import gradio as gr
from stability_sdk import client
import stability_sdk.interfaces.gooseai.generation.generation_pb2 as generation
from PIL import Image
import io
import os
import warnings
# theme = gr.themes.Monochrome(
# primary_hue="indigo",
# secondary_hue="blue",
# neutral_hue="slate",
# radius_size=gr.themes.sizes.radius_sm,
# font=[gr.themes.GoogleFont("Open Sans"), "ui-sans-serif", "system-ui", "sans-serif"],
# )
def infer(prompt, api_key):
stability_api = client.StabilityInference(
key=api_key, # API Key reference.
verbose=True, # Print debug messages.
engine="stable-diffusion-xl-beta-v2-2-2", # Set the engine to use for generation.
# Available engines: stable-diffusion-v1 stable-diffusion-v1-5 stable-diffusion-512-v2-0 stable-diffusion-768-v2-0 stable-inpainting-v1-0 stable-inpainting-512-v2-0
)
answers = stability_api.generate(
prompt=prompt,
#seed=992446758, # If a seed is provided, the resulting generated image will be deterministic.
# What this means is that as long as all generation parameters remain the same, you can always recall the same image simply by generating it again.
# Note: This isn't quite the case for Clip Guided generations, which we'll tackle in a future example notebook.
steps=50, # Amount of inference steps performed on image generation. Defaults to 30.
cfg_scale=8.0, # Influences how strongly your generation is guided to match your prompt.
# Setting this value higher increases the strength in which it tries to match your prompt.
# Defaults to 7.0 if not specified.
width=512, # Generation width, defaults to 512 if not included.
height=512, # Generation height, defaults to 512 if not included.
samples=2, # Number of images to generate, defaults to 1 if not included.
sampler=generation.SAMPLER_K_DPMPP_2M # Choose which sampler we want to denoise our generation with.
# Defaults to k_dpmpp_2m if not specified. Clip Guidance only supports ancestral samplers.
# (Available Samplers: ddim, plms, k_euler, k_euler_ancestral, k_heun, k_dpm_2, k_dpm_2_ancestral, k_dpmpp_2s_ancestral, k_lms, k_dpmpp_2m)
)
results = []
for resp in answers:
for artifact in resp.artifacts:
if artifact.finish_reason == generation.FILTER:
warnings.warn(
"Your request activated the API's safety filters and could not be processed."
"Please modify the prompt and try again.")
if artifact.type == generation.ARTIFACT_IMAGE:
img = Image.open(io.BytesIO(artifact.binary))
results.append(img)
return results
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;
}
.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}
"""
with gr.Blocks(css = css) as demo:
gr.HTML(
"""
Stable Diffusion XL Demo
This is an unoffical demo for Stable Diffusion XL, which is the latest stable diffusion model released by Stability AI. The main features include Next-level photorealism capabilities, image composition and face generation, use of shorter prompts to create descriptive imagery, greater capability to produce legible text and rich visuals and jaw-dropping aesthetics. Please refer to
the official website. for further information
"""
)
gr.HTML("
You can duplicate this Space to run it privately without a queue for shorter queue times :
")
api_key_input = gr.Textbox(type = "password", label = "Enter your StabilityAI API key here")
with gr.Row(elem_id="prompt-container").style(mobile_collapse=False, equal_height=True):
with gr.Column():
text = gr.Textbox(
label="Enter your prompt",
show_label=False,
max_lines=1,
placeholder="Enter your prompt",
elem_id="prompt-text-input",
).style(
border=(True, False, True, True),
rounded=(True, False, False, True),
container=False,
)
btn = gr.Button("Generate image").style(
margin=False,
rounded=(False, True, True, False),
full_width=False,
)
gallery = gr.Gallery(
label="Generated images", show_label=False, elem_id="gallery"
).style(grid=[2], height="auto")
btn.click(infer, inputs=[text, api_key_input], outputs=[gallery])
examples = [
["Vintage hot rod with custom flame paint job"],
["Ancient, mysterious temple in a mountain range, surrounded by misty clouds and tall peaks"],
["Glimpses of a herd of wild elephants crossing a savanna"],
["Beautiful waterfall in a lush jungle, with sunlight shining through the trees,"]
]
ex = gr.Examples(examples=examples,inputs=[text], cache_examples=False)
demo.launch()
