mindseye-lite / app.py
multimodalart's picture
Revert back
fd00b5e
raw
history blame
No virus
4.7 kB
import gradio as gr
import random
import os
import io, base64
from PIL import Image
import numpy
import shortuuid
latent = gr.Interface.load("spaces/multimodalart/latentdiffusion")
rudalle = gr.Interface.load("spaces/multimodalart/rudalle")
#print(rudalle)
#guided = gr.Interface.load("spaces/EleutherAI/clip-guided-diffusion")
#print(guided)
def text2image_latent(text,steps,width,height,images,diversity):
results = latent(text, steps, width, height, images, diversity)
image_paths = []
image_arrays = []
for image in results[1]:
image_str = image[0]
image_str = image_str.replace("data:image/png;base64,","")
decoded_bytes = base64.decodebytes(bytes(image_str, "utf-8"))
img = Image.open(io.BytesIO(decoded_bytes))
#image_arrays.append(numpy.asarray(img))
url = shortuuid.uuid()
temp_dir = './tmp'
if not os.path.exists(temp_dir):
os.makedirs(temp_dir, exist_ok=True)
image_path = f'{temp_dir}/{url}.png'
img.save(f'{temp_dir}/{url}.png')
image_paths.append(image_path)
return(results[0],image_paths)
def text2image_rudalle(text,aspect,model):
image = rudalle(text,aspect,model)[0]
return(image)
#def text2image_guided(text):
# image = guided(text, None, 10, 600, 0, 0, 0, random.randint(0,2147483647), None, 50, 32)
# print(image)
# image = image[0]
# return(image)
css_mt = {"margin-top": "1em"}
empty = gr.outputs.HTML()
with gr.Blocks() as mindseye:
gr.Markdown("<h1>MindsEye Lite <small><small>run multiple text-to-image models in one place</small></small></h1><p>MindsEye Lite orchestrates multiple text-to-image Hugging Face Spaces in one convenient space, so you can try different models. This work carries the spirit of <a href='https://multimodal.art/mindseye' target='_blank'>MindsEye Beta</a>, a tool to run multiple models with a single UI, but adjusted to the current hardware limitations of Spaces. MindsEye Lite was created by <a style='color: rgb(99, 102, 241);font-weight:bold' href='https://twitter.com/multimodalart' target='_blank'>@multimodalart</a>, keep up with the <a style='color: rgb(99, 102, 241);' href='https://multimodal.art/news' target='_blank'>latest multimodal ai art news here</a> and consider <a style='color: rgb(99, 102, 241);' href='https://www.patreon.com/multimodalart' target='_blank'>supporting us on Patreon</a></div></p>")
gr.Markdown("<style>.mx-auto.container .gr-form-gap {flex-direction: row; gap: calc(1rem * calc(1 - var(--tw-space-y-reverse)));} .mx-auto.container .gr-form-gap .flex-col, .mx-auto.container .gr-form-gap .gr-box{width: 100%}</style>")
text = gr.inputs.Textbox(placeholder="Try writing something..", label="Prompt")
with gr.Column():
with gr.Row():
with gr.Tabs():
with gr.TabItem("Latent Diffusion"):
steps = gr.inputs.Slider(label="Steps - more steps can increase quality but will take longer to generate",default=45,maximum=50,minimum=1,step=1)
width = gr.inputs.Slider(label="Width", default=256, step=32, maximum=256, minimum=32)
height = gr.inputs.Slider(label="Height", default=256, step=32, maximum = 256, minimum=32)
images = gr.inputs.Slider(label="Images - How many images you wish to generate", default=2, step=1, minimum=1, maximum=4)
diversity = gr.inputs.Slider(label="Diversity scale - How different from one another you wish the images to be",default=5.0, minimum=1.0, maximum=15.0)
get_image_latent = gr.Button("Generate Image",css=css_mt)
with gr.TabItem("ruDALLE"):
aspect = gr.inputs.Radio(label="Aspect Ratio", choices=["Square", "Horizontal", "Vertical"],default="Square")
model = gr.inputs.Dropdown(label="Model", choices=["Surrealism","Realism", "Emoji"], default="Surrealism")
get_image_rudalle = gr.Button("Generate Image",css=css_mt)
with gr.TabItem("VQGAN+CLIP"):
pass
with gr.TabItem("V-Diffusion"):
pass
with gr.Row():
with gr.Tabs():
with gr.TabItem("Image output"):
image = gr.outputs.Image()
with gr.TabItem("Gallery output"):
gallery = gr.Gallery(label="Individual images")
get_image_latent.click(text2image_latent, inputs=[text,steps,width,height,images,diversity], outputs=[image,gallery])
get_image_rudalle.click(text2image_rudalle, inputs=[text,aspect,model], outputs=image)
mindseye.launch()