Spaces:
Running
Running
Sunil Surendra Singh
commited on
Commit
β’
a80e18e
1
Parent(s):
9d8add7
Added github action for deployment
Browse files- .github/workflows/main.yml +19 -0
- README.md +5 -5
.github/workflows/main.yml
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
name: Sync to Hugging Face hub
|
2 |
+
on:
|
3 |
+
push:
|
4 |
+
branches: [main]
|
5 |
+
# to run this workflow manually from the Actions tab
|
6 |
+
workflow_dispatch:
|
7 |
+
|
8 |
+
jobs:
|
9 |
+
sync-to-hub:
|
10 |
+
runs-on: ubuntu-latest
|
11 |
+
steps:
|
12 |
+
- uses: actions/checkout@v3
|
13 |
+
with:
|
14 |
+
fetch-depth: 0
|
15 |
+
lfs: true
|
16 |
+
- name: Push to hub
|
17 |
+
env:
|
18 |
+
HF_TOKEN: ${{ secrets.HF_TOKEN }}
|
19 |
+
run: git push --force https://sssingh:$HF_TOKEN@huggingface.co/spaces/sssingh/pic-to-story main
|
README.md
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
---
|
2 |
-
title: Picture to Story Generator
|
3 |
emoji: π
|
4 |
colorFrom: yellow
|
5 |
colorTo: red
|
6 |
sdk: gradio
|
7 |
-
sdk_version:
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
license: mit
|
@@ -16,7 +16,7 @@ license: mit
|
|
16 |
# The Storyteller
|
17 |
***A Large Language Model Based App to Generate Stories from Pictures***
|
18 |
|
19 |
-
<img src="https://github.com/sssingh/pic-to-story/blob/main/
|
20 |
|
21 |
>This application employs a Text2Image model hosted by Huggingface, which is a modified adaptation of the Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation (BLIP) model. First, it generates a descriptive caption for an image. Then, it utilizes this caption to construct a prompt, which is subsequently used with OpenAI's GPT-3.5 to create engaging stories based on the provided picture.
|
22 |
|
@@ -30,7 +30,7 @@ BLIP model details can be found [here](https://huggingface.co/Sof22/image-captio
|
|
30 |
|
31 |
App UI is shown below:
|
32 |
|
33 |
-
<img src="https://github.com/sssingh/pic-to-story/blob/main/
|
34 |
|
35 |
**Dark Mode Toggle**: Activate it to switch between dark and light mode.
|
36 |
**Image Selector**: Click on it to pick an image from your computer, or drag and drop an image onto it directly. Click the 'X' to clear the selection and resets the app.
|
@@ -43,7 +43,7 @@ App UI is shown below:
|
|
43 |
|
44 |
The app includes pre-defined examples for your convenience, allowing you to quickly test its capabilities. Explore the examples section, choose one, and click "Generate Story" without needing to upload an image.
|
45 |
|
46 |
-
<img src="https://github.com/sssingh/pic-to-story/blob/main/
|
47 |
|
48 |
# Project Source
|
49 |
[π Visit GitHub Repo](https://github.com/sssingh/pic-to-story)
|
|
|
1 |
---
|
2 |
+
title: Picture to Story Generator
|
3 |
emoji: π
|
4 |
colorFrom: yellow
|
5 |
colorTo: red
|
6 |
sdk: gradio
|
7 |
+
sdk_version: 3.46.0
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
license: mit
|
|
|
16 |
# The Storyteller
|
17 |
***A Large Language Model Based App to Generate Stories from Pictures***
|
18 |
|
19 |
+
<img src="https://github.com/sssingh/pic-to-story/blob/main/assets/title.jpg?raw=true" width="1000" height="350"/><br><br>
|
20 |
|
21 |
>This application employs a Text2Image model hosted by Huggingface, which is a modified adaptation of the Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation (BLIP) model. First, it generates a descriptive caption for an image. Then, it utilizes this caption to construct a prompt, which is subsequently used with OpenAI's GPT-3.5 to create engaging stories based on the provided picture.
|
22 |
|
|
|
30 |
|
31 |
App UI is shown below:
|
32 |
|
33 |
+
<img src="https://github.com/sssingh/pic-to-story/blob/main/assets/story-teller-app.png?raw=true" width="1000" height="450"/><br><br>
|
34 |
|
35 |
**Dark Mode Toggle**: Activate it to switch between dark and light mode.
|
36 |
**Image Selector**: Click on it to pick an image from your computer, or drag and drop an image onto it directly. Click the 'X' to clear the selection and resets the app.
|
|
|
43 |
|
44 |
The app includes pre-defined examples for your convenience, allowing you to quickly test its capabilities. Explore the examples section, choose one, and click "Generate Story" without needing to upload an image.
|
45 |
|
46 |
+
<img src="https://github.com/sssingh/pic-to-story/blob/main/assets/story-teller-examples.png?raw=true" width="1000" height="350"/><br><br>
|
47 |
|
48 |
# Project Source
|
49 |
[π Visit GitHub Repo](https://github.com/sssingh/pic-to-story)
|