
        prompt,
        conditioning_image,
        height=size,
        width=size,
        num_inference_steps=num_inference_steps,
        generator=generator,
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale,
        controlnet_conditioning_scale=1.0,
    ).images[0]

    #del conditioning_image, conditioning_image_raw
    #gc.collect()

    return output_image

with gr.Blocks(theme=gr.themes.Default(font=[gr.themes.GoogleFont("Inconsolata"), "Arial", "sans-serif"])) as demo:
    gr.Markdown(
        """
    # Animal Pose Control Net
    # This is a demo of Animal Pose Control Net, which is a model trained on runwayml/stable-diffusion-v1-5 with new type of conditioning.
    """)

    with gr.Row():
        with gr.Column():
            prompt = gr.Textbox(
                label="Prompt",
            )
            negative_prompt = gr.Textbox(
                label="Negative Prompt",
            )
            conditioning_image = gr.Image(
                label="Conditioning Image",
            )
            with gr.Accordion('Advanced options', open=False):
                with gr.Row():
                    num_inference_steps = gr.Slider(
                        10, 40, 20,
                        step=1,
                        label="Steps",
                    )
                    size = gr.Slider(
                        256, 768, 512,
                        step=128,
                        label="Size",
                    )
                with gr.Row():
                    guidance_scale = gr.Slider(
                        label='Guidance Scale',
                        minimum=0.1,
                        maximum=30.0,
                        value=7.0,
                        step=0.1
                    )
                    seed = gr.Slider(
                        label='Seed',
                        value=-1,
                        minimum=-1,
                        maximum=2147483647,
                        step=1,
                        # randomize=True
                    )
            submit_btn = gr.Button(
                value="Submit",
                variant="primary"
            )
        with gr.Column(min_width=300):
            output = gr.Image(
                label="Result",
            )

    submit_btn.click(
        fn=infer,
        inputs=[
            prompt, negative_prompt, conditioning_image, num_inference_steps, size, guidance_scale, seed
            #prompt, size, seed
        ],
        outputs=output
    )
    gr.Examples(
        examples=[
            #["a tortoiseshell cat is sitting on a cushion"],
            #["a yellow dog standing on a lawn"],
            ["a tortoiseshell cat is sitting on a cushion",  "https://huggingface.co/JFoz/dog-cat-pose/blob/main/images_0.png"],
            ["a yellow dog standing on a lawn", "https://huggingface.co/JFoz/dog-cat-pose/blob/main/images_1.png"],
        ],
        inputs=[
            #prompt, negative_prompt, conditioning_image
            prompt
        ],
        outputs=output,
        fn=infer,
        cache_examples=True,
    )
    gr.Markdown(
        """
    * [Dataset](https://huggingface.co/datasets/JFoz/dog-poses-controlnet-dataset)
    * [Diffusers model](), [Web UI model](https://huggingface.co/JFoz/dog-pose)
    * [Training Report](https://wandb.ai/john-fozard/dog-cat-pose/runs/kmwcvae5))
    """)

#gr.Interface(infer, inputs=["text"], outputs=[output], title=title, description=description, examples=examples).queue().launch()
demo.launch()