SDXL LoRA DreamBooth - domipapp/domiai2-0

Prompt
An image of a 28 year old man <s0><s1>

Prompt
An image of a 28 year old man with a goofy face expression <s0><s1>

Prompt
An image of a 28 year old man with a sad face expression <s0><s1>

Prompt
An sitting portrait image of a 28 year old man <s0><s1>

Prompt
An image of a 28 year old man with a smile <s0><s1>

Prompt
An image of a 28 year old man with a serious face expression <s0><s1>

Prompt
An image of a 28 year old man with a happy face expression holding a cat <s0><s1>

Prompt
An image of a 28 year old man with an angry face expression <s0><s1>

Prompt
An image of a 28 year old man in the mountains <s0><s1>

Prompt
An image of a 28 year old man outdoors <s0><s1>

Prompt
A close-up image of a 28 year old man with a serious face expression <s0><s1>

Prompt
A close-up image of a 28 year old man with a goofy face expression <s0><s1>

Model description

These are domipapp/domiai2-0 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 domiai2-0.safetensors here 💾.
- Place it on your models/Lora folder.
- On AUTOMATIC1111, load the LoRA by adding <lora:domiai2-0:1> to your prompt. On ComfyUI just load it as a regular LoRA.
Embeddings: download domiai2-0_emb.safetensors here 💾.
- Place it on it on your embeddings folder
- Use it by adding domiai2-0_emb to your prompt. For example, Eddie Redmayne man domiai2-0_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('domipapp/domiai2-0', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='domipapp/domiai2-0', filename='domiai2-0_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('Eddie Redmayne man <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.

domipapp
/

domiai2-0