multimodalart's picture
import gradio as gr
import cv2
import torch
import os
from imwatermark import WatermarkEncoder
import numpy as np
from PIL import Image
import re
from datasets import load_dataset
from diffusers import DiffusionPipeline, EulerDiscreteScheduler
from share_btn import community_icon_html, loading_icon_html, share_js
REPO_ID = "stabilityai/stable-diffusion-2"
device = "cuda" if torch.cuda.is_available() else "cpu"
wm = "SDV2"
wm_encoder = WatermarkEncoder()
wm_encoder.set_watermark('bytes', wm.encode('utf-8'))
def put_watermark(img, wm_encoder=None):
if wm_encoder is not None:
img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
img = wm_encoder.encode(img, 'dwtDct')
img = Image.fromarray(img[:, :, ::-1])
return img
repo_id = "stabilityai/stable-diffusion-2"
scheduler = EulerDiscreteScheduler.from_pretrained(repo_id, subfolder="scheduler", prediction_type="v_prediction")
pipe = DiffusionPipeline.from_pretrained(repo_id, torch_dtype=torch.float16, revision="fp16", scheduler=scheduler)
pipe =
#If you have duplicated this Space or is running locally, you can remove this snippet
if "HUGGING_FACE_HUB_TOKEN" in os.environ:
word_list_dataset = load_dataset("stabilityai/word-list", data_files="list.txt", use_auth_token=True)
word_list = word_list_dataset["train"]['text']
def infer(prompt, samples, steps, scale, seed):
#If you have duplicated this Space or is running locally, you can remove this snippet
if "HUGGING_FACE_HUB_TOKEN" in os.environ:
for filter in word_list:
if"\b{filter}\b", prompt):
raise gr.Error("Unsafe content found. Please try again with different prompts.")
generator = torch.Generator(device=device).manual_seed(seed)
images = pipe(prompt, width=768, height=768, num_inference_steps=steps, guidance_scale=scale, num_images_per_prompt=samples, generator=generator).images
images_watermarked = []
for image in images:
image = put_watermark(image, wm_encoder)
return images_watermarked
css = """
.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;
padding-top: 1.5rem;
#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 {
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;
flex: 1 1 50%; border-top-right-radius: 0; border-bottom-right-radius: 0;
gap: 0;
#component-9{margin-top: -19px}
.image_duplication{position: absolute; width: 100px; left: 50px}
block = gr.Blocks(css=css)
examples = [
'A high tech solarpunk utopia in the Amazon rainforest',
'A pikachu fine dining with a view to the Eiffel Tower',
'A mecha robot in a favela in expressionist style',
'an insect robot preparing a delicious meal',
"A small cabin on top of a snowy mountain in the style of Disney, artstation",
with block:
<div style="text-align: center; margin: 0 auto;">
display: inline-flex;
align-items: center;
gap: 0.8rem;
font-size: 1.75rem;
viewBox="0 0 115 115"
<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>
<h1 style="font-weight: 900; margin-bottom: 7px;">
Stable Diffusion 2 Demo
<p style="margin-bottom: 10px; font-size: 94%; line-height: 23px;">
Stable Diffusion 2 is the latest text-to-image model from StabilityAI. <a style="text-decoration: underline;" href="">Access Stable Diffusion 1 Space here</a><br>For faster generation and API
access you can try
style="text-decoration: underline;"
>DreamStudio Beta</a
with gr.Group():
with gr.Box():
with gr.Row(elem_id="prompt-container").style(mobile_collapse=False, equal_height=True):
text = gr.Textbox(
label="Enter your prompt",
placeholder="Enter your prompt",
border=(True, False, True, True),
rounded=(True, False, False, True),
btn = gr.Button("Generate image").style(
rounded=(False, True, True, False),
gallery = gr.Gallery(
label="Generated images", show_label=False, elem_id="gallery"
).style(grid=[2], height="auto")
with gr.Accordion("Custom options", open=False):
samples = gr.Slider(label="Images", minimum=1, maximum=4, value=4, step=1)
steps = gr.Slider(label="Steps", minimum=1, maximum=50, value=25, step=1)
scale = gr.Slider(
label="Guidance Scale", minimum=0, maximum=50, value=9, step=0.1
seed = gr.Slider(
with gr.Group():
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")
ex = gr.Examples(examples=examples, fn=infer, inputs=[text, samples, steps, scale, seed], outputs=[gallery], cache_examples=False)
ex.dataset.headers = [""]
text.submit(infer, inputs=[text, samples, steps, scale, seed], outputs=[gallery]), inputs=[text, samples, steps, scale, seed], outputs=[gallery])
<div class="footer">
<p>Model by <a href="" style="text-decoration: underline;" target="_blank">Stability AI</a> - Gradio Demo by 🤗 Hugging Face using the <a href="" style="text-decoration: underline;" target="_blank">🧨 diffusers library</a>
<div class="acknowledgments">
The model is licensed with a <a href="" 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="" 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="" 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="" style="text-decoration: underline;" target="_blank">model card</a></p>
block.queue(concurrency_count=1, max_size=50).launch(max_threads=150)