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

Prompt

Design a promotional poster for AI chatbot integration services. The image should feature the text WARNER & SPENCER with a chatbot icon. Include bold text for AI CHATBOT and Integration Services, service details with checkmarks, and a Contact Us button on the left. A friendly chatbot graphic should be placed on the right side.

Model description

These are javeriahassan/socialmedia-std-xl-base-1-0 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.safetensors here 💾.
  • Place it on your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:socialmedia-std-xl-base-1-0:1> to your prompt. On ComfyUI just load it as a regular LoRA.
• Embeddings: download socialmedia-std-xl-base-1-0_emb.safetensors here 💾.
  • Place it on it on your embeddings folder
  • Use it by adding socialmedia-std-xl-base-1-0_emb to your prompt. For example, 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. (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', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='javeriahassan/socialmedia-std-xl-base-1-0', filename='socialmedia-std-xl-base-1-0_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('Design a promotional poster for AI chatbot integration services. The image should feature the text WARNER & SPENCER with a chatbot icon. Include bold text for AI CHATBOT and Integration Services, service details with checkmarks, and a Contact Us button on the left. A friendly chatbot graphic should be placed on the right side.').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.