Spaces:
Sleeping
Sleeping
clementchadebec
commited on
Commit
•
03e20b2
1
Parent(s):
d740c01
Update app.py
Browse files
app.py
CHANGED
@@ -93,7 +93,8 @@ with gr.Blocks(css=css) as demo:
|
|
93 |
gr.Markdown(
|
94 |
f"""
|
95 |
# ⚡ Flash Diffusion: FlashPixart ⚡
|
96 |
-
This is an interactive demo of [Flash Diffusion](http://arxiv.org/abs/2406.02347), a diffusion distillation method proposed in [
|
|
|
97 |
[This model](https://huggingface.co/jasperai/flash-pixart) is a **66.5M** LoRA distilled version of [Pixart-α](https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS) model that is able to generate 1024x1024 images in **4 steps**.
|
98 |
Currently running on {power_device}.
|
99 |
"""
|
|
|
93 |
gr.Markdown(
|
94 |
f"""
|
95 |
# ⚡ Flash Diffusion: FlashPixart ⚡
|
96 |
+
This is an interactive demo of [Flash Diffusion](http://arxiv.org/abs/2406.02347), a diffusion distillation method proposed in [Flash Diffusion: Accelerating Any Conditional
|
97 |
+
Diffusion Model for Few Steps Image Generation](http://arxiv.org/abs/2406.02347) *by Clément Chadebec, Onur Tasar, Eyal Benaroche and Benjamin Aubin.*
|
98 |
[This model](https://huggingface.co/jasperai/flash-pixart) is a **66.5M** LoRA distilled version of [Pixart-α](https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS) model that is able to generate 1024x1024 images in **4 steps**.
|
99 |
Currently running on {power_device}.
|
100 |
"""
|