SDXL LoRA DreamBooth - multimodalart/mouse-public-domain-rank16

Prompt

A <s0><s1> mouse cartoon piloting a boat

Prompt

A <s0><s1> mouse cartoon piloting a boat

Prompt

A <s0><s1> mouse cartoon pulling the boat's horn

Prompt

A <s0><s1> mouse cartoon zoom out piloting a boat

Prompt

A <s0><s1> mouse cartoon mad at a bucket

Prompt

A <s0><s1> mouse cartoon opening a dog's mouth

Prompt

A <s0><s1> mouse cartoon dancing in the kitchen

Prompt

A <s0><s1> mouse cartoon looking at a cow

Prompt

A <s0><s1> mouse cartoon plahying musical instruments

Prompt

A <s0><s1> mouse cartoon sitting down

Model description

These are multimodalart/mouse-public-domain-rank16 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 mouse-public-domain-rank16.safetensors here 💾.
  • Place it on your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:mouse-public-domain-rank16:1> to your prompt. On ComfyUI just load it as a regular LoRA.
• Embeddings: download mouse-public-domain-rank16_emb.safetensors here 💾.
  • Place it on it on your embeddings folder
  • Use it by adding mouse-public-domain-rank16_emb to your prompt. For example, A mouse-public-domain-rank16_emb mouse cartoon (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('multimodalart/mouse-public-domain-rank16', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='multimodalart/mouse-public-domain-rank16', filename='mouse-public-domain-rank16_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> mouse cartoon ').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.