Hugging Face's logo

Spaces:
valhalla
/
minDALLE
Runtime error

App Files Community
1
minDALLE
File size: 4,504 Bytes 
b442155
 
 
aff2150
b442155
aff2150
b442155
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
 
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")