metadata

tags:
  - stable-diffusion-xl
  - stable-diffusion-xl-diffusers
  - text-to-image
  - diffusers
  - lora
  - template:sd-lora
widget:
  - text: a black cat with gold and blue eyes in the style of <s0><s1>
    output:
      url: image-0.png
  - text: a man on a horse in the water at night in the style of <s0><s1>
    output:
      url: image-1.png
  - text: a man in a cloak standing in a pond with stars in the style of <s0><s1>
    output:
      url: image-2.png
  - text: >-
      a woman standing in front of a door with stars in the sky in the style of
      <s0><s1>
    output:
      url: image-3.png
  - text: the legend of zelda by joshua in the style of <s0><s1>
    output:
      url: image-4.png
  - text: >-
      a woman in a black cloak standing in the middle of a forest in the style
      of <s0><s1>
    output:
      url: image-5.png
  - text: a man standing on the rocks in the ocean at night in the style of <s0><s1>
    output:
      url: image-6.png
  - text: >-
      the legend of zelda, the legend of zelda wallpaper in the style of
      <s0><s1>
    output:
      url: image-7.png
  - text: the legend of zelda - moonlight in the style of <s0><s1>
    output:
      url: image-8.png
  - text: the legend of zelda wind waker wallpaper in the style of <s0><s1>
    output:
      url: image-9.png
  - text: a man in a forest with a sword and flowers in the style of <s0><s1>
    output:
      url: image-10.png
  - text: a person riding a horse in a field with flowers in the style of <s0><s1>
    output:
      url: image-11.png
  - text: a woman in a boat on a river in the woods in the style of <s0><s1>
    output:
      url: image-12.png
  - text: a man riding a horse in the water with stars in the style of <s0><s1>
    output:
      url: image-13.png
  - text: the witcher 3 - the starry night in the style of <s0><s1>
    output:
      url: image-14.png
  - text: the legend of zelda in the style of <s0><s1>
    output:
      url: image-15.png
  - text: the legend of zelda - twilight princess in the style of <s0><s1>
    output:
      url: image-16.png
  - text: the lord of the rings by joshua klein in the style of <s0><s1>
    output:
      url: image-17.png
  - text: the legend of zelda breath of the wild in the style of <s0><s1>
    output:
      url: image-18.png
  - text: a man on a horse is walking in the woods at night in the style of <s0><s1>
    output:
      url: image-19.png
  - text: >-
      a man in armor sitting in the middle of a field with flowers and stars in
      the style of <s0><s1>
    output:
      url: image-20.png
  - text: the legend of zelda by joshua in the style of <s0><s1>
    output:
      url: image-21.png
  - text: a woman with a sword in the middle of flowers in the style of <s0><s1>
    output:
      url: image-22.png
  - text: a woman with a sword in the middle of flowers in the style of <s0><s1>
    output:
      url: image-23.png
  - text: a woman sitting on a rock in front of a castle in the style of <s0><s1>
    output:
      url: image-24.png
  - text: a wolf and a woman standing in front of the moon in the style of <s0><s1>
    output:
      url: image-25.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: in the style of <s0><s1>
license: openrail++

SDXL LoRA DreamBooth - WalkerSpace/blue-zelda-style

Prompt
a black cat with gold and blue eyes in the style of <s0><s1>

Prompt
a man on a horse in the water at night in the style of <s0><s1>

Prompt
a man in a cloak standing in a pond with stars in the style of <s0><s1>

Prompt
a woman standing in front of a door with stars in the sky in the style of <s0><s1>

Prompt
the legend of zelda by joshua in the style of <s0><s1>

Prompt
a woman in a black cloak standing in the middle of a forest in the style of <s0><s1>

Prompt
a man standing on the rocks in the ocean at night in the style of <s0><s1>

Prompt
the legend of zelda, the legend of zelda wallpaper in the style of <s0><s1>

Prompt
the legend of zelda - moonlight in the style of <s0><s1>

Prompt
the legend of zelda wind waker wallpaper in the style of <s0><s1>

Prompt
a man in a forest with a sword and flowers in the style of <s0><s1>

Prompt
a person riding a horse in a field with flowers in the style of <s0><s1>

Prompt
a woman in a boat on a river in the woods in the style of <s0><s1>

Prompt
a man riding a horse in the water with stars in the style of <s0><s1>

Prompt
the witcher 3 - the starry night in the style of <s0><s1>

Prompt
the legend of zelda in the style of <s0><s1>

Prompt
the legend of zelda - twilight princess in the style of <s0><s1>

Prompt
the lord of the rings by joshua klein in the style of <s0><s1>

Prompt
the legend of zelda breath of the wild in the style of <s0><s1>

Prompt
a man on a horse is walking in the woods at night in the style of <s0><s1>

Prompt
a man in armor sitting in the middle of a field with flowers and stars in the style of <s0><s1>

Prompt
a woman with a sword in the middle of flowers in the style of <s0><s1>

Prompt
a woman sitting on a rock in front of a castle in the style of <s0><s1>

Prompt
a wolf and a woman standing in front of the moon in the style of <s0><s1>

Model description

These are WalkerSpace/blue-zelda-style 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 blue-zelda-style.safetensors here 💾.
- Place it on your models/Lora folder.
- On AUTOMATIC1111, load the LoRA by adding <lora:blue-zelda-style:1> to your prompt. On ComfyUI just load it as a regular LoRA.
Embeddings: download blue-zelda-style_emb.safetensors here 💾.
- Place it on it on your embeddings folder
- Use it by adding blue-zelda-style_emb to your prompt. For example, in the style of blue-zelda-style_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('WalkerSpace/blue-zelda-style', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='WalkerSpace/blue-zelda-style', filename='blue-zelda-style_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('in the style of <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.