---
license: cc-by-nc-4.0
library_name: diffusers
base_model: runwayml/stable-diffusion-v1-5
tags:
- lora
- text-to-image
---
# ⚡ FlashDiffusion: FlashSD ⚡


Flash Diffusion is a diffusion distillation method proposed in [ADD ARXIV]() *by Clément Chadebec, Onur Tasar and Benjamin Aubin.*
This model is a 26.4M LoRA distilled version of SD1.5 model. The main purpose of this model is to reproduce the main results of the paper.


<p align="center">
   <img style="width:700px;" src="images/hf_grid.png">
</p>

# How to use?

The model can be used using the `StableDiffusionPipeline` from `diffusers` library directly. It can allow reducing the number of required sampling steps to **2-4 steps**.

```python
from diffusers import StableDiffusionPipeline, LCMScheduler

adapter_id = "jasperai/flash-sd"

pipe = StableDiffusionPipeline.from_pretrained(
  "runwayml/stable-diffusion-v1-5",
  use_safetensors=True,
)

pipe.scheduler = LCMScheduler.from_pretrained(
  "runwayml/stable-diffusion-v1-5",
  subfolder="scheduler",
  timestep_spacing="trailing",
)
pipe.to("cuda")

# Fuse and load LoRA weights
pipe.load_lora_weights(adapter_id)
pipe.fuse_lora()

prompt = "A raccoon reading a book in a lush forest."

image = pipe(prompt, num_inference_steps=4, guidance_scale=0).images[0]
```
<p align="center">
   <img style="width:400px;" src="images/raccoon.png">
</p>

# Training Details
The model was trained for 20k iterations on 2 H100 GPUs (representing approx. **13 hours** of training). Please refer to the [paper]() for further parameters details. 

**Metrics on COCO 2017 validation set**

- 2 steps:
  - FID-5k: 22.6
  - CLIP Score (ViT-g/14): 0.306
  
- 4 steps:
  - FID-5k: 22.5
  - CLIP Score (ViT-g/14):

**Metrics on COCO 2014 validation**
- 2 steps:
  - FID-30k:
- 4 steps:
  - FID-30k: