app.py

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")
diffusion = gr.Interface.load("spaces/multimodalart/diffusion")
print(diffusion)
vqgan = gr.Interface.load("spaces/multimodalart/vqgan")

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))
        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(image_paths)
  
def text2image_rudalle(text,aspect,model):
    image = rudalle(text,aspect,model)[0]
    return([image])

def text2image_vqgan(text,width,height,style,steps,flavor):
    results = vqgan(text,width,height,style,steps,flavor)
    return([results])

def text2image_diffusion(text,steps_diff, images_diff, weight, clip):
    results = diffusion(text, steps_diff, images_diff, weight, clip)
    image_paths = []
    image_arrays = []
    for image in results:
        image_str = image
        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))
        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(image_paths)

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 models in one Spaces. This work carries the spirit of <a href='https://multimodal.art/mindseye' target='_blank'>MindsEye Beta</a>, but with simplified versions of the models due to 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>h1{margin-bottom:1em} .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%} .svelte-1bwm9qh > .grid {grid-template-columns: repeat(3,minmax(0,1fr));} @media only screen and (max-width: 1000px){.mx-auto.container .gr-form-gap{flex-direction: column}}</style>")
    text = gr.inputs.Textbox(placeholder="Type your prompt to generate an image", label="Prompt - try adding increments to your prompt such as 'a painting of', 'in the style of Picasso'", default="A giant mecha robot in Rio de Janeiro, oil on canvas")
    with gr.Column():
        with gr.Row():
            with gr.Tabs():
                with gr.TabItem("Latent Diffusion"):
                    gr.Markdown("<a href='https://huggingface.co/spaces/multimodalart/latentdiffusion' target='_blank'>Latent Diffusion</a> is the state of the art of open source text-to-image models, superb in text synthesis. Sometimes struggles with complex prompts")
                    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"):
                    gr.Markdown("<a href='https://huggingface.co/spaces/multimodalart/rudalle' target='_blank'>ruDALLE</a> is a replication of DALL-E 1 in the russian language. No worries, your prompts will be translated automatically to russian. In case you see an error, try again a few times")
                    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"):
                    gr.Markdown("<a href='https://huggingface.co/spaces/multimodalart/vqgan' target='_blank'>VQGAN+CLIP</a> is the most famous text-to-image generator. Can produce good artistic results")
                    width_vq = gr.inputs.Slider(label="Width", default=256, minimum=32, step=32, maximum=512)
                    height_vq= gr.inputs.Slider(label="Height", default=256, minimum=32, step=32, maximum=512)
                    style = gr.inputs.Dropdown(label="Style - Hyper Fast Results is fast but compromises a bit of the quality",choices=["Default","Balanced","Detailed","Consistent Creativity","Realistic","Smooth","Subtle MSE","Hyper Fast Results"],default="Hyper Fast Results")
                    steps_vq = gr.inputs.Slider(label="Steps - more steps can increase quality but will take longer to generate. All styles that are not Hyper Fast need at least 200 steps",default=50,maximum=300,minimum=1,step=1)
                    flavor = gr.inputs.Dropdown(label="Flavor - pick a flavor for the style of the images, based on the images below",choices=["ginger", "cumin", "holywater", "zynth", "wyvern", "aaron", "moth", "juu"])
                    get_image_vqgan = gr.Button("Generate Image",css=css_mt)
                with gr.TabItem("Guided Diffusion"):
                    gr.Markdown("<a href='https://huggingface.co/spaces/multimodalart/diffusion' target='_blank'>Guided Diffusion</a> models produce superb quality results. V-Diffusion is its latest implementation")
                    steps_diff = gr.inputs.Slider(label="Steps - more steps can increase quality but will take longer to generate",default=40,maximum=80,minimum=1,step=1)
                    images_diff = gr.inputs.Slider(label="Number of images in parallel", default=2, maximum=4, minimum=1, step=1)
                    weight = gr.inputs.Slider(label="Weight - how closely the image should resemble the prompt", default=5, maximum=15, minimum=0, step=1)
                    clip = gr.inputs.Checkbox(label="CLIP Guided - improves coherence with complex prompts, makes it slower")
                    get_image_diffusion = gr.Button("Generate Image",css=css_mt)
        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=gallery)
    get_image_rudalle.click(text2image_rudalle, inputs=[text,aspect,model], outputs=gallery)
    get_image_vqgan.click(text2image_vqgan, inputs=[text,width_vq,height_vq,style,steps_vq,flavor],outputs=gallery)
    get_image_diffusion.click(text2image_diffusion, inputs=[text, steps_diff, images_diff, weight, clip],outputs=gallery)
mindseye.launch()