T-Shirt Vector Style - FLUX
<Gallery />
Model description
<p>Trigger word for this lora is <strong><em><span style="color:color(srgb 0.84 0.900784 0.900784)">5h1rt</span></em></strong><span style="color:color(srgb 0.84 0.900784 0.900784)"> </span><br /><span style="color:color(srgb 0.84 0.900784 0.900784)">it is best used like this at the end of the prompt, .."in the style of </span><strong><em><span style="color:color(srgb 0.84 0.900784 0.900784)">5h1rt"</span></em></strong></p><p>I highly recommend you word your prompt like so.. "tshirt design, (your prompt here), in the style of <strong><em><span style="color:color(srgb 0.84 0.900784 0.900784)">5h1rt</span></em></strong><span style="color:color(srgb 0.84 0.900784 0.900784)">"</span></p><p></p><p>This lora is intended to create vector like images with a solid color background for easily removing the background and printing it on a tshirt or any other items. <em>It is still experimental</em> and I am looking for ways to improve my dataset. It's best if you follow me so you get notifications if/when I release a second version of this..</p><p></p><p>I use <a target="_blank" rel="ugc" href="https://github.com/mcmonkeyprojects/SwarmUI">SwarmUI</a> for 95% of my image generations and encourage you to try it out! Here's the link to the OFFICAL<a target="_blank" rel="ugc" href="https://github.com/mcmonkeyprojects/SwarmUI"> GitHub repo </a>and also checkout this install video from Kleebz Tech AI to get you started!</p><div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/vIBTxUZL0Jc?si=nF9xlcBEBG_mwlbD" start="0"></iframe></div><p></p><p></p><p></p><p></p>
Trigger words
You should use 5h1rt to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
from diffusers import AutoPipelineForText2Image
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('SouthbayJay/t-shirt-vector-style-flux', weight_name='vector_shirt_flux_v1.safetensors')
image = pipeline('`5h1rt`').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers