Spaces:
Runtime error
Runtime error
typo, cancel button is borked on hf
Browse files
app.py
CHANGED
|
@@ -122,9 +122,9 @@ with gr.Blocks(title = 'Make-A-Video Stable Diffusion JAX', analytics_enabled =
|
|
| 122 |
intro1 = gr.Markdown("""
|
| 123 |
# Make-A-Video Stable Diffusion JAX
|
| 124 |
|
| 125 |
-
We have extended a pretrained
|
| 126 |
We take advantage of the extra 5 input channels of the inpaint model to guide the video generation with a hint image and mask.
|
| 127 |
-
The hint image can be given by the
|
| 128 |
|
| 129 |
The temporal convolution and attention is a port of [Make-A-Video Pytorch](https://github.com/lucidrains/make-a-video-pytorch/blob/main/make_a_video_pytorch) to FLAX.
|
| 130 |
It is a pseudo 3D convolution that seperately convolves accross the spatial dimension in 2D and over the temporal dimension in 1D.
|
|
@@ -155,7 +155,7 @@ with gr.Blocks(title = 'Make-A-Video Stable Diffusion JAX', analytics_enabled =
|
|
| 155 |
with gr.Row(variant = variant):
|
| 156 |
with gr.Column(variant = variant):
|
| 157 |
with gr.Row():
|
| 158 |
-
cancel_button = gr.Button(value = 'Cancel')
|
| 159 |
submit_button = gr.Button(value = 'Make A Video', variant = 'primary')
|
| 160 |
prompt_input = gr.Textbox(
|
| 161 |
label = 'Prompt',
|
|
@@ -269,7 +269,7 @@ with gr.Blocks(title = 'Make-A-Video Stable Diffusion JAX', analytics_enabled =
|
|
| 269 |
inputs = trigger_inputs,
|
| 270 |
outputs = will_trigger
|
| 271 |
)
|
| 272 |
-
cancel_button.click(fn = lambda: None, cancels = ev)
|
| 273 |
|
| 274 |
demo.queue(concurrency_count = 1, max_size = 32)
|
| 275 |
demo.launch()
|
|
|
|
| 122 |
intro1 = gr.Markdown("""
|
| 123 |
# Make-A-Video Stable Diffusion JAX
|
| 124 |
|
| 125 |
+
We have extended a pretrained LDM inpainting image generation model with temporal convolutions and attention.
|
| 126 |
We take advantage of the extra 5 input channels of the inpaint model to guide the video generation with a hint image and mask.
|
| 127 |
+
The hint image can be given by the user, otherwise it is generated by an generative image model.
|
| 128 |
|
| 129 |
The temporal convolution and attention is a port of [Make-A-Video Pytorch](https://github.com/lucidrains/make-a-video-pytorch/blob/main/make_a_video_pytorch) to FLAX.
|
| 130 |
It is a pseudo 3D convolution that seperately convolves accross the spatial dimension in 2D and over the temporal dimension in 1D.
|
|
|
|
| 155 |
with gr.Row(variant = variant):
|
| 156 |
with gr.Column(variant = variant):
|
| 157 |
with gr.Row():
|
| 158 |
+
#cancel_button = gr.Button(value = 'Cancel')
|
| 159 |
submit_button = gr.Button(value = 'Make A Video', variant = 'primary')
|
| 160 |
prompt_input = gr.Textbox(
|
| 161 |
label = 'Prompt',
|
|
|
|
| 269 |
inputs = trigger_inputs,
|
| 270 |
outputs = will_trigger
|
| 271 |
)
|
| 272 |
+
#cancel_button.click(fn = lambda: None, cancels = ev)
|
| 273 |
|
| 274 |
demo.queue(concurrency_count = 1, max_size = 32)
|
| 275 |
demo.launch()
|