clementchadebec commited on
Commit
8f3e0f4
1 Parent(s): 752f3e2

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -105,7 +105,7 @@ with gr.Blocks(css=css) as demo:
105
  This is an interactive demo of [Flash Diffusion](https://gojasper.github.io/flash-diffusion-project/), a diffusion distillation method proposed in [Flash Diffusion: Accelerating Any Conditional
106
  Diffusion Model for Few Steps Image Generation](http://arxiv.org/abs/2406.02347) *by Clément Chadebec, Onur Tasar, Eyal Benaroche and Benjamin Aubin.*
107
  [This model](https://huggingface.co/jasperai/flash-sd3) is a **90.4M** LoRA distilled version of [SD3](https://huggingface.co/stabilityai/stable-diffusion-3-medium) model that is able to generate 1024x1024 images in **4 steps**.
108
- The model was trained for ~45 hours on 2 H100 GPUs. Results can be compared with the teacher model [here](https://huggingface.co/spaces/stabilityai/stable-diffusion-3-medium)
109
  Currently running on {power_device}.
110
  """
111
  )
 
105
  This is an interactive demo of [Flash Diffusion](https://gojasper.github.io/flash-diffusion-project/), a diffusion distillation method proposed in [Flash Diffusion: Accelerating Any Conditional
106
  Diffusion Model for Few Steps Image Generation](http://arxiv.org/abs/2406.02347) *by Clément Chadebec, Onur Tasar, Eyal Benaroche and Benjamin Aubin.*
107
  [This model](https://huggingface.co/jasperai/flash-sd3) is a **90.4M** LoRA distilled version of [SD3](https://huggingface.co/stabilityai/stable-diffusion-3-medium) model that is able to generate 1024x1024 images in **4 steps**.
108
+ Results can be compared with the teacher model [here](https://huggingface.co/spaces/stabilityai/stable-diffusion-3-medium).
109
  Currently running on {power_device}.
110
  """
111
  )