Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -261,14 +261,35 @@ with demo:
|
|
261 |
<div>
|
262 |
<h1 style='text-align: center'>Generating Human Motion from Textual Descriptions with Discrete Representations (T2M-GPT)</h1>
|
263 |
This space uses <a href='https://mael-zys.github.io/T2M-GPT/' target='_blank'><b>T2M-GPT models</b></a> based on Vector Quantised-Variational AutoEncoder (VQ-VAE) and Generative Pre-trained Transformer (GPT) for human motion generation from textural descriptions🤗
|
|
|
|
|
|
|
|
|
|
|
264 |
<figure>
|
265 |
-
<img src="https://huggingface.co/vumichien/T2M-GPT/resolve/main/
|
266 |
-
<figcaption>
|
267 |
</figcaption>
|
268 |
</figure>
|
269 |
-
|
270 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
271 |
with gr.Row():
|
|
|
272 |
gr.Markdown('''
|
273 |
### Generate human motion by **T2M-GPT**
|
274 |
##### Step 1. Give prompt text describing human motion
|
|
|
261 |
<div>
|
262 |
<h1 style='text-align: center'>Generating Human Motion from Textual Descriptions with Discrete Representations (T2M-GPT)</h1>
|
263 |
This space uses <a href='https://mael-zys.github.io/T2M-GPT/' target='_blank'><b>T2M-GPT models</b></a> based on Vector Quantised-Variational AutoEncoder (VQ-VAE) and Generative Pre-trained Transformer (GPT) for human motion generation from textural descriptions🤗
|
264 |
+
</div>
|
265 |
+
''')
|
266 |
+
with gr.Row():
|
267 |
+
with gr.Column():
|
268 |
+
gr.Markdown('''
|
269 |
<figure>
|
270 |
+
<img src="https://huggingface.co/vumichien/T2M-GPT/resolve/main/demo_slow1.gif" alt="Demo Slow", width="425", height=480/>
|
271 |
+
<figcaption> a man starts off in an up right position with botg arms extended out by his sides, he then brings his arms down to his body and claps his hands together. after this he wals down amd the the left where he proceeds to sit on a seat
|
272 |
</figcaption>
|
273 |
</figure>
|
274 |
+
''')
|
275 |
+
with gr.Column():
|
276 |
+
gr.Markdown('''
|
277 |
+
<figure>
|
278 |
+
<img src="https://huggingface.co/vumichien/T2M-GPT/resolve/main/demo_slow2.gif" alt="Demo Slow 2", width="425", height=480/>
|
279 |
+
<figcaption> a person puts their hands together, leans forwards slightly then swings the arms from right to left
|
280 |
+
</figcaption>
|
281 |
+
</figure>
|
282 |
+
''')
|
283 |
+
with gr.Column():
|
284 |
+
gr.Markdown('''
|
285 |
+
<figure>
|
286 |
+
<img src="https://huggingface.co/vumichien/T2M-GPT/resolve/main/demo_slow3.gif" alt="Demo Slow 3", width="425", height=480/>
|
287 |
+
<figcaption> a man is practicing the waltz with a partner
|
288 |
+
</figcaption>
|
289 |
+
</figure>
|
290 |
+
''')
|
291 |
with gr.Row():
|
292 |
+
with gr.Column():
|
293 |
gr.Markdown('''
|
294 |
### Generate human motion by **T2M-GPT**
|
295 |
##### Step 1. Give prompt text describing human motion
|