metadata

license: other
license_name: bespoke-lora-trained-license
license_link: >-
  https://multimodal.art/civitai-licenses?allowNoCredit=False&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True
tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
  - migrated
  - people
  - tool
  - slider
  - number of people
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: null
widget:
  - text: 'hipster men at a bar posing for a picture '
    parameters:
      negative_prompt: >-
        shirtless, nude, cartoon, cgi, render, illustration, painting, drawing,
        bad quality, grainy, low resolution
    output:
      url: 1670646.jpeg
  - text: 'hipster men at a bar posing for a picture '
    parameters:
      negative_prompt: >-
        shirtless,  nude, cartoon, cgi, render, illustration, painting, drawing,
        bad quality, grainy, low resolution
    output:
      url: 1670739.jpeg
  - text: 'hipster men at a bar posing for a picture '
    parameters:
      negative_prompt: >-
        shirtless,  nude, cartoon, cgi, render, illustration, painting, drawing,
        bad quality, grainy, low resolution
    output:
      url: 1670714.jpeg
  - text: 'hipster men at a bar posing for a picture '
    parameters:
      negative_prompt: >-
        shirtless,  nude, cartoon, cgi, render, illustration, painting, drawing,
        bad quality, grainy, low resolution
    output:
      url: 1670719.jpeg
  - text: 'hipster men at a bar posing for a picture '
    parameters:
      negative_prompt: >-
        shirtless,  nude, cartoon, cgi, render, illustration, painting, drawing,
        bad quality, grainy, low resolution
    output:
      url: 1670723.jpeg
  - text: ' '
    output:
      url: 1671159.jpeg

People Count Slider - LoRA

Prompt
hipster men at a bar posing for a picture

Negative Prompt
shirtless, nude, cartoon, cgi, render, illustration, painting, drawing, bad quality, grainy, low resolution

Model description

Weights can swing very far on this one -8.0 to +8.0. It can do extremely large crowds the higher you go and I wanted to be able to keep granular control.

Positive = More people

Negative = Less people

Simple LoRA to help with adjusting the number of people in a picture. You can swing it both ways pretty far out from -8 to +8 without much distortion.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

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/people-count-slider-lora', weight_name='people_count_slider_v1.safetensors')
image = pipeline('Your custom prompt').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers