metadata

tags:
  - stable-diffusion-xl
  - stable-diffusion-xl-diffusers
  - diffusers-training
  - text-to-image
  - diffusers
  - lora
  - template:sd-lora
widget:
  - text: a <s0><s1> pack of pop tarts in pizza flavor
    output:
      url: image_0.png
  - text: a <s0><s1> pack of pop tarts in pizza flavor
    output:
      url: image_1.png
  - text: a <s0><s1> pack of pop tarts in pizza flavor
    output:
      url: image_2.png
  - text: a <s0><s1> pack of pop tarts in pizza flavor
    output:
      url: image_3.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: a <s0><s1> pack of pop tarts
license: openrail++

SDXL LoRA DreamBooth - linoyts/pop_tart_clip_skip

Prompt
a <s0><s1> pack of pop tarts in pizza flavor

Model description

These are linoyts/pop_tart_clip_skip 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 pop_tart_clip_skip.safetensors here 💾.
- Place it on your models/Lora folder.
- On AUTOMATIC1111, load the LoRA by adding <lora:pop_tart_clip_skip:1> to your prompt. On ComfyUI just load it as a regular LoRA.
Embeddings: download pop_tart_clip_skip_emb.safetensors here 💾.
- Place it on it on your embeddings folder
- Use it by adding pop_tart_clip_skip_emb to your prompt. For example, a pop_tart_clip_skip_emb pack of pop tarts (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('linoyts/pop_tart_clip_skip', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='linoyts/pop_tart_clip_skip', filename='pop_tart_clip_skip_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> pack of pop tarts in pizza flavor').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.