SDXL LoRA DreamBooth - GoHugo/hugo

Prompt

A photo of <s0><s1> a man with long hair and a black t - shirt

Prompt

A photo of <s0><s1> a man in a grey shirt posing for a photo

Prompt

A photo of <s0><s1> a man in a blue shirt smiling

Prompt

A photo of <s0><s1> a drawing of a young man with brown hair

Prompt

A photo of <s0><s1> a man with a piercing on his nose

Prompt

A photo of <s0><s1> a man with blue eyes and a green hoodie

Prompt

A photo of <s0><s1> a man with curly hair and blue eyes

Prompt

A photo of <s0><s1> a man with curly hair and a white tank top

Prompt

A photo of <s0><s1> a drawing of a young man with brown hair

Prompt

A photo of <s0><s1> a man with dark hair and a black jacket

Prompt

A photo of <s0><s1> a man with a black hoodie and a black jacket

Prompt

A photo of <s0><s1> a man with short hair and a blue shirt

Prompt

A photo of <s0><s1> a man with short hair and a green jacket

Prompt

A photo of <s0><s1> a man with a green hair and a green arrow on his head

Prompt

A photo of <s0><s1> a man with a black shirt and blue eyes

Prompt

A photo of <s0><s1> a man with long hair and a green shirt

Prompt

A photo of <s0><s1> a man with blue eyes is looking at the camera

Model description

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