javeriahassan/socialmedia-std-xl-base-1-0-3000-1000

SDXL LoRA DreamBooth - javeriahassan/socialmedia-std-xl-base-1-0-3000-1000

<Gallery />

Model description

These are javeriahassan/socialmedia-std-xl-base-1-0-3000-1000 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 [`socialmedia-std-xl-base-1-0-3000-1000.safetensors` here 💾](/javeriahassan/socialmedia-std-xl-base-1-0-3000-1000/blob/main/socialmedia-std-xl-base-1-0-3000-1000.safetensors).
• —Place it on your models/Lora folder.
• —On AUTOMATIC1111, load the LoRA by adding <lora:socialmedia-std-xl-base-1-0-3000-1000:1> to your prompt. On ComfyUI just load it as a regular LoRA.
• —Embeddings: download [`socialmedia-std-xl-base-1-0-3000-1000_emb.safetensors` here 💾](/javeriahassan/socialmedia-std-xl-base-1-0-3000-1000/blob/main/socialmedia-std-xl-base-1-0-3000-1000_emb.safetensors).
• —Place it on it on your embeddings folder
• —Use it by adding socialmedia-std-xl-base-1-0-3000-1000_emb to your prompt. For example, Create a promotional image with The design layout consists of a vibrant image occupying the upper half, displaying a person engaged in gardening, surrounded by lush greenery. Below this, the text section follows, aligned center-left. The title GARDENING SERVICES uses a bold sans-serif font in green, drawing immediate attention. Below the title is a description in smaller black sans-serif font, which provides additional information about the services offered, maintaining clarity and readability. To the right, a circular badge in dark green contains the promotion details, UP TO 20% OFF, using contrasting white text for emphasis. This badge adds a focal point to the design. At the bottom left, a green button with the text BOOK NOW invites action, utilizing a rounded rectangular shape. Adjacent to it, website information is laid out with an icon, both in green, ensuring consistent branding. The overall alignment is balanced, providing an appealing mix of imagery and information. (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('javeriahassan/socialmedia-std-xl-base-1-0-3000-1000', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='javeriahassan/socialmedia-std-xl-base-1-0-3000-1000', filename='socialmedia-std-xl-base-1-0-3000-1000_emb.safetensors', repo_type="model")
state_dict = load_file(embedding_path)
pipeline.load_textual_inversion(state_dict["clip_l"], token=[], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
pipeline.load_textual_inversion(state_dict["clip_g"], token=[], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
        
image = pipeline('Create a promotional image for a SHOE SALE with bold black text near the bottom on a white and gray background. Include a red 50% OFF badge, a SHOP NOW button, sneakers, socks, and shoeboxes overlaying a gray diagonal strip. The design should have red cursive text and a liceria & co. logo in the top-left corner.').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.