SDXL LoRA DreamBooth - alex-SDXL-LoRA
Model description
These are alex-SDXL-LoRA LoRA adaption weights for SG161222/RealVisXL_V4.0.
Download model
Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
- LoRA: download
alex-SDXL-LoRA.safetensors
here 💾.- Place it on your
models/Lora
folder. - On AUTOMATIC1111, load the LoRA by adding
<lora:alex-SDXL-LoRA:1>
to your prompt. On ComfyUI just load it as a regular LoRA.
- Place it on your
- Embeddings: download
alex-SDXL-LoRA_emb.safetensors
here 💾.- Place it on it on your
embeddings
folder - Use it by adding
alex-SDXL-LoRA_emb
to your prompt. For example,a photo of a alex-SDXL-LoRA_emb man
(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('alex-SDXL-LoRA', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='alex-SDXL-LoRA', filename='alex-SDXL-LoRA_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 a <s0><s1> man').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
- 14
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for max-fofanov/alex-SDXL-LoRA
Base model
SG161222/RealVisXL_V4.0
Adapter
this model