import gradio as gr
from datasets import load_dataset
import base64
import re
import os
import requests
from PIL import Image
from io import BytesIO
import user_history
from share_btn import community_icon_html, loading_icon_html, share_js
word_list_dataset = load_dataset("google/word-list-sd", data_files="list.txt", use_auth_token=True)
word_list = word_list_dataset["train"]['text']
def infer(prompt, negative="low_quality", scale=7, profile: gr.OAuthProfile | None = None):
for filter in word_list:
if re.search(rf"\b{filter}\b", prompt):
raise gr.Error("Please try again with a different prompt")
images = []
url = os.getenv('JAX_BACKEND_URL')
payload = {'prompt': prompt, 'negative_prompt': negative, 'guidance_scale': scale}
images_request = requests.post(url, json = payload)
for image in images_request.json()["images"]:
image_b64 = (f"data:image/jpeg;base64,{image}")
images.append(image_b64)
if profile is not None: # avoid conversion on non-logged-in users
pil_image = Image.open(BytesIO(base64.b64decode(image)))
user_history.save_image( # save images + metadata to user history
label=prompt,
image=pil_image,
profile=profile,
metadata={
"prompt": prompt,
"negative_prompt": negative,
"guidance_scale": scale,
},
)
return images, gr.update(visible=True)
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;
}
.gradio-container {
max-width: 730px !important;
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 {padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; max-width: 13rem; margin-left: auto;}
div#share-btn-container > div {flex-direction: row;background: black;align-items: center}
#share-btn-container:hover {background-color: #060606}
#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: 0.5rem !important; padding-bottom: 0.5rem !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}
#share-btn-container.hidden {display: none!important}
.gr-form{
flex: 1 1 50%; border-top-right-radius: 0; border-bottom-right-radius: 0;
}
#prompt-container{
gap: 0;
}
#prompt-container .form{
border-top-right-radius: 0;
border-bottom-right-radius: 0;
}
#gen-button{
border-top-left-radius:0;
border-bottom-left-radius: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}
.tabitem{border: 0 !important}
"""
block = gr.Blocks()
examples = [
[
"A serious capybara at work, wearing a suit",
None,
None
],
[
'A Squirtle fine dining with a view to the London Eye',
None,
None
],
[
'A tamale food cart in front of a Japanese Castle',
None,
None
],
[
'a graffiti of a robot serving meals to people',
None,
None
],
[
'a beautiful cabin in Attersee, Austria, 3d animation style',
None,
None
],
]
with block:
gr.HTML(
"""
Fast Stable Diffusion XL on TPU v5e ⚡
SDXL is a high quality text-to-image model from Stability AI. This demo is running on Google Cloud TPU v5e, to achieve efficient and cost-effective inference of 1024×1024 images. How does it work?
The model is licensed with a Stability AI CreativeML Open RAIL++-M license. The License allows users to take advantage of the model in a wide range of settings (including free use and redistribution) as long as they respect the specific use case restrictions outlined, which correspond to model applications the licensor deems ill-suited for the model or are likely to cause harm. For the full list of restrictions please read the license
Biases and content acknowledgment
Despite how impressive being able to turn text into image is, beware that this model may output content that reinforces or exacerbates societal biases, as well as realistic faces, pornography and violence. You can read more in the model card
"""
)
with gr.Blocks(css=css) as block_with_history:
with gr.Tab("Demo"):
block.render()
with gr.Tab("Past generations"):
user_history.render()
block_with_history.queue(concurrency_count=4, max_size=10).launch()
#block_with_history.launch(server_name="0.0.0.0")