SDXL LoRA DreamBooth - rexoscare/kalighat-paintings-lora

Prompt

a painting of a man sitting on a chair with a glass in the style of <s0><s1>

Prompt

an indian painting depicting a woman and man in the style of <s0><s1>

Prompt

an indian painting of a woman sitting and petting a peacock in the style of <s0><s1>

Prompt

an indian woman is taking a selfie with her husband in the style of <s0><s1>

Prompt

a painting of a woman swinging on a swing in the style of <s0><s1>

Prompt

an indian painting of a man holding a fish in the style of <s0><s1>

Prompt

an indian painting depicting a bird and a man in the style of <s0><s1>

Prompt

an indian painting depicting four women dancing in the style of <s0><s1>

Prompt

an indian painting depicting a woman pouring water into a pot in the style of <s0><s1>

Prompt

a painting depicting two women carrying bricks in the style of <s0><s1>

Prompt

an indian painting of a couple sitting on a couch in the style of <s0><s1>

Prompt

an indian painting depicting a hindu goddess Kali in the style of <s0><s1>

Prompt

a painting of two men in traditional clothing in the style of <s0><s1>

Prompt

a painting of a woman playing a sitar in the style of <s0><s1>

Prompt

a painting of a woman in a sari in the style of <s0><s1>

Prompt

an indian painting of a man sitting on a chair in the style of <s0><s1>

Prompt

an indian painting depicting a man sitting on a chariot in the style of <s0><s1>

Prompt

an indian painting of a man sitting on a chair in the style of <s0><s1>

Prompt

an indian painting depicting lord Shiva holding baby lord Ganesha in the style of <s0><s1>

Prompt

an old painting of a man sitting on a chair and a woman operating a handheld fan in the style of <s0><s1>

Prompt

an indian painting depicting lord Ganesha sitting on a tree in the style of <s0><s1>

Prompt

a painting of a woman sitting on a chair with a baby lord Ganesh in the style of <s0><s1>

Prompt

a painting of a woman carrying branches of a tree in the style of <s0><s1>

Prompt

an indian painting of a man and woman in traditional clothing where man is smoking a hookah in the style of <s0><s1>

Prompt

an indian painting depicting a woman getting her hair done in the style of <s0><s1>

Prompt

a painting of a man sitting on a chair with a book in the style of <s0><s1>

Prompt

an indian painting depicting two women in traditional clothing in the style of <s0><s1>

Prompt

a painting of a man playing a sitar in the style of <s0><s1>

Prompt

an indian painting of a man smoking a pipe in the style of <s0><s1>

Prompt

two women sitting on a yellow background with a brush in the style of <s0><s1>

Prompt

an indian painting depicting a woman sitting on a couch brushing her hair in the style of <s0><s1>

Prompt

an indian painting depicting a woman and man quarrelling in the style of <s0><s1>

Prompt

a painting of one men sitting on a chair and the other one on the floor in the style of <s0><s1>

Prompt

an indian painting of lord Ganesha sitting on a chair in the style of <s0><s1>

Model description

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