SDXL LoRA DreamBooth - sessex/mm-tabi-boot-product

- Prompt
- a photo of purple <s0><s1>

- Prompt
- a photo of brown <s0><s1>

- Prompt
- a photo of tan <s0><s1>

- Prompt
- a photo of metallic <s0><s1>

- Prompt
- a photo of tan <s0><s1>

- Prompt
- a photo of grey <s0><s1>

- Prompt
- a photo of white <s0><s1>

- Prompt
- a photo of brown <s0><s1>

- Prompt
- a photo of black <s0><s1>

- Prompt
- a photo of white <s0><s1>

- Prompt
- a photo of brown <s0><s1>

- Prompt
- a photo of black <s0><s1>

- Prompt
- a photo of light blue <s0><s1>

- Prompt
- a photo of grey <s0><s1>

- Prompt
- a photo of tan <s0><s1>

- Prompt
- a photo of black <s0><s1>

- Prompt
- a photo of white <s0><s1>

- Prompt
- a photo of tan <s0><s1>

- Prompt
- a photo of grey <s0><s1>

- Prompt
- a photo of black <s0><s1>

- Prompt
- a photo of metallic <s0><s1>

- Prompt
- a photo of black <s0><s1>

- Prompt
- a photo of black <s0><s1>

- Prompt
- a photo of black <s0><s1>

- Prompt
- a photo of gold cowboy <s0><s1>

- Prompt
- a photo of tall tan <s0><s1>

- Prompt
- a photo of tall white <s0><s1>

- Prompt
- a photo of tall burgundy <s0><s1>

- Prompt
- a photo of tall black <s0><s1>

- Prompt
- a photo of tall black <s0><s1>

- Prompt
- a photo of tall white patterned <s0><s1>

- Prompt
- a photo of burgundy <s0><s1>

- Prompt
- a photo of black <s0><s1>

- Prompt
- a photo of burgundy <s0><s1>
Model description
These are sessex/mm-tabi-boot-product 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
mm-tabi-boot-product.safetensors
here 💾.- Place it on your
models/Lora
folder. - On AUTOMATIC1111, load the LoRA by adding
<lora:mm-tabi-boot-product:1>
to your prompt. On ComfyUI just load it as a regular LoRA.
- Place it on your
- Embeddings: download
mm-tabi-boot-product_emb.safetensors
here 💾.- Place it on it on your
embeddings
folder - Use it by adding
mm-tabi-boot-product_emb
to your prompt. For example,a photo of mm-tabi-boot-product_emb
(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('sessex/mm-tabi-boot-product', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='sessex/mm-tabi-boot-product', filename='mm-tabi-boot-product_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 photo 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.
- Downloads last month
- 7
Model tree for sessex/mm-tabi-boot-product
Base model
stabilityai/stable-diffusion-xl-base-1.0