SDXL LoRA DreamBooth - mtgentry/mason-test

Prompt

photo of sksScotty person smiling outdoors with trees in background

Prompt

photo of sksScotty person smiling in front of a window with plants outside

Prompt

photo of sksScotty person sitting at a desk with a black case in front of him

Prompt

photo of sksScotty person holding a transparent phone in one hand and a Samsung S9+ box in the other

Prompt

photo of sksScotty person indoors with shelves and tools in the background looking serious

Prompt

photo of sksScotty person holding a smartphone with the home screen visible

Prompt

photo of sksScotty person smiling and talking with another person indoors

Prompt

photo of sksScotty person smiling outdoors with trees in the background

Prompt

photo of sksScotty person standing in a factory with machines in the background

Prompt

photo of sksScotty person smiling while plugging wired earphones into a smartphone

Prompt

photo of sksScotty person holding a camera on a flexible tripod while vlogging outdoors

Prompt

photo of sksScotty person wearing red Adidas track jacket taking a mirror selfie indoors

Prompt

photo of sksScotty person smiling while using a microscope in a lab setting

Prompt

photo of sksScotty person smiling in a factory wearing a white lab coat and cap

Prompt

photo of sksScotty person smiling outdoors wearing a black cap

Prompt

photo of sksScotty person smiling indoors with shelves of tools behind him

Prompt

photo of sksScotty person smiling and holding an open iPhone showing its components

Prompt

photo of sksScotty person indoors holding an open iPhone and looking at it with amused expression

Prompt

photo of sksScotty person indoors holding a Samsung Galaxy S9+ phone and smiling

Prompt

photo of sksScotty person indoors close-up resting chin on hands with neutral expression

Model description

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