SDXL LoRA DreamBooth - GAS17/elsalvo2

Prompt
in the style of <s0><s1> a painting of a tall building with many windows

Prompt
in the style of <s0><s1> a drawing of a building with a clock tower

Prompt
in the style of <s0><s1> the liver building is shown in this photo

Prompt
in the style of <s0><s1> a painting of a large building with a clock tower

Prompt
in the style of <s0><s1> the grand hotel, a futuristic building with many windows

Prompt
in the style of <s0><s1> a large building with a clock tower on top

Prompt
in the style of <s0><s1> a large building with many windows and a clock tower

Prompt
in the style of <s0><s1> a large building with a clock tower in the sky

Prompt
in the style of <s0><s1> the building is made of stone and has many windows

Prompt
in the style of <s0><s1> a large building with a purple sky

Model description

These are GAS17/elsalvo2 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 elsalvo2.safetensors here 💾.
- Place it on your models/Lora folder.
- On AUTOMATIC1111, load the LoRA by adding <lora:elsalvo2:1> to your prompt. On ComfyUI just load it as a regular LoRA.
Embeddings: download elsalvo2_emb.safetensors here 💾.
- Place it on it on your embeddings folder
- Use it by adding elsalvo2_emb to your prompt. For example, A photo of elsalvo2_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('GAS17/elsalvo2', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='GAS17/elsalvo2', filename='elsalvo2_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.

GAS17
/

elsalvo2