---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: a boy in Halloween costumes, Linear red light
  parameters:
    negative_prompt: (lowres, low quality, worst quality)
  output:
    url: images/6e4fc324ef43cc11435f1e0419cbd5b13e38c9f8f9289578ffa75282.jpg
- text: a cat, Linear red light
  parameters:
    negative_prompt: (lowres, low quality, worst quality)
  output:
    url: images/2a3e77a3bf8abf4e15a9d02f05afc6064b9874ace8d58eb8928d3fd9.jpg
- text: Halloween Lanterns on the table, Linear red light
  parameters:
    negative_prompt: (lowres, low quality, worst quality)
  output:
    url: images/201dd797dcadcb680d2ea4004910a6430efaf7620268a57584fb77d1.jpg
- text: Eiffel Tower, Linear red light
  parameters:
    negative_prompt: (lowres, low quality, worst quality)
  output:
    url: images/fed3ec00baa80515fa20e37d373b82bcbebdb11e2270217f24b25ea1.jpg
- text: a Witch, Linear red light
  parameters:
    negative_prompt: (lowres, low quality, worst quality)
  output:
    url: images/c717a319c28471f0973c3d5d2e4c881e79d1bd9260691a07fee4eda8.jpg
- text: a vampire, moon, Linear red light
  parameters:
    negative_prompt: (lowres, low quality, worst quality)
  output:
    url: images/7b9a2e73e1dae5f3224dd4224e4aa984f29a60133ba80a238dfe3966.jpg
base_model: stabilityai/stable-diffusion-3.5-large
instance_prompt: Linear red light
license: other
license_name: stabilityai-ai-community
license_link: >-
  https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/LICENSE.md
---
# SD3.5-LoRA-Linear-Red-Light

<Gallery />


## Trigger words

You should use `Linear red light` to trigger the image generation.


## Inference

```python
import torch
from diffusers import StableDiffusion3Pipeline # please install diffusers from the source

pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3.5-large-diffusers", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("Shakker-Labs/SD3.5-LoRA-Linear-Red-Light", weight_name="SD35-lora-Linear-Red-Light.safetensors")
pipe.fuse_lora(lora_scale=1.0)
pipe.to("cuda")

prompt = "a cat, Linear red light"
negative_prompt = "(lowres, low quality, worst quality)"

image = pipe(prompt=prompt,
             negative_prompt=negative_prompt
             num_inference_steps=24, 
             guidance_scale=4.0,
             width=960, height=1280,
            ).images[0]
image.save(f"toy_example.jpg")
```