MAIchelangelo / app.py
Seba8820's picture
Update app.py
6991d59
Raw History Blame Contribute Delete
4.43 kB
import math
import random
import gradio as gr
import torch
from PIL import Image, ImageOps
from diffusers import StableDiffusionInstructPix2PixPipeline
help_text = """
"""
model_id = "timbrooks/instruct-pix2pix"
def main():
pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained(model_id, torch_dtype=torch.float16, safety_checker=None).to("cuda")
def generate(
input_image: Image.Image,
instruction: str,
steps: int,
randomize_seed: bool,
seed: int,
randomize_cfg: bool,
text_cfg_scale: float,
image_cfg_scale: float,
):
seed = random.randint(0, 100000) if randomize_seed else seed
text_cfg_scale = round(random.uniform(6.0, 9.0), ndigits=2) if randomize_cfg else text_cfg_scale
image_cfg_scale = round(random.uniform(1.2, 1.8), ndigits=2) if randomize_cfg else image_cfg_scale
width, height = input_image.size
factor = 512 / max(width, height)
factor = math.ceil(min(width, height) * factor / 64) * 64 / min(width, height)
width = int((width * factor) // 64) * 64
height = int((height * factor) // 64) * 64
input_image = ImageOps.fit(input_image, (width, height), method=Image.Resampling.LANCZOS)
if instruction == "":
return [input_image, seed]
generator = torch.manual_seed(seed)
edited_image = pipe(
instruction, image=input_image,
guidance_scale=text_cfg_scale, image_guidance_scale=image_cfg_scale,
num_inference_steps=steps, generator=generator,
).images[0]
return [seed, text_cfg_scale, image_cfg_scale, edited_image]
def reset():
return [0, "Randomize Seed", 1371, "Fix CFG", 7.5, 1.5, None]
with gr.Blocks() as demo:
gr.HTML("""<h1 style="font-weight: 900; margin-bottom: 7px;">
MAIchelangelo
</h1>
<p>
<br/>
<a href="">
<img style="margin-top: 0em; margin-bottom: 0em" src="" alt=""></a>
<p/>""")
with gr.Row():
with gr.Column(scale=1, min_width=100):
generate_button = gr.Button("Generate")
with gr.Column(scale=1, min_width=100):
reset_button = gr.Button("Reset",visible=False)
with gr.Column(scale=3):
instruction = gr.Textbox(lines=1, label="Edit Instruction", interactive=True,value="Make into a Picasso painting")
with gr.Row():
input_image = gr.Image(label="Input Image", source="webcam", type="pil", interactive=True)
edited_image = gr.Image(label=f"Edited Image", type="pil", interactive=False)
input_image.style(height=512, width=512)
edited_image.style(height=512, width=512)
with gr.Row():
steps = gr.Number(value=50, precision=0, label="Steps", interactive=True,visible=False)
randomize_seed = gr.Radio(
["Fix Seed", "Randomize Seed"],
value="Randomize Seed",
type="index",
show_label=False,
interactive=True,
visible=False,
)
seed = gr.Number(value=1371, precision=0, label="Seed", interactive=True,visible=False)
randomize_cfg = gr.Radio(
["Fix CFG", "Randomize CFG"],
value="Fix CFG",
type="index",
show_label=False,
interactive=True,
visible=False,
)
text_cfg_scale = gr.Number(value=16.5, label=f"Text CFG", interactive=True,visible=True)
image_cfg_scale = gr.Number(value=1.5, label=f"Image CFG", interactive=True,visible=False)
gr.Markdown(help_text)
generate_button.click(
fn=generate,
inputs=[
input_image,
instruction,
steps,
randomize_seed,
seed,
randomize_cfg,
text_cfg_scale,
image_cfg_scale,
],
outputs=[seed, text_cfg_scale, image_cfg_scale, edited_image],
)
reset_button.click(
fn=reset,
inputs=[],
outputs=[steps, randomize_seed, seed, randomize_cfg, text_cfg_scale, image_cfg_scale, edited_image],
)
demo.queue(concurrency_count=1)
demo.launch(share=True)
if __name__ == "__main__":
main()