SDXL LoRA DreamBooth - joelbryan/petmalu-babalu

Prompt

In the style of <s0><s1> babalu wearing a hat and suspenders

Prompt

In the style of <s0><s1> babalu in plaid shirt sitting in front of a window

Prompt

In the style of <s0><s1> babalu in an orange shirt is standing next to a tree

Prompt

In the style of <s0><s1> babalu in a red shirt is standing in front of a tree

Prompt

In the style of <s0><s1> babalu in a colorful shirt

Prompt

In the style of <s0><s1> babalu standing next to another in front of a clock

Prompt

In the style of <s0><s1> babalu and person in the movie person

Prompt

In the style of <s0><s1> babalu sitting next to another in front of a wooden wall

Prompt

In the style of <s0><s1> babalu in a green shirt is sitting at a table

Prompt

In the style of <s0><s1> babalu in a white t - shirt talking on a cell phone

Prompt

In the style of <s0><s1> babalu in a red hat and a colorful shirt

Prompt

In the style of <s0><s1> babalu wearing a hat and a red shirt

Prompt

In the style of <s0><s1> babalu wearing a hat and smiling

Prompt

In the style of <s0><s1> babalu in a hat

Prompt

In the style of <s0><s1> babalu with a yellow shirt is making a face

Prompt

In the style of <s0><s1> babalu in plaid shirt with his mouth open

Prompt

In the style of <s0><s1> babalu with his mouth open and his tongue sticking out

Model description

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