app.py

import gradio as gr

import torch
from PIL import Image, ImageDraw, ImageFont, ImageOps, ImageEnhance
from quanto import qfloat8, quantize, freeze
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
from diffusers.utils import make_image_grid

atkbold = ImageFont.truetype("Atkinson-Hyperlegible-Bold-102.otf",50)

default_width = 1920
default_height = 1080
default_timesteps = 8

def mask_image_factory(mask_text="ASK FOR\nA SNACK", width=default_width, height=default_height):
    img = Image.new("L", (width, height), (0,))
    draw = ImageDraw.Draw(img)
    draw.multiline_text(
        xy=(0,0),
        text=mask_text,
        fill=(255,),
        font=atkbold,
        align="center",
        spacing=0,
    )
    cropped = img.crop(img.getbbox())
    # Calculate aspect ratios
    image_aspect_ratio = width / height
    cropped_aspect_ratio = cropped.size[0] / cropped.size[1]

    # Determine which dimension of cropped.size is larger
    if cropped_aspect_ratio > image_aspect_ratio:
        # Calculate new dimensions for padding
        new_width = int(cropped.size[1] * image_aspect_ratio)
        new_height = cropped.size[1]
    else:
        new_width = cropped.size[0]
        new_height = int(cropped.size[0] / image_aspect_ratio)

    # Pad the image to the desired aspect ratio
    padded = ImageOps.pad(cropped, (new_width, new_height))

    resized = padded.resize((width, height), resample=Image.Resampling.LANCZOS)
    return resized

preferred_device = "cuda" if torch.cuda.is_available() else ("mps" if torch.backends.mps.is_available() else "cpu")
# preferred_device = "cpu"
preferred_dtype = torch.float32

controlnet = ControlNetModel.from_pretrained(
    "monster-labs/control_v1p_sd15_qrcode_monster",
#    "monster-labs/control_v1p_sdxl_qrcode_monster",
    subfolder="v2",
    torch_dtype=preferred_dtype,
    #torch_dtype=unet_preferred_dtype
).to(preferred_device)

#quantize(controlnet, weights=qfloat8)
#freeze(controlnet)

ctlpipe = StableDiffusionControlNetPipeline.from_pretrained(
    "SimianLuo/LCM_Dreamshaper_v7",
    controlnet=controlnet,
    torch_dtype=preferred_dtype,
    safety_checker=None,
).to(preferred_device)

#quantize(ctlpipe.unet, weights=qfloat8)
#freeze(ctlpipe.unet)
#quantize(ctlpipe.text_encoder, weights=qfloat8)
#freeze(ctlpipe.text_encoder)

def app(prompt, negative_prompt, mask_text, num_inference_steps, controlnet_conditioning_scale, width, height, seed, count):
    all_images = [ctlpipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        image=mask_image_factory(mask_text=mask_text, width=width, height=height),
        num_inference_steps=int(num_inference_steps),
        guidance_scale=8.0,
        controlnet_conditioning_scale=float(controlnet_conditioning_scale),
        generator=torch.manual_seed(int(seed + i)),
        height=height,
        width=width,
    ).images[0] for i in range(count)]
    if count == 1:
        cols = 1
        rows = 1
    elif count == 2:
        cols = 1
        rows = 2
    else:
        cols = 2 if count % 2 == 0 else 1
        rows = count // cols
    return make_image_grid(all_images, cols=cols, rows=rows)


app("corgis running in the park", "ugly, wrong", "ASK FOR\nA SNACK", 1, 1.0, default_height, default_width, 42, 1)

iface = gr.Interface(
    app,
    [
        gr.Textbox(label="Prompt", value="large happy dogs frolic on the seashore, tall cliffs, sun at the horizon, boulders, tide pools, golden hour"),
        gr.Textbox(label="Negative Prompt", value="ugly, wrong"),
        gr.Textbox(label="Mask Text", value="ASK FOR\nA SNACK"),
        gr.Number(label="Number of Inference Steps", value=default_timesteps, minimum=1, maximum=50, step=1),
        gr.Slider(label="ControlNet Conditioning Scale", value=0.6, minimum=-1.0, maximum=2.0, step=0.01),
        gr.Number(label="Width", value=default_width, minimum=256, maximum=2048, precision=0),
        gr.Number(label="Height", value=default_height, minimum=256, maximum=2048, precision=0),
        gr.Number(label="Random Number Seed", value=42, minimum=0, maximum=2**32-1, precision=0),
        gr.Radio(label="Number of Images to Generate with Subsequent Consecutive Seeds", choices=[1, 2, 4, 6, 10], value=2),
    ],
    "image",
)

iface.launch()