SDXL LoRA DreamBooth - chechiamah/dithering-samples

Prompt
a black and white image of a man with a hat in the style of <s0><s1>

Prompt
a colorful spiral pattern is shown in this image in the style of <s0><s1>

Prompt
a painting of a tree with blue and green leaves in the style of <s0><s1>

Prompt
the great wave off kanagawa by person in the style of <s0><s1>

Prompt
a pixel art drawing of a man in a hat in the style of <s0><s1>

Prompt
a man with glasses and a black shirt in the style of <s0><s1>

Prompt
a desert landscape with a blue sky and sand dunes in the style of <s0><s1>

Prompt
halftone dot pattern background vector in the style of <s0><s1>

Prompt
a set of four black and white abstract patterns in the style of <s0><s1>

Model description

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

chechiamah
/

dithering-samples