---
license: other
license_name: bespoke-lora-trained-license
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- depth of field
- tool
- dof
- blurry background
- focus

base_model: runwayml/stable-diffusion-v1-5
instance_prompt: 
widget:
- text: ' '
  
  output:
    url: >-
      2221968.jpeg
- text: ' '
  
  output:
    url: >-
      2221993.jpeg
- text: 'photo of a man  smiling  in the forest, beard '
  parameters:
    negative_prompt: cartoon, cgi, render, illustration, painting, drawing, bad quality, grainy, low resolution
            
  output:
    url: >-
      2222002.jpeg
- text: 'photo of a man  smiling  in the forest, beard '
  parameters:
    negative_prompt: cartoon, cgi, render, illustration, painting, drawing, bad quality, grainy, low resolution
            
  output:
    url: >-
      2222004.jpeg
- text: 'photo of a woman with light brown hair, posing for a photo, centered streets of big city '
  parameters:
    negative_prompt: hat, nude, cartoon, cgi, render, illustration, painting, drawing, bad quality, grainy, low resolution
            
  output:
    url: >-
      2222006.jpeg
- text: 'photo of a woman with light brown hair, posing for a photo, centered streets of big city '
  parameters:
    negative_prompt: hat, nude, cartoon, cgi, render, illustration, painting, drawing, bad quality, grainy, low resolution
            
  output:
    url: >-
      2222008.jpeg

---

# Depth of Field Slider - LoRA 

<Gallery />





## Model description

<ul><li><p>weight: <strong>-8.0 to 8.0 </strong><em>( or way more or less )</em></p></li><li><p>positive: <strong>large DOF (sharp background)</strong></p></li><li><p>negative: <strong>narrow DOF (blurry background)</strong></p></li></ul><p></p><p>UPDATE:</p><p>The original file had an sdxl meta tag that makes automatic1111 web ui only show it for sdxl. I have uploaded one with the correct meta tag. If you are having issues, download and replace the previous one with the new one and refresh your network modules.</p><p></p><p>Weight depends on starting photo, if it already has a shallow depth of field, you may need to go pretty high to remove it (10.0 to 15.0), but -5.0 to 5.0 works for most images. The image stays pretty stable even at extreme values, though it will change the composition.</p><p></p>



## Download model

Weights for this model are available in Safetensors format.

[Download](/ostris/depth-of-field-slider-lora/tree/main) them in the Files & versions tab.

## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('ostris/depth-of-field-slider-lora', weight_name='depth_of_field_slider_v1.safetensors')
image = pipeline('photo of a woman with light brown hair, posing for a photo, centered streets of big city ').images[0]
```

For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)