depth2img / app.py
amankishore's picture
Fix UI
8293478
import gradio as gr
import torch
import os
from PIL import Image
import numpy as np
from diffusers import StableDiffusionDepth2ImgPipeline
from pathlib import Path
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
is_gpu_associated = torch.cuda.is_available()
dept2img = StableDiffusionDepth2ImgPipeline.from_pretrained(
"stabilityai/stable-diffusion-2-depth",
torch_dtype=torch.float16,
).to(device)
css = '''
.instruction{position: absolute; top: 0;right: 0;margin-top: 0px !important}
.arrow{position: absolute;top: 0;right: -110px;margin-top: -8px !important}
#component-4, #component-3, #component-10{min-height: 0}
.duplicate-button img{margin: 0}
'''
def pad_image(input_image):
pad_w, pad_h = np.max(((2, 2), np.ceil(
np.array(input_image.size) / 64).astype(int)), axis=0) * 64 - input_image.size
im_padded = Image.fromarray(
np.pad(np.array(input_image), ((0, pad_h), (0, pad_w), (0, 0)), mode='edge'))
w, h = im_padded.size
if w == h:
return im_padded
elif w > h:
new_image = Image.new(im_padded.mode, (w, w), (0, 0, 0))
new_image.paste(im_padded, (0, (w - h) // 2))
return new_image
else:
new_image = Image.new(im_padded.mode, (h, h), (0, 0, 0))
new_image.paste(im_padded, ((h - w) // 2, 0))
return new_image
def predict(input_image, prompt, negative_prompt, steps, num_samples, scale, seed, strength, depth_image=None):
if not is_gpu_associated:
raise gr.Error("Please associate a T4 GPU for this Space")
torch.cuda.empty_cache()
depth = None
if depth_image is not None:
depth_image = pad_image(depth_image)
depth_image = depth_image.resize((512, 512))
depth = np.array(depth_image.convert("L"))
depth = depth.astype(np.float32) / 255.0
depth = depth[None, None]
depth = torch.from_numpy(depth)
init_image = input_image.convert("RGB")
image = pad_image(init_image) # resize to integer multiple of 32
image = image.resize((512, 512))
result = dept2img(
image=image,
prompt=prompt,
negative_prompt=negative_prompt,
depth_image=depth,
seed=seed,
strength=strength,
num_inference_steps=steps,
guidance_scale=scale,
num_images_per_prompt=num_samples,
)
return result['images']
block = gr.Blocks().queue()
with block:
with gr.Box():
if is_gpu_associated:
top_description = gr.HTML(f'''
<div style="text-align: center; max-width: 650px; margin: 0 auto;">
<div>
<img class="logo" src="file/mirage.png" alt="Mirage Logo"
style="margin: auto; max-width: 7rem;">
<br />
<h1 style="font-weight: 900; font-size: 2.5rem;">
Depth2Img Web UI
</h1>
<br />
<a class="duplicate-button" style="display:inline-block" target="_blank" href="https://huggingface.co/spaces/MirageML/depth2img?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a>
</div>
<br />
<br />
<p style="margin-bottom: 10px; font-size: 94%">
Create variations of an image while preserving shape and depth!
</p>
</div>
''')
else:
top_description = gr.HTML(f'''
<div style="text-align: center; max-width: 650px; margin: 0 auto;">
<div>
<img class="logo" src="file/mirage.png" alt="Mirage Logo"
style="margin: auto; max-width: 7rem;">
<br />
<h1 style="font-weight: 900; font-size: 2.5rem;">
Depth2Img Web UI
</h1>
<br />
<a class="duplicate-button" style="display:inline-block" target="_blank" href="https://huggingface.co/spaces/MirageML/depth2img?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a>
</div>
<br />
<br />
<p style="margin-bottom: 10px; font-size: 94%">
Create variations of an image while preserving shape and depth!
</p>
<br />
<p>There's only one step left before you can run the app: <a href="https://huggingface.co/spaces/{os.environ['SPACE_ID']}/settings" style="text-decoration: underline" target="_blank">attribute a <b>T4 GPU</b> to it (via the Settings tab)</a> and run the app below. You will be billed by the minute from when you activate the GPU until it is turned it off.</p>
</div>
''')
with gr.Row():
with gr.Column():
input_image = gr.Image(source='upload', type="pil")
# depth_image = gr.Image(
# source='upload', type="pil", label="Depth image Optional", value=None)
depth_image = None
prompt = gr.Textbox(label="Prompt")
negative_prompt = gr.Textbox(label="Negative Pompt")
run_button = gr.Button(label="Run")
with gr.Accordion("Advanced options", open=False):
num_samples = gr.Slider(
label="Images", minimum=1, maximum=4, value=1, step=1)
steps = gr.Slider(label="Steps", minimum=1,
maximum=100, value=50, step=1)
scale = gr.Slider(
label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1
)
strength = gr.Slider(
label="Strength", minimum=0.0, maximum=1.0, value=0.9, step=0.01
)
seed = gr.Slider(
label="Seed",
minimum=0,
maximum=2147483647,
step=1,
randomize=True,
)
with gr.Column():
gallery = gr.Gallery(label="Generated images", show_label=False).style(
grid=[2], height="auto")
if is_gpu_associated:
gr.Examples(
examples=[
["./examples/original_iso.png", "hogwarts castle",
"", 50, 4, 10.0, 123123123, 0.8],
["./examples/original_sword.png", "flaming sword",
"", 50, 4, 9.0, 1734133747, 0.8],
],
inputs=[input_image, prompt, negative_prompt, steps,
num_samples, scale, seed, strength],
outputs=[gallery],
fn=predict,
cache_examples=True,
)
run_button.click(fn=predict, inputs=[input_image, prompt, negative_prompt,
steps, num_samples, scale, seed, strength], outputs=[gallery])
block.launch(show_api=False)