SDXL LoRA DreamBooth - dream2589632147/cathrin

Prompt

blurry, low quality, overexposed, underexposed, harsh shadows, deformed face, asymmetrical eyes, bad anatomy, extra fingers, extra limbs, cross eye, oversharpened, plastic skin, heavy makeup, old woman, child, asian, african, cartoon, anime, cgi

Prompt

ultra realistic RAW photo of a 22yo european woman, soft facial features, natural blonde hair, light blue eyes, smooth fair skin, subtle makeup, symmetrical face, small straight nose, soft pink lips, delicate jawline, studio portrait, 85mm lens, shallow depth of field, natural skin texture, high detail, professional photography 22yo european blonde woman, soft facial features, studio portrait, softbox lighting, white background, elegant black dress, 85mm lens

Prompt

22yo european blonde woman, beauty portrait, grey background, soft cinematic lighting, natural expression

Prompt

22yo european blonde woman, close up portrait, high key lighting, minimal makeup

Prompt

22yo european blonde woman, half body studio shot, beige background, soft warm lighting

Prompt

22yo european blonde woman, outdoor portrait, natural sunlight, park background, casual white shirt

Prompt

22yo european blonde woman, soft cloudy daylight, close up, natural expression

Prompt

22yo european blonde woman, outdoor candid shot, smiling, shallow depth of field

Prompt

22yo european blonde woman, reading book, warm indoor light

Prompt

22yo european blonde woman, coffee shop background, casual outfit

Prompt

22yo european blonde woman, bedroom soft morning light portrait

Prompt

22yo european blonde woman, side profile portrait, natural lighting

Prompt

22yo european blonde woman, looking over shoulder, soft light

Prompt

22yo european blonde woman, slight top angle shot

Prompt

22yo european blonde woman, slight low angle portrait

Prompt

22yo european blonde woman, close up face crop, ultra detailed skin

Prompt

22yo european blonde woman, neutral expression, cinematic light

Prompt

22yo european blonde woman, subtle serious expression

Prompt

22yo european blonde woman, thoughtful expression, window light

Prompt

22yo european blonde woman, casual jeans and t-shirt, daylight portrait

Prompt

22yo european blonde woman, winter coat portrait, soft cloudy light

Prompt

22yo european blonde woman, minimalist fashion portrait, clean background

Model description

These are dream2589632147/cathrin 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 cathrin.safetensors here 💾.
  • Place it on your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:cathrin:1> to your prompt. On ComfyUI just load it as a regular LoRA.
• Embeddings: download cathrin_emb.safetensors here 💾.
  • Place it on it on your embeddings folder
  • Use it by adding cathrin_emb to your prompt. For example, A cathrin_emb character (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('dream2589632147/cathrin', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='dream2589632147/cathrin', filename='cathrin_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 <s0><s1> character').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.