Fabrice-TIERCELIN's picture
You'd rather use modern AIs like Flux Kontext or Qwen Image Edit
6211c62 verified
import gradio as gr
import numpy as np
import time
import math
import random
import torch
try:
import spaces
except:
class spaces():
def GPU(*args, **kwargs):
def decorator(function):
return lambda *dummy_args, **dummy_kwargs: function(*dummy_args, **dummy_kwargs)
return decorator
from diffusers import (
ControlNetModel,
StableDiffusionControlNetPipeline,
)
from PIL import Image
from pillow_heif import register_heif_opener
register_heif_opener()
max_64_bit_int = np.iinfo(np.int32).max
if torch.cuda.is_available():
device = "cuda"
floatType = torch.float16
else:
device = "cpu"
floatType = torch.float32
controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11e_sd15_ip2p", torch_dtype = floatType)
pipe = StableDiffusionControlNetPipeline.from_pretrained(
"botp/stable-diffusion-v1-5", safety_checker = None, controlnet = controlnet, torch_dtype = floatType
)
pipe = pipe.to(device)
def update_seed(is_randomize_seed, seed):
if is_randomize_seed:
return random.randint(0, max_64_bit_int)
return seed
def check(
input_image,
prompt,
negative_prompt,
denoising_steps,
num_inference_steps,
guidance_scale,
image_guidance_scale,
is_randomize_seed,
seed,
progress = gr.Progress()):
if input_image is None:
raise gr.Error("Please provide an image.")
if prompt is None or prompt == "":
raise gr.Error("Please provide a prompt input.")
@spaces.GPU(duration=420)
def pix2pix(
input_image,
prompt,
negative_prompt,
denoising_steps,
num_inference_steps,
guidance_scale,
image_guidance_scale,
is_randomize_seed,
seed,
progress = gr.Progress()):
check(
input_image,
prompt,
negative_prompt,
denoising_steps,
num_inference_steps,
guidance_scale,
image_guidance_scale,
is_randomize_seed,
seed
)
start = time.time()
progress(0, desc = "Preparing data...")
if negative_prompt is None:
negative_prompt = ""
if denoising_steps is None:
denoising_steps = 0
if num_inference_steps is None:
num_inference_steps = 20
if guidance_scale is None:
guidance_scale = 5
if image_guidance_scale is None:
image_guidance_scale = 1.5
if seed is None:
seed = random.randint(0, max_64_bit_int)
random.seed(seed)
torch.manual_seed(seed)
original_height, original_width, dummy_channel = np.array(input_image).shape
output_width = original_width
output_height = original_height
mask_image = Image.new(mode = input_image.mode, size = (output_width, output_height), color = "white")
limitation = "";
# Limited to 1 million pixels
if 1024 * 1024 < output_width * output_height:
factor = ((1024 * 1024) / (output_width * output_height))**0.5
output_width = math.floor(output_width * factor)
output_height = math.floor(output_height * factor)
limitation = " Due to technical limitation, the image have been downscaled and then upscaled.";
# Width and height must be multiple of 8
output_width = output_width - (output_width % 8)
output_height = output_height - (output_height % 8)
progress(None, desc = "Processing...")
output_image = pipe(
seeds=[seed],
width = output_width,
height = output_height,
prompt = prompt,
negative_prompt = negative_prompt,
image = input_image,
mask_image = mask_image,
num_inference_steps = num_inference_steps,
guidance_scale = guidance_scale,
image_guidance_scale = image_guidance_scale,
denoising_steps = denoising_steps,
show_progress_bar = True
).images[0]
if limitation != "":
output_image = output_image.resize((original_width, original_height))
end = time.time()
secondes = int(end - start)
minutes = math.floor(secondes / 60)
secondes = secondes - (minutes * 60)
hours = math.floor(minutes / 60)
minutes = minutes - (hours * 60)
return [
output_image,
("Start again to get a different result. " if is_randomize_seed else "") + "The image has been generated in " + ((str(hours) + " h, ") if hours != 0 else "") + ((str(minutes) + " min, ") if hours != 0 or minutes != 0 else "") + str(secondes) + " sec." + limitation
]
with gr.Blocks() as interface:
gr.HTML(
"""
<h1 style="text-align: center;">Instruct Pix2Pix demo</h1>
<p style="text-align: center;">Modifies your image using a textual instruction, freely, without account, without watermark, without installation, which can be downloaded</p>
<br/>
<br/>
✨ Powered by <i>SD 1.5</i> and <i>ControlNet</i>. You'd rather use modern AIs like <i>Flux Kontext</i> or <i>Qwen Image Edit</i>. The result quality extremely varies depending on what we ask.
<br/>
<ul>
<li>To change the <b>view angle</b> of your image, I recommend to use <i>Zero123</i>,</li>
<li>To <b>upscale</b> your image, I recommend to use <i><a href="https://huggingface.co/spaces/Fabrice-TIERCELIN/SUPIR">SUPIR</a></i>,</li>
<li>To <b>slightly change</b> your image, I recommend to use <i>Image-to-Image SDXL</i>,</li>
<li>To change <b>one detail</b> on your image, I recommend to use <i>Inpaint SDXL</i>,</li>
<li>To remove the <b>background</b> of your image, I recommend to use <i>BRIA</i>,</li>
<li>To enlarge the <b>viewpoint</b> of your image, I recommend to use <i>Uncrop</i>,</li>
<li>To make a <b>tile</b> of your image, I recommend to use <i>Make My Image Tile</i>,</li>
</ul>
<br/>
""" + ("🏃‍♀️ Estimated time: few minutes." if torch.cuda.is_available() else "🐌 Slow process... ~1 hour.") + """
Your computer must not enter into standby mode. You can launch several generations in different browser tabs when you're gone. If this space does not work or you want a faster run, use <i>Instruct Pix2Pix</i> available on hysts's <i>ControlNet-v1-1</i> space (last tab) or on <i>Dezgo</i> site.<br>You can duplicate this space on a free account, it's designed to work on CPU, GPU and ZeroGPU.<br/>
<a href='https://huggingface.co/spaces/Fabrice-TIERCELIN/Instruct-Pix2Pix?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'></a>
<br/>
⚖️ You can use, modify and share the generated images but not for commercial uses.
"""
)
with gr.Column():
input_image = gr.Image(label = "Your image", sources = ["upload", "webcam", "clipboard"], type = "pil")
prompt = gr.Textbox(label = "Prompt", info = "Instruct what to change in the image", placeholder = "Order the AI what to change in the image", lines = 2)
with gr.Accordion("Advanced options", open = False):
negative_prompt = gr.Textbox(label = "Negative prompt", placeholder = "Describe what you do NOT want to see in the image", value = ''
'blurring, aliasing, unsharp, weird textures, ugly, dirty, messy, '
'worst quality, low quality, frames, watermark, signature, jpeg artifacts, '
'deformed, lowres, over-smooth')
denoising_steps = gr.Slider(minimum = 0, maximum = 1000, value = 0, step = 1, label = "Denoising", info = "lower=irrelevant result, higher=relevant result")
num_inference_steps = gr.Slider(minimum = 10, maximum = 500, value = 20, step = 1, label = "Number of inference steps", info = "lower=faster, higher=image quality")
guidance_scale = gr.Slider(minimum = 1, maximum = 13, value = 5, step = 0.1, label = "Guidance Scale", info = "lower=image quality, higher=follow the prompt")
image_guidance_scale = gr.Slider(minimum = 1, value = 1.5, step = 0.1, label = "Image Guidance Scale", info = "lower=image quality, higher=follow the image")
randomize_seed = gr.Checkbox(label = "\U0001F3B2 Randomize seed", value = True, info = "If checked, result is always different")
seed = gr.Slider(minimum = 0, maximum = max_64_bit_int, step = 1, randomize = True, label = "Seed")
submit = gr.Button("🚀 Modify", variant = "primary")
modified_image = gr.Image(label = "Modified image")
information = gr.HTML()
submit.click(fn = update_seed, inputs = [
randomize_seed,
seed
], outputs = [
seed
], queue = False, show_progress = False).then(check, inputs = [
input_image,
prompt,
negative_prompt,
denoising_steps,
num_inference_steps,
guidance_scale,
image_guidance_scale,
randomize_seed,
seed
], outputs = [], queue = False, show_progress = False).success(pix2pix, inputs = [
input_image,
prompt,
negative_prompt,
denoising_steps,
num_inference_steps,
guidance_scale,
image_guidance_scale,
randomize_seed,
seed
], outputs = [
modified_image,
information
], scroll_to_output = True)
gr.Examples(
run_on_click = True,
fn = pix2pix,
inputs = [
input_image,
prompt,
negative_prompt,
denoising_steps,
num_inference_steps,
guidance_scale,
image_guidance_scale,
randomize_seed,
seed
],
outputs = [
modified_image,
information
],
examples = [
[
"./Examples/Example1.webp",
"What if it's snowing?",
"blurring, aliasing, unsharp, weird textures, ugly, dirty, messy, "
"worst quality, low quality, frames, watermark, signature, jpeg artifacts, "
"deformed, lowres, over-smooth",
1,
20,
5,
1.5,
False,
42
],
[
"./Examples/Example2.png",
"What if this woman had brown hair?",
"blurring, aliasing, unsharp, weird textures, ugly, dirty, messy, "
"worst quality, low quality, frames, watermark, signature, jpeg artifacts, "
"deformed, lowres, over-smooth",
1,
20,
5,
1.5,
False,
42
],
[
"./Examples/Example3.jpeg",
"Replace the house by a windmill",
"blurring, aliasing, unsharp, weird textures, ugly, dirty, messy, "
"worst quality, low quality, frames, watermark, signature, jpeg artifacts, "
"deformed, lowres, over-smooth",
1,
20,
5,
1.5,
False,
42
],
[
"./Examples/Example4.gif",
"What if the camera was in opposite side?",
"blurring, aliasing, unsharp, weird textures, ugly, dirty, messy, "
"worst quality, low quality, frames, watermark, signature, jpeg artifacts, "
"deformed, lowres, over-smooth",
1,
20,
5,
1.5,
False,
42
],
[
"./Examples/Example5.bmp",
"Turn him into cyborg",
"blurring, aliasing, unsharp, weird textures, ugly, dirty, messy, "
"worst quality, low quality, frames, watermark, signature, jpeg artifacts, "
"deformed, lowres, over-smooth",
1,
20,
5,
25,
False,
42
],
],
cache_examples = False,
)
interface.queue().launch()