metadata
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
widget:
- text: A <s0><s1> character
output:
url: image-0.png
- text: A <s0><s1> character
output:
url: image-1.png
- text: A <s0><s1> character
output:
url: image-2.png
- text: A <s0><s1> character
output:
url: image-3.png
- text: A <s0><s1> character
output:
url: image-4.png
- text: A <s0><s1> character
output:
url: image-5.png
- text: A <s0><s1> character
output:
url: image-6.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: A <s0><s1> character
license: openrail++
SDXL LoRA DreamBooth - multimodalart/public-domain-mouse-character
Model description
These are multimodalart/public-domain-mouse-character 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
public-domain-mouse-character.safetensors
here 💾.- Place it on your
models/Lora
folder. - On AUTOMATIC1111, load the LoRA by adding
<lora:public-domain-mouse-character:1>
to your prompt. On ComfyUI just load it as a regular LoRA.
- Place it on your
- Embeddings: download
public-domain-mouse-character_emb.safetensors
here 💾.- Place it on it on your
embeddings
folder - Use it by adding
public-domain-mouse-character_emb
to your prompt. For example,A public-domain-mouse-character_emb character
(you need both the LoRA and the embeddings as they were trained together for this LoRA)
- Place it on it on your
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('multimodalart/public-domain-mouse-character', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='multimodalart/public-domain-mouse-character', filename='public-domain-mouse-character_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 <s0><s1> character').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.