SDXL LoRA DreamBooth - haroonalhadisk/haroonalhadi-test2

Prompt

A photo of <s0><s1> haroonalhadi a man in a blue shirt and black tie

Prompt

A photo of <s0><s1> haroonalhadi a man sitting on some steps in front of a colorful building

Prompt

A photo of <s0><s1> haroonalhadi a man standing in front of a pagoda

Prompt

A photo of <s0><s1> haroonalhadi a man in a grey shirt and jeans standing in a room

Prompt

A photo of <s0><s1> haroonalhadi a man laying on a couch

Prompt

A photo of <s0><s1> haroonalhadi a man with a moustache and a blue shirt

Prompt

A photo of <s0><s1> haroonalhadi a man with long hair and beard in a bathroom

Prompt

A photo of <s0><s1> haroonalhadi a man with long hair and a beard sitting in a chair

Prompt

A photo of <s0><s1> haroonalhadi a man with a beard and a long hair is sitting in a chair

Prompt

A photo of <s0><s1> haroonalhadi a man with a beard and tank top is taking a selfie

Prompt

A photo of <s0><s1> haroonalhadi a man sitting on a couch with a remote control

Prompt

A photo of <s0><s1> haroonalhadi a man with a beard and a black shirt taking a selfie

Prompt

A photo of <s0><s1> haroonalhadi a man in a pink sherwani leaning against a wall

Prompt

A photo of <s0><s1> haroonalhadi a man in a pink sherwani leaning against a wall

Model description

These are haroonalhadisk/haroonalhadi-test2 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 haroonalhadi-test2.safetensors here 💾.
  • Place it on your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:haroonalhadi-test2:1> to your prompt. On ComfyUI just load it as a regular LoRA.
• Embeddings: download haroonalhadi-test2_emb.safetensors here 💾.
  • Place it on it on your embeddings folder
  • Use it by adding haroonalhadi-test2_emb to your prompt. For example, A photo of haroonalhadi-test2_emb haroonalhadi (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('haroonalhadisk/haroonalhadi-test2', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='haroonalhadisk/haroonalhadi-test2', filename='haroonalhadi-test2_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> haroonalhadi').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.