Spaces:
Runtime error
Runtime error
File size: 3,231 Bytes
0ea4415 b442155 0ea4415 b442155 0ea4415 091b9da 6924972 091b9da 0ea4415 b442155 0ea4415 b442155 0ea4415 054827b 0ea4415 |
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 |
import os
import sys
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import numpy as np
import streamlit as st
from PIL import Image
import clip
from dalle.models import Dalle
from dalle.utils.utils import clip_score, download
url = "https://arena.kakaocdn.net/brainrepo/models/minDALL-E/57b008f02ceaa02b779c8b7463143315/1.3B.tar.gz"
root = os.path.expanduser("~/.cache/minDALLE")
filename = os.path.basename(url)
pathname = filename[:-len('.tar.gz')]
expected_md5 = url.split("/")[-2]
download_target = os.path.join(root, filename)
result_path = os.path.join(root, pathname)
if not os.path.exists(result_path):
result_path = download(url, root)
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
st.header("minDALL-E")
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")
|