sd21_zero / app.py
John6666's picture
Upload 4 files
56e89f4 verified
import spaces
import gradio as gr
from share_btn import community_icon_html, loading_icon_html, share_js
import torch
from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
import os, uuid, random, subprocess
MODELS = ["Manojb/stable-diffusion-2-1-base"]
#MODELS = ["Manojb/stable-diffusion-2-base", "Manojb/stable-diffusion-2-1-base"]
DURATION = 10
IS_ZERO_GPU = bool(os.getenv("SPACES_ZERO_GPU"))
IS_CUDA = True if IS_ZERO_GPU else bool(torch.cuda.is_available())
DEVICE = "cuda" if IS_CUDA else "cpu"
DTYPE = torch.float16 if IS_CUDA else torch.float32
if IS_ZERO_GPU:
print("Running on Zero GPU.")
os.environ["ZEROGPU_SIZE"] = "auto" # https://huggingface.co/posts/cbensimon/356529804559377
subprocess.run("rm -rf /data-nvme/zerogpu-offload/*", shell=True)
torch.set_float32_matmul_precision("high") # https://pytorch.org/blog/accelerating-generative-ai-3/
def load_pipelines(model_ids):
pipes = {}
for model_id in model_ids:
scheduler = EulerDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
pipes[model_id] = StableDiffusionPipeline.from_pretrained(model_id, scheduler=scheduler, torch_dtype=DTYPE).to(DEVICE)
return pipes
PIPES = load_pipelines(MODELS)
def gen_random_seed():
return random.randint(0, 2147483647)
@spaces.GPU(duration=DURATION)
def infer(prompt, negative, scale, model_id=MODELS[0], images=[], progress=gr.Progress(track_tqdm=True)):
if images is None: images = []
try:
pipe = PIPES.get(model_id, None)
if pipe is None: raise gr.Error(f"Pipeline not found: {model_id}")
image = pipe(prompt=prompt, negative_prompt=negative, guidance_scale=scale).images[0]
file_path = f"{uuid.uuid4()}.jpg"
image.save(file_path)
if image: images.append(file_path)
return images
except Exception as e:
print(e)
raise gr.Error(f"Error: {e}")
@spaces.GPU(duration=DURATION)
def infer_advance(prompt, negative, scale, width, height, steps, seed, samples, model_id=MODELS[0], images=[], progress=gr.Progress(track_tqdm=True)):
if images is None: images = []
try:
pipe = PIPES.get(model_id, None)
if pipe is None: raise gr.Error(f"Pipeline not found: {model_id}")
for i in range(samples):
generator = torch.Generator(device=DEVICE).manual_seed(seed=seed if i==0 else gen_random_seed())
image = pipe(prompt=prompt, negative_prompt=negative, guidance_scale=scale, width=width, height=height, num_inference_steps=steps, generator=generator).images[0]
file_path = f"{uuid.uuid4()}.jpg"
image.save(file_path)
if image: images.append(file_path)
yield images
except Exception as e:
print(e)
raise gr.Error(f"Error: {e}")
css = """
.gradio-container {
max-width: 768px !important;
}
.gradio-container {
font-family: 'IBM Plex Sans', sans-serif;
}
.gr-button {
color: white;
border-color: black;
background: black;
}
input[type='range'] {
accent-color: black;
}
.dark input[type='range'] {
accent-color: #dfdfdf;
}
.container {
max-width: 730px;
margin: auto;
}
#gallery {
min-height: 22rem;
margin-bottom: 15px;
margin-left: auto;
margin-right: auto;
border-bottom-right-radius: .5rem !important;
border-bottom-left-radius: .5rem !important;
}
#gallery>div>.h-full {
min-height: 20rem;
}
.details:hover {
text-decoration: underline;
}
.gr-button {
white-space: nowrap;
}
.gr-button:focus {
border-color: rgb(147 197 253 / var(--tw-border-opacity));
outline: none;
box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000);
--tw-border-opacity: 1;
--tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color);
--tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color);
--tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity));
--tw-ring-opacity: .5;
}
#advanced-btn {
font-size: .7rem !important;
line-height: 19px;
margin-top: 12px;
margin-bottom: 12px;
padding: 2px 8px;
border-radius: 14px !important;
}
#advanced-options {
display: none;
margin-bottom: 20px;
}
.footer {
margin-bottom: 45px;
margin-top: 35px;
text-align: center;
border-bottom: 1px solid #e5e5e5;
}
.footer>p {
font-size: .8rem;
display: inline-block;
padding: 0 10px;
transform: translateY(10px);
background: white;
}
.dark .footer {
border-color: #303030;
}
.dark .footer>p {
background: #0b0f19;
}
.acknowledgments h4{
margin: 1.25em 0 .25em 0;
font-weight: bold;
font-size: 115%;
}
.animate-spin {
animation: spin 1s linear infinite;
}
@keyframes spin {
from {
transform: rotate(0deg);
}
to {
transform: rotate(360deg);
}
}
#share-btn-container {
display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem;
margin-top: 10px;
margin-left: auto;
}
#share-btn-container .styler{
background-color: #000000;
}
#share-btn {
all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important;right:0;
}
#share-btn * {
all: unset;
}
#share-btn-container div:nth-child(-n+2){
width: auto !important;
min-height: 0px !important;
}
#share-btn-container .wrap {
display: none !important;
}
.gr-form{
flex: 1 1 50%; border-top-right-radius: 0; border-bottom-right-radius: 0;
}
#prompt-container{
gap: 0;
}
#prompt-text-input, #negative-prompt-text-input{padding: .45rem 0.625rem}
#component-16{border-top-width: 1px!important;margin-top: 1em}
.image_duplication{position: absolute; width: 100px; left: 50px}
button{height: 100%}
.info { align-items: center; text-align: center; }
"""
block = gr.Blocks()
examples = [
[
'A high tech solarpunk utopia in the Amazon rainforest',
'low quality',
9
],
[
'A pikachu fine dining with a view to the Eiffel Tower',
'low quality',
9
],
[
'A mecha robot in a favela in expressionist style',
'low quality, 3d, photorealistic',
9
],
[
'an insect robot preparing a delicious meal',
'low quality, illustration',
9
],
[
"A small cabin on top of a snowy mountain in the style of Disney, artstation",
'low quality, ugly',
9
],
]
with block:
gr.HTML(
"""
<div style="text-align: center; margin: 0 auto;">
<div
style="
display: inline-flex;
align-items: center;
gap: 0.8rem;
font-size: 1.75rem;
"
>
<svg
width="0.65em"
height="0.65em"
viewBox="0 0 115 115"
fill="none"
xmlns="http://www.w3.org/2000/svg"
>
<rect width="23" height="23" fill="white"></rect>
<rect y="69" width="23" height="23" fill="white"></rect>
<rect x="23" width="23" height="23" fill="#AEAEAE"></rect>
<rect x="23" y="69" width="23" height="23" fill="#AEAEAE"></rect>
<rect x="46" width="23" height="23" fill="white"></rect>
<rect x="46" y="69" width="23" height="23" fill="white"></rect>
<rect x="69" width="23" height="23" fill="black"></rect>
<rect x="69" y="69" width="23" height="23" fill="black"></rect>
<rect x="92" width="23" height="23" fill="#D9D9D9"></rect>
<rect x="92" y="69" width="23" height="23" fill="#AEAEAE"></rect>
<rect x="115" y="46" width="23" height="23" fill="white"></rect>
<rect x="115" y="115" width="23" height="23" fill="white"></rect>
<rect x="115" y="69" width="23" height="23" fill="#D9D9D9"></rect>
<rect x="92" y="46" width="23" height="23" fill="#AEAEAE"></rect>
<rect x="92" y="115" width="23" height="23" fill="#AEAEAE"></rect>
<rect x="92" y="69" width="23" height="23" fill="white"></rect>
<rect x="69" y="46" width="23" height="23" fill="white"></rect>
<rect x="69" y="115" width="23" height="23" fill="white"></rect>
<rect x="69" y="69" width="23" height="23" fill="#D9D9D9"></rect>
<rect x="46" y="46" width="23" height="23" fill="black"></rect>
<rect x="46" y="115" width="23" height="23" fill="black"></rect>
<rect x="46" y="69" width="23" height="23" fill="black"></rect>
<rect x="23" y="46" width="23" height="23" fill="#D9D9D9"></rect>
<rect x="23" y="115" width="23" height="23" fill="#AEAEAE"></rect>
<rect x="23" y="69" width="23" height="23" fill="black"></rect>
</svg>
<h1 style="font-weight: 900; margin-bottom: 7px;margin-top:5px">
Stable Diffusion 2.1 Demo
</h1>
</div>
<p style="margin-bottom: 10px; font-size: 94%; line-height: 23px;">
Stable Diffusion 2.1 is the latest text-to-image model from StabilityAI. <a style="text-decoration: underline;" href="https://huggingface.co/spaces/stabilityai/stable-diffusion-1">Access Stable Diffusion 1 Space here</a><br>For faster generation and API
access you can try
<a
href="http://beta.dreamstudio.ai/"
style="text-decoration: underline;"
target="_blank"
>DreamStudio Beta</a
>.</a>
</p>
</div>
"""
, visible=False)
with gr.Group():
with gr.Row(elem_id="prompt-container"):
with gr.Column(scale=3):
text = gr.Textbox(
label="Enter your prompt",
show_label=False,
max_lines=1,
placeholder="Enter your prompt",
elem_id="prompt-text-input",
)
negative = gr.Textbox(
label="Enter your negative prompt",
show_label=False,
max_lines=1,
placeholder="Enter a negative prompt",
elem_id="negative-prompt-text-input",
)
with gr.Column(scale=1, min_width=150):
btn = gr.Button("Generate image")
gallery = gr.Gallery(
label="Generated images", show_label=False, elem_id="gallery",
)
with gr.Group(elem_id="container-advanced-btns"):
with gr.Group(elem_id="share-btn-container"):
community_icon = gr.HTML(community_icon_html)
loading_icon = gr.HTML(loading_icon_html)
share_button = gr.Button("Share to community", elem_id="share-btn")
with gr.Accordion("Advanced settings", open=False):
model_id = gr.Dropdown(label="Model", choices=MODELS, value=MODELS[0], allow_custom_value=True)
samples = gr.Slider(label="Images", minimum=1, maximum=4, value=4, step=1)
with gr.Row():
width = gr.Slider(label="Width", minimum=256, maximum=2048, step=32, value=768)
height = gr.Slider(label="Height", minimum=256, maximum=2048, step=32, value=768)
steps = gr.Slider(label="Steps", minimum=1, maximum=50, value=45, step=1)
guidance_scale = gr.Slider(
label="Guidance Scale", minimum=0, maximum=50, value=9, step=0.1
)
seed = gr.Slider(
label="Seed",
minimum=0,
maximum=2147483647,
step=1,
randomize=True,
)
advanced_button = gr.Button("Generate images (advanced)")
ex = gr.Examples(examples=examples, fn=infer, inputs=[text, negative, guidance_scale], outputs=[gallery], cache_examples=False)
ex.dataset.headers = [""]
negative.submit(infer, inputs=[text, negative, guidance_scale, model_id, gallery], outputs=[gallery])
text.submit(infer, inputs=[text, negative, guidance_scale, model_id, gallery], outputs=[gallery])
btn.click(infer, inputs=[text, negative, guidance_scale, model_id, gallery], outputs=[gallery])
advanced_button.click(infer_advance, inputs=[text, negative, guidance_scale, width, height, steps, seed, samples, model_id, gallery], outputs=[gallery])
share_button.click(
None,
[],
[],
js=share_js,
)
gr.HTML(
"""
<div class="footer">
<p>Model by <a href="https://huggingface.co/stabilityai" style="text-decoration: underline;" target="_blank">StabilityAI</a> - backend running JAX on TPUs due to generous support of <a href="https://sites.research.google/trc/about/" style="text-decoration: underline;" target="_blank">Google TRC program</a> - Gradio Demo by 🤗 Hugging Face
</p>
</div>
"""
)
with gr.Accordion(label="License", open=False):
gr.HTML(
"""<div class="acknowledgments">
<p><h4>LICENSE</h4>
The model is licensed with a <a href="https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL" style="text-decoration: underline;" target="_blank">CreativeML OpenRAIL++</a> license. The authors claim no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in this license. The license forbids you from sharing any content that violates any laws, produce any harm to a person, disseminate any personal information that would be meant for harm, spread misinformation and target vulnerable groups. For the full list of restrictions please <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" target="_blank" style="text-decoration: underline;" target="_blank">read the license</a></p>
<p><h4>Biases and content acknowledgment</h4>
Despite how impressive being able to turn text into image is, beware to the fact that this model may output content that reinforces or exacerbates societal biases, as well as realistic faces, pornography and violence. The model was trained on the <a href="https://laion.ai/blog/laion-5b/" style="text-decoration: underline;" target="_blank">LAION-5B dataset</a>, which scraped non-curated image-text-pairs from the internet (the exception being the removal of illegal content) and is meant for research purposes. You can read more in the <a href="https://huggingface.co/CompVis/stable-diffusion-v1-4" style="text-decoration: underline;" target="_blank">model card</a></p>
</div>
"""
)
block.queue().launch(css=css, ssr_mode=False, show_error=True)