SDXL LoRA DreamBooth - mtgentry/saraportrait

Prompt

A photo of <s0><s1> a woman and a little girl smiling for the camera

Prompt

A photo of <s0><s1> a woman holding a plate of food

Prompt

A photo of <s0><s1> a woman in a black dress standing in a living room

Prompt

A photo of <s0><s1> a woman sitting at a table with a dog

Prompt

A photo of <s0><s1> a woman in a dress and black cardigan standing on a sidewalk

Prompt

A photo of <s0><s1> a woman and two children riding a tricycle

Prompt

A photo of <s0><s1> a woman holding a baby in her arms

Prompt

A photo of <s0><s1> a woman and a child sitting at a table

Prompt

A photo of <s0><s1> two people playing chess in a library

Prompt

A photo of <s0><s1> a woman reading to her baby while sitting on a couch

Prompt

A photo of <s0><s1> a woman is smiling while holding a ghost costume

Prompt

A photo of <s0><s1> a woman holding a purple stuffed animal in a field

Prompt

A photo of <s0><s1> a woman holding a child in her arms while sitting on a couch

Prompt

A photo of <s0><s1> a woman and child sitting on the floor in front of a christmas tree

Prompt

A photo of <s0><s1> a woman taking a selfie in front of a mirror

Prompt

A photo of <s0><s1> a woman and a little girl smiling for the camera

Prompt

A photo of <s0><s1> a woman and a child are smiling

Prompt

A photo of <s0><s1> a woman and two children are sitting at a table with a paper star

Prompt

A photo of <s0><s1> a woman and a little girl are sitting on the ground

Prompt

A photo of <s0><s1> a woman laying on a couch with a dog

Prompt

A photo of <s0><s1> a woman and a child are smiling for the camera

Prompt

A photo of <s0><s1> a woman and a child standing on a sidewalk

Prompt

A photo of <s0><s1> a woman and a little girl are smiling for the camera

Prompt

A photo of <s0><s1> a woman sitting on a bench

Prompt

A photo of <s0><s1> a woman standing next to a black car

Prompt

A photo of <s0><s1> a woman cutting a cake with a knife

Prompt

A photo of <s0><s1> a woman and a little girl taking a selfie

Prompt

A photo of <s0><s1> a woman and a baby sit on the floor with books

Prompt

A photo of <s0><s1> a woman holding a child

Model description

These are mtgentry/saraportrait LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.

Download model

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

• LoRA: download saraportrait.safetensors here 💾.
  • Place it on your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:saraportrait:1> to your prompt. On ComfyUI just load it as a regular LoRA.
• Embeddings: download saraportrait_emb.safetensors here 💾.
  • Place it on it on your embeddings folder
  • Use it by adding saraportrait_emb to your prompt. For example, A photo of saraportrait_emb (you need both the LoRA and the embeddings as they were trained together for this LoRA)

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
        
pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('mtgentry/saraportrait', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='mtgentry/saraportrait', filename='saraportrait_emb.safetensors' repo_type="model")
state_dict = load_file(embedding_path)
pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
        
image = pipeline('A photo of <s0><s1>').images[0]

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

Trigger words

To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:

to trigger concept TOK → use <s0><s1> in your prompt

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: True.

Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.