SDXL LoRA DreamBooth - Norod78/sdxl-humeow-lora-r16

- Prompt
- <s0><s1> HuMeow with blue eyes and orange ears

- Prompt
- <s0><s1> HuMeow dressed in a jacket and boots

- Prompt
- <s0><s1> HuMeow wearing a jacket and headphones

- Prompt
- <s0><s1> HuMeow dressed in a jacket and jeans

- Prompt
- <s0><s1> HuMeow dressed as a clown standing in front of a black background

- Prompt
- <s0><s1> HuMeow dressed as a clown

- Prompt
- <s0><s1> HuMeow in a hard hat and overalls

- Prompt
- <s0><s1> HuMeow in a yellow suit and yellow boots

- Prompt
- <s0><s1> HuMeow black statue sitting on a table

- Prompt
- <s0><s1> HuMeow dressed in a tuxedo

- Prompt
- <s0><s1> HuMeow wearing an orange jacket

- Prompt
- <s0><s1> HuMeow in a suit and backpack

- Prompt
- <s0><s1> HuMeow wearing a jacket and sunglasses

- Prompt
- <s0><s1> HuMeow wearing sunglasses and a pink shirt

- Prompt
- <s0><s1> HuMeow wearing pink clothes and a white shirt

- Prompt
- <s0><s1> HuMeow wearing a pink jacket and sneakers

- Prompt
- <s0><s1> HuMeow wearing a pink suit and sunglasses

- Prompt
- <s0><s1> HuMeow three witches in costumes walking through the woods

- Prompt
- <s0><s1> HuMeow three witches and a fox in the woods

- Prompt
- <s0><s1> HuMeow a group dressed up in fancy clothes

- Prompt
- <s0><s1> HuMeow a group dressed up in fancy clothes

- Prompt
- <s0><s1> HuMeow with red hair and freckles

- Prompt
- <s0><s1> HuMeow painting in a pink dress

- Prompt
- <s0><s1> HuMeow with a headdress and a necklace

- Prompt
- <s0><s1> HuMeow with a collar and a woman looking at it

- Prompt
- <s0><s1> HuMeow with a lace dress and a bow tie

- Prompt
- <s0><s1> HuMeow with a white head and hair

- Prompt
- <s0><s1> HuMeow with blue eyes and a long tail

- Prompt
- <s0><s1> HuMeow dressed in armor with red hair

- Prompt
- <s0><s1> HuMeow dressed in a suit and tie

- Prompt
- <s0><s1> HuMeow digital painting with big eyes

- Prompt
- <s0><s1> HuMeow portrait

- Prompt
- <s0><s1> HuMeow with long hair and a suit

- Prompt
- <s0><s1> HuMeow the walking dead season 10 episode 10
Model description
These are Norod78/sdxl-humeow-lora-r16 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
sdxl-humeow-lora-r16.safetensors
here 💾.- Place it on your
models/Lora
folder. - On AUTOMATIC1111, load the LoRA by adding
<lora:sdxl-humeow-lora-r16:1>
to your prompt. On ComfyUI just load it as a regular LoRA.
- Place it on your
- Embeddings: download
sdxl-humeow-lora-r16_emb.safetensors
here 💾.- Place it on it on your
embeddings
folder - Use it by adding
sdxl-humeow-lora-r16_emb
to your prompt. For example,sdxl-humeow-lora-r16_emb HuMeow
(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('Norod78/sdxl-humeow-lora-r16', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='Norod78/sdxl-humeow-lora-r16', filename='sdxl-humeow-lora-r16_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('<s0><s1> HuMeow').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.
- Downloads last month
- 90
Model tree for Norod78/sdxl-humeow-lora-r16
Base model
stabilityai/stable-diffusion-xl-base-1.0