---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
base_model: stabilityai/stable-diffusion-xl-base-1.0
license: cc-by-nc-nd-4.0
inference: False
---
# ⚡ Flash Diffusion: FlashSDXL ⚡


Flash Diffusion is a diffusion distillation method proposed in [Flash Diffusion: Accelerating Any Conditional
Diffusion Model for Few Steps Image Generation](http://arxiv.org/abs/2406.02347) *by Clément Chadebec, Onur Tasar, Eyal Benaroche, and Benjamin Aubin* from Jasper Research.
This model is a **108M LoRA** distilled version of [SDXL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) model that is able to generate images in **4 steps**. The main purpose of this model is to reproduce the main results of the paper.
See our [live demo](https://huggingface.co/spaces/jasperai/FlashPixart) and official [Github repo](https://github.com/gojasper/flash-diffusion).


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

# How to use?

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

```python
from diffusers import DiffusionPipeline, LCMScheduler

adapter_id = "jasperai/flash-sdxl"

pipe = DiffusionPipeline.from_pretrained(
  "stabilityai/stable-diffusion-xl-base-1.0",
  use_safetensors=True,
)

pipe.scheduler = LCMScheduler.from_pretrained(
  "stabilityai/stable-diffusion-xl-base-1.0",
  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>

# Combining Flash Diffusion with Existing LoRAs 🎨

FlashSDXL can also be combined with existing LoRAs to unlock few steps generation in a **training free** manner. It can be integrated straight to Hugging Face pipelines. See an example below.

```python
from diffusers import DiffusionPipeline, LCMScheduler
import torch

user_lora_id = "TheLastBen/Papercut_SDXL"
trigger_word = "papercut"

flash_lora_id = "jasperai/flash-sdxl"

# Load Pipeline
pipe = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    variant="fp16"
)

# Set scheduler
pipe.scheduler = LCMScheduler.from_config(
    pipe.scheduler.config
)

# Load LoRAs
pipe.load_lora_weights(flash_lora_id, adapter_name="flash")
pipe.load_lora_weights(user_lora_id, adapter_name="lora")

pipe.set_adapters(["flash", "lora"], adapter_weights=[1.0, 1.0])
pipe.to(device="cuda", dtype=torch.float16)

prompt = f"{trigger_word} a cute corgi"

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

# How to use in Comfy?

To use FlashSDXL locally using Comfyui you need to :

1. Make sure your comfyUI install is up to date
2. Download the checkpoint from [huggingface](https://huggingface.co/jasperai/flash-sdxl).
   In case you wonder how, go to "Files and Version" go to `comfy/` folder and hit the download button next to the `FlashSDXL.safetensors`
3. Move the new checkpoint file to your local `comfyUI/models/loras/.` folder
4. Use it as a LoRA on top of `sd_xl_base_1.0_0.9vae.safetensors`, a simple comfyui `workflow.json` is provided in this repo (available in the same `comfy/` folder)

> Disclaimer : Model has been trained to work with a cfg scale of 1 and a lcm scheduler but parameters can be tweaked a bit.

# Combining Flash Diffusion with Existing ControlNets 🎨

FlashSDXL can also be combined with existing ControlNets to unlock few steps generation in a **training free** manner. It can be integrated straight to Hugging Face pipelines. See an example below.

```python
import torch
import cv2
import numpy as np
from PIL import Image

from diffusers import StableDiffusionXLControlNetPipeline, ControlNetModel, LCMScheduler
from diffusers.utils import load_image, make_image_grid

flash_lora_id = "jasperai/flash-sdxl"

image = load_image(
    "https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png"
).resize((1024, 1024))

image = np.array(image)

image = cv2.Canny(image, 100, 200)
image = image[:, :, None].repeat(3, 2)
canny_image = Image.fromarray(image)

# Load ControlNet
controlnet = ControlNetModel.from_pretrained(
    "diffusers/controlnet-canny-sdxl-1.0",
    torch_dtype=torch.float16,
    variant="fp16"
)
pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    controlnet=controlnet,
    torch_dtype=torch.float16,
    safety_checker=None,
    variant="fp16"
).to("cuda")

# Set scheduler
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)

# Load LoRA
pipe.load_lora_weights(flash_lora_id)
pipe.fuse_lora()

image = pipe(
    "picture of the mona lisa",
    image=canny_image,
    num_inference_steps=4,
    guidance_scale=0,
    controlnet_conditioning_scale=0.5,
    cross_attention_kwargs={"scale": 1},
).images[0]
make_image_grid([canny_image, image], rows=1, cols=2)
```
<p align="center">
   <img style="width:400px;" src="images/controlnet.jpg">
</p>


# Training Details
The model was trained for 20k iterations on 4 H100 GPUs (representing approximately a total of 176 GPU hours of training). Please refer to the [paper](http://arxiv.org/abs/2406.02347) for further parameters details. 

**Metrics on COCO 2014 validation (Table 3)**
  - FID-10k: 21.62 (4 NFE)
  - CLIP Score: 0.327 (4 NFE)

## Citation
If you find this work useful or use it in your research, please consider citing us

```bibtex
@misc{chadebec2024flash,
      title={Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation}, 
      author={Clement Chadebec and Onur Tasar and Eyal Benaroche and Benjamin Aubin},
      year={2024},
      eprint={2406.02347},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
```
   
## License
This model is released under the the Creative Commons BY-NC license.