from diffusers import AutoencoderKL, UNet2DConditionModel, StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, DPMSolverMultistepScheduler
import gradio as gr
import torch
from PIL import Image
import utils
import datetime
import time
import psutil
import random
start_time = time.time()
is_colab = utils.is_google_colab()
state = None
current_steps = 25
class Model:
def __init__(self, name, path="", prefix=""):
self.name = name
self.path = path
self.prefix = prefix
self.pipe_t2i = None
self.pipe_i2i = None
models = [
Model("Protogen x5.3 (Photorealism)", "darkstorm2150/Protogen_x5.3_Official_Release")
]
custom_model = None
if is_colab:
models.insert(0, Model("Custom model"))
custom_model = models[0]
last_mode = "txt2img"
current_model = models[1] if is_colab else models[0]
current_model_path = current_model.path
if is_colab:
pipe = StableDiffusionPipeline.from_pretrained(
current_model.path,
torch_dtype=torch.float16,
scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler"),
safety_checker=lambda images, clip_input: (images, False)
)
else:
pipe = StableDiffusionPipeline.from_pretrained(
current_model.path,
torch_dtype=torch.float16,
scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler")
)
if torch.cuda.is_available():
pipe = pipe.to("cuda")
pipe.enable_xformers_memory_efficient_attention()
device = "GPU 🔥" if torch.cuda.is_available() else "CPU 🥶"
def error_str(error, title="Error"):
return f"""#### {title}
{error}""" if error else ""
def update_state(new_state):
global state
state = new_state
def update_state_info(old_state):
if state and state != old_state:
return gr.update(value=state)
def custom_model_changed(path):
models[0].path = path
global current_model
current_model = models[0]
def on_model_change(model_name):
prefix = "Enter prompt. \"" + next((m.prefix for m in models if m.name == model_name), None) + "\" is prefixed automatically" if model_name != models[0].name else "Don't forget to use the custom model prefix in the prompt!"
return gr.update(visible = model_name == models[0].name), gr.update(placeholder=prefix)
def on_steps_change(steps):
global current_steps
current_steps = steps
def pipe_callback(step: int, timestep: int, latents: torch.FloatTensor):
update_state(f"{step}/{current_steps} steps")#\nTime left, sec: {timestep/100:.0f}")
def inference(model_name, prompt, guidance, steps, n_images=1, width=512, height=512, seed=0, img=None, strength=0.5, neg_prompt=""):
update_state(" ")
print(psutil.virtual_memory()) # print memory usage
global current_model
for model in models:
if model.name == model_name:
current_model = model
model_path = current_model.path
# generator = torch.Generator('cuda').manual_seed(seed) if seed != 0 else None
if seed == 0:
seed = random.randint(0, 2147483647)
generator = torch.Generator('cuda').manual_seed(seed)
try:
if img is not None:
return img_to_img(model_path, prompt, n_images, neg_prompt, img, strength, guidance, steps, width, height, generator, seed), f"Done. Seed: {seed}"
else:
return txt_to_img(model_path, prompt, n_images, neg_prompt, guidance, steps, width, height, generator, seed), f"Done. Seed: {seed}"
except Exception as e:
return None, error_str(e)
def txt_to_img(model_path, prompt, n_images, neg_prompt, guidance, steps, width, height, generator, seed):
print(f"{datetime.datetime.now()} txt_to_img, model: {current_model.name}")
global last_mode
global pipe
global current_model_path
if model_path != current_model_path or last_mode != "txt2img":
current_model_path = model_path
update_state(f"Loading {current_model.name} text-to-image model...")
if is_colab or current_model == custom_model:
pipe = StableDiffusionPipeline.from_pretrained(
current_model_path,
torch_dtype=torch.float16,
scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler"),
safety_checker=lambda images, clip_input: (images, False)
)
else:
pipe = StableDiffusionPipeline.from_pretrained(
current_model_path,
torch_dtype=torch.float16,
scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler")
)
# pipe = pipe.to("cpu")
# pipe = current_model.pipe_t2i
if torch.cuda.is_available():
pipe = pipe.to("cuda")
pipe.enable_xformers_memory_efficient_attention()
last_mode = "txt2img"
prompt = current_model.prefix + prompt
result = pipe(
prompt,
negative_prompt = neg_prompt,
num_images_per_prompt=n_images,
num_inference_steps = int(steps),
guidance_scale = guidance,
width = width,
height = height,
generator = generator,
callback=pipe_callback)
# update_state(f"Done. Seed: {seed}")
return replace_nsfw_images(result)
def img_to_img(model_path, prompt, n_images, neg_prompt, img, strength, guidance, steps, width, height, generator, seed):
print(f"{datetime.datetime.now()} img_to_img, model: {model_path}")
global last_mode
global pipe
global current_model_path
if model_path != current_model_path or last_mode != "img2img":
current_model_path = model_path
update_state(f"Loading {current_model.name} image-to-image model...")
if is_colab or current_model == custom_model:
pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
current_model_path,
torch_dtype=torch.float16,
scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler"),
safety_checker=lambda images, clip_input: (images, False)
)
else:
pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
current_model_path,
torch_dtype=torch.float16,
scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler")
)
# pipe = pipe.to("cpu")
# pipe = current_model.pipe_i2i
if torch.cuda.is_available():
pipe = pipe.to("cuda")
pipe.enable_xformers_memory_efficient_attention()
last_mode = "img2img"
prompt = current_model.prefix + prompt
ratio = min(height / img.height, width / img.width)
img = img.resize((int(img.width * ratio), int(img.height * ratio)), Image.LANCZOS)
result = pipe(
prompt,
negative_prompt = neg_prompt,
num_images_per_prompt=n_images,
image = img,
num_inference_steps = int(steps),
strength = strength,
guidance_scale = guidance,
# width = width,
# height = height,
generator = generator,
callback=pipe_callback)
# update_state(f"Done. Seed: {seed}")
return replace_nsfw_images(result)
def replace_nsfw_images(results):
if is_colab:
return results.images
for i in range(len(results.images)):
if results.nsfw_content_detected[i]:
results.images[i] = Image.open("nsfw.png")
return results.images
# css = """.finetuned-diffusion-div div{display:inline-flex;align-items:center;gap:.8rem;font-size:1.75rem}.finetuned-diffusion-div div h1{font-weight:900;margin-bottom:7px}.finetuned-diffusion-div p{margin-bottom:10px;font-size:94%}a{text-decoration:underline}.tabs{margin-top:0;margin-bottom:0}#gallery{min-height:20rem}
# """
with gr.Blocks(css="style.css") as demo:
gr.HTML(
f"""
Protogen Web UI
Demo for multiple fine-tuned Stable Diffusion models, trained on different styles:
darkstorm2150
, darkstorm2150, darkstorm2150 + in colab notebook you can load any other Diffusers 🧨 SD model hosted on HuggingFace 🤗.
Running on {device}{(" in a Google Colab." if is_colab else "")}
You can also duplicate this space and upgrade to gpu by going to settings:
"""
)
with gr.Row():
with gr.Column(scale=55):
with gr.Group():
model_name = gr.Dropdown(label="Model", choices=[m.name for m in models], value=current_model.name)
with gr.Box(visible=False) as custom_model_group:
custom_model_path = gr.Textbox(label="Custom model path", placeholder="Path to model, e.g. nitrosocke/Arcane-Diffusion", interactive=True)
gr.HTML("Custom models have to be downloaded first, so give it some time.
")
with gr.Row():
prompt = gr.Textbox(label="Prompt", show_label=False, max_lines=2,placeholder="Enter prompt. Style applied automatically").style(container=False)
generate = gr.Button(value="Generate").style(rounded=(False, True, True, False))
# image_out = gr.Image(height=512)
gallery = gr.Gallery(label="Generated images", show_label=False, elem_id="gallery").style(grid=[2], height="auto")
state_info = gr.Textbox(label="State", show_label=False, max_lines=2).style(container=False)
error_output = gr.Markdown()
with gr.Column(scale=45):
with gr.Tab("Options"):
with gr.Group():
neg_prompt = gr.Textbox(label="Negative prompt", placeholder="What to exclude from the image")
n_images = gr.Slider(label="Images", value=1, minimum=1, maximum=10, step=1)
with gr.Row():
guidance = gr.Slider(label="Guidance scale", value=7.5, maximum=15)
steps = gr.Slider(label="Steps", value=current_steps, minimum=2, maximum=75, step=1)
with gr.Row():
width = gr.Slider(label="Width", value=512, minimum=64, maximum=1024, step=8)
height = gr.Slider(label="Height", value=512, minimum=64, maximum=1024, step=8)
seed = gr.Slider(0, 2147483647, label='Seed (0 = random)', value=0, step=1)
with gr.Tab("Image to image"):
with gr.Group():
image = gr.Image(label="Image", height=256, tool="editor", type="pil")
strength = gr.Slider(label="Transformation strength", minimum=0, maximum=1, step=0.01, value=0.5)
if is_colab:
model_name.change(on_model_change, inputs=model_name, outputs=[custom_model_group, prompt], queue=False)
custom_model_path.change(custom_model_changed, inputs=custom_model_path, outputs=None)
# n_images.change(lambda n: gr.Gallery().style(grid=[2 if n > 1 else 1], height="auto"), inputs=n_images, outputs=gallery)
steps.change(on_steps_change, inputs=[steps], outputs=[], queue=False)
inputs = [model_name, prompt, guidance, steps, n_images, width, height, seed, image, strength, neg_prompt]
outputs = [gallery, error_output]
prompt.submit(inference, inputs=inputs, outputs=outputs)
generate.click(inference, inputs=inputs, outputs=outputs)
# ex = gr.Examples([
# ], inputs=[model_name, prompt, guidance, steps], outputs=outputs, fn=inference, cache_examples=False)
ex = gr.Examples(
[
#[models[0].name, "portrait of a beautiful alyx vance half life", 10, 50, "canvas frame, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((b&w)), weird colors, blurry, (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), Photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy"],
#[models[1].name, "Brad Pitt with sunglasses, highly realistic", 7.5, 50, "canvas frame, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((b&w)), weird colors, blurry, (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), Photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy"],
[models[1].name, "(extremely detailed CG unity 8k wallpaper), the most beautiful artwork in the world", 7.5, 50, "human, people, canvas frame, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((b&w)), weird colors, blurry, (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), Photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy"],
#[models[3].name, "(extremely detailed CG unity 8k wallpaper), full shot body photo star lord chris pratt posing in an outdoor spaceship, holding a gun, extremely detailed, trending on ArtStation, trending on CGSociety, Intricate, High Detail, dramatic, realism, beautiful and detailed lighting, shadows", 7.5, 50, "canvas frame, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((b&w)), weird colors, blurry, (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), Photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy"],
#[models[4].name, "(extremely detailed CG unity 8k wallpaper), full body portrait of (david:1.1), staring at us with a mysterious gaze, realistic, masterpiece, highest quality, ((scifi)), lens flare, ((light sparkles)), unreal engine, digital painting, trending on ArtStation, trending on CGSociety, Intricate, High Detail, dramatic, realism, beautiful and detailed lighting, shadows", 7.5, 50, "canvas frame, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((b&w)), weird colors, blurry, (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), Photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy"],
#[models[5].name, "(extremely detailed CG unity 8k wallpaper), full body portrait of (david:1.1), staring at us with a mysterious gaze, realistic, masterpiece, highest quality, ((scifi)), lens flare, ((light sparkles)), unreal engine, digital painting, trending on ArtStation, trending on CGSociety, Intricate, High Detail, dramatic, realism, beautiful and detailed lighting, shadows", 7.5, 50, "canvas frame, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((b&w)), weird colors, blurry, (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), Photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy"],
#[models[6].name, "(extremely detailed CG unity 8k wallpaper), full body portrait of (david:1.1), staring at us with a mysterious gaze, realistic, masterpiece, highest quality, ((scifi)), lens flare, ((light sparkles)), unreal engine, digital painting, trending on ArtStation, trending on CGSociety, Intricate, High Detail, dramatic, realism, beautiful and detailed lighting, shadows", 7.5, 50, "canvas frame, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((b&w)), weird colors, blurry, (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), Photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy"],
#[models[7].name, "(extremely detailed CG unity 8k wallpaper), full body portrait of (david:1.1), staring at us with a mysterious gaze, realistic, masterpiece, highest quality, ((scifi)), lens flare, ((light sparkles)), unreal engine, digital painting, trending on ArtStation, trending on CGSociety, Intricate, High Detail, dramatic, realism, beautiful and detailed lighting, shadows", 7.5, 50, "canvas frame, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((b&w)), weird colors, blurry, (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), Photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy"],
],
inputs=[model_name, prompt, guidance, steps, neg_prompt],
outputs=outputs,
fn=inference,
cache_examples=False,
)
gr.HTML("""
""")
demo.load(update_state_info, inputs=state_info, outputs=state_info, every=0.5, show_progress=False)
print(f"Space built in {time.time() - start_time:.2f} seconds")
# if not is_colab:
demo.queue(concurrency_count=1)
demo.launch(debug=is_colab, share=is_colab)