app.py

import os
import sys

import numpy as np
import streamlit as st
from PIL import Image

# import clip


# sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

# import gradio as gr
# from dalle.models import Dalle
# from dalle.utils.utils import clip_score, set_seed


device = "cpu"
# model = Dalle.from_pretrained("minDALL-E/1.3B")  # This will automatically download the pretrained model.
# model.to(device=device)

# model_clip, preprocess_clip = clip.load("ViT-B/32", device=device)
# model_clip.to(device=device)


# def sample(prompt):
#     # Sampling
#     images = (
#         model.sampling(prompt=prompt, top_k=256, top_p=None, softmax_temperature=1.0, num_candidates=3, device=device)
#         .cpu()
#         .numpy()
#     )
#     images = np.transpose(images, (0, 2, 3, 1))

#     # CLIP Re-ranking
#     rank = clip_score(
#         prompt=prompt, images=images, model_clip=model_clip, preprocess_clip=preprocess_clip, device=device
#     )

#     # Save images
#     images = images[rank]
#     # print(rank, images.shape)
#     pil_images = []
#     for i in range(len(images)):
#         im = Image.fromarray((images[i] * 255).astype(np.uint8))
#         pil_images.append(im)

#     # im = Image.fromarray((images[0] * 255).astype(np.uint8))
#     return pil_images


# title = "Interactive demo: ImageGPT"
# description = "Demo for OpenAI's ImageGPT: Generative Pretraining from Pixels. To use it, simply upload an image or use the example image below and click 'submit'. Results will show up in a few seconds."
# article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2109.10282'>ImageGPT: Generative Pretraining from Pixels</a> | <a href='https://openai.com/blog/image-gpt/'>Official blog</a></p>"

# iface = gr.Interface(
#     fn=sample,
#     inputs=[gr.inputs.Textbox(label="What would you like to see?")],
#     outputs=gr.outputs.Image(type="pil", label="Model input + completions"),
#     title=title,
#     description=description,
#     article=article,
#     #examples=examples,
#     enable_queue=True,
# )
# iface.launch(debug=True)

#!/usr/bin/env python
# coding: utf-8


st.sidebar.markdown(
    """
<style>
.aligncenter {
    text-align: center;
}
</style>
<p class="aligncenter">
    <img src="https://raw.githubusercontent.com/borisdayma/dalle-mini/main/img/logo.png"/>
</p>
""",
    unsafe_allow_html=True,
)
st.sidebar.markdown(
    """
___
<p style='text-align: center'>
DALL·E mini is an AI model that generates images from any prompt you give!
</p>

<p style='text-align: center'>
Created by Boris Dayma et al. 2021
<br/>
<a href="https://github.com/borisdayma/dalle-mini" target="_blank">GitHub</a> | <a href="https://wandb.ai/dalle-mini/dalle-mini/reports/DALL-E-mini--Vmlldzo4NjIxODA" target="_blank">Project Report</a>
</p>
        """,
    unsafe_allow_html=True,
)

st.header("DALL·E mini")
st.subheader("Generate images from text")

prompt = st.text_input("What do you want to see?")

DEBUG = False
# if prompt != "":
#     container = st.empty()
#     container.markdown(
#         f"""
#         <style> p {{ margin:0 }} div {{ margin:0 }} </style>
#         <div data-stale="false" class="element-container css-1e5imcs e1tzin5v1">
#         <div class="stAlert">
#         <div role="alert" data-baseweb="notification" class="st-ae st-af st-ag st-ah st-ai st-aj st-ak st-g3 st-am st-b8 st-ao st-ap st-aq st-ar st-as st-at st-au st-av st-aw st-ax st-ay st-az st-b9 st-b1 st-b2 st-b3 st-b4 st-b5 st-b6">
#         <div class="st-b7">
#         <div class="css-whx05o e13vu3m50">
#         <div data-testid="stMarkdownContainer" class="css-1ekf893 e16nr0p30">
#                 <img src="https://raw.githubusercontent.com/borisdayma/dalle-mini/main/app/streamlit/img/loading.gif" width="30"/>
#                 Generating predictions for: <b>{prompt}</b>
#         </div>
#         </div>
#         </div>
#         </div>
#         </div>
#         </div>
#         <small><i>Predictions may take up to 40s under high load. Please stand by.</i></small>
#     """,
#         unsafe_allow_html=True,
#     )

#     print(f"Getting selections: {prompt}")
#     selected = sample(prompt)

#     margin = 0.1  # for better position of zoom in arrow
#     n_columns = 3
#     cols = st.columns([1] + [margin, 1] * (n_columns - 1))
#     for i, img in enumerate(selected):
#         cols[(i % n_columns) * 2].image(img)
#     container.markdown(f"**{prompt}**")

#     st.button("Again!", key="again_button")