SDXL LoRA DreamBooth - timelord7000/jan-comic3000

Prompt

a comic strip with a girl in a pink hat and a purple bag in the style of <s0><s1>

Prompt

a comic strip with a cartoon character and text in the style of <s0><s1>

Prompt

the game cover for bryna and the minic knight in the style of <s0><s1>

Prompt

a cartoon comic with a girl wearing a hat with horns in the style of <s0><s1>

Prompt

a comic strip with a woman in a purple hat and a purple dragon in the style of <s0><s1>

Model description

These are timelord7000/jan-comic3000 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 jan-comic3000.safetensors here 💾.
  • Place it on your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:jan-comic3000:1> to your prompt. On ComfyUI just load it as a regular LoRA.
• Embeddings: download jan-comic3000_emb.safetensors here 💾.
  • Place it on it on your embeddings folder
  • Use it by adding jan-comic3000_emb to your prompt. For example, in the style of jan-comic3000_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('timelord7000/jan-comic3000', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='timelord7000/jan-comic3000', filename='jan-comic3000_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.