FirstLast/RealisticVision-LoRA-libr-0.15

SD1.5 LoRA DreamBooth - FirstLast/RealisticVision-LoRA-libr-0.2

Prompt

a portrait of a woman wearing libr dress, bokeh, cinematic

Prompt

a portrait of a woman wearing libr dress, bokeh, cinematic

Prompt

a portrait of a woman wearing libr dress, bokeh, cinematic

Prompt

a portrait of a woman wearing libr dress, bokeh, cinematic

Model description

These are FirstLast/RealisticVision-LoRA-libr-0.2 LoRA adaption weights for SG161222/Realistic_Vision_V5.1_noVAE.

Download model

Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke

• LoRA: download RealisticVision-LoRA-libr-0.2.safetensors here 💾.
  • Place it on your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:RealisticVision-LoRA-libr-0.2:1> to your prompt. On ComfyUI just load it as a regular LoRA.

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('FirstLast/RealisticVision-LoRA-libr-0.2', weight_name='pytorch_lora_weights.safetensors')

image = pipeline('a portrait of a woman wearing libr dress, bokeh, cinematic').images[0]

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

Trigger words

You should use a libr dress to trigger the image generation.

Details

All Files & versions.

The weights were trained using 🧨 diffusers Advanced Dreambooth Training Script.

LoRA for the text encoder was enabled. False.

Pivotal tuning was enabled: False.

Special VAE used for training: None.