metadata

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
  - sad
  - happy
  - emotions
  - tool
  - slider
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: null
widget:
  - text: >-
      close up photo of a woman with dirty blonde hair, soft box photography in
      a dark room, straight hair, centered in frame
    parameters:
      negative_prompt: >-
        cartoon, cgi, render, illustration, painting, drawing, bad quality,
        grainy, low resolution
    output:
      url: 1800239.jpeg

Emotion Sliders

Prompt
close up photo of a woman with dirty blonde hair, soft box photography in a dark room, straight hair, centered in frame

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

Model description

I am going to add various emotion sliders here so they will all be in one place. In general, the weights will be -5 to 5, but each one may be more or less. Check versions at the top. Each one will be labeled with the emotion it affects.

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/emotion-sliders', weight_name='emotion_happy_slider_v1.safetensors')
image = pipeline('close up photo of a woman with dirty blonde hair, soft box photography in a dark room, straight hair, centered in frame').images[0]

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