import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stablediffusionapi/albedobase-xl", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("robindon/lora-trained-xl-TOK-person")
prompt = "A photo of TOK person in dress"
image = pipe(prompt).images[0]SDXL LoRA DreamBooth - robindon/lora-trained-xl-TOK-person
- Prompt
- A photo of TOK person in dress
- Prompt
- A photo of TOK person in dress
- Prompt
- A photo of TOK person in dress
- Prompt
- A photo of TOK person in dress
Model description
These are robindon/lora-trained-xl-TOK-person LoRA adaption weights for stablediffusionapi/albedobase-xl.
The weights were trained using DreamBooth.
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
Trigger words
You should use a photo of TOK person to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 11
Model tree for robindon/lora-trained-xl-TOK-person
Base model
stablediffusionapi/albedobase-xl