metadata

tags:
  - text-to-image
  - flux
  - lora
  - diffusers
  - template:sd-lora
  - ai-toolkit
widget:
  - text: >-
      Tshirt Design, A cartoon image of a person juggling paintbrushes, gears,
      and lightbulbs, with the phrase "Embrace the Mess" written in playful,
      graffiti-style font. The background is a mix of vibrant splashes of paint
      and abstract doodles, representing creativity in action, tsdsign
    output:
      url: samples/1732548090228__000001000_0.jpg
  - text: >-
      Tshirt Design, A skeleton skateboarding through outer space, leaving a
      trail of colorful stardust behind. The words "Skate Through the Universe"
      wrap around the design in glowing, stylized font, tsdsign
    output:
      url: samples/1732548099417__000001000_1.jpg
base_model: black-forest-labs/FLUX.1-schnell
instance_prompt: tsdsign
license: apache-2.0

tshirt-design

Model trained with AI Toolkit by Ostris

Prompt
Tshirt Design, A skeleton skateboarding through outer space, leaving a trail of colorful stardust behind. The words "Skate Through the Universe" wrap around the design in glowing, stylized font, tsdsign

Trigger words

You should use tsdsign to trigger the image generation.

Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-schnell', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('dhanushreddy29/tshirt-design', weight_name='tshirt-design.safetensors')
image = pipeline('Tshirt Design, A cartoon image of a person juggling paintbrushes, gears, and lightbulbs, with the phrase "Embrace the Mess" written in playful, graffiti-style font. The background is a mix of vibrant splashes of paint and abstract doodles, representing creativity in action, tsdsign').images[0]
image.save("my_image.png")

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers