metadata

tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
widget:
  - text: graphis-01, bubble tea
    parameters:
      negative_prompt: text, watermark, ugly, messy, bad, photo
    output:
      url: images/graphis-01-01.jpg
  - text: graphis-01 a girl with black hair and big round glasses, bob cut hair
    parameters:
      negative_prompt: text, watermark, ugly, messy, bad, photo
    output:
      url: images/graphis-01-02.jpg
  - text: graphis-01 chicken
    parameters:
      negative_prompt: text, watermark, ugly, messy, bad, photo
    output:
      url: images/graphis-01-03.jpg
  - text: graphis-01 black and white cat
    parameters:
      negative_prompt: text, watermark, ugly, messy, bad, photo
    output:
      url: images/graphis-01-04.jpg
  - text: graphis-01 strawberry, red
    parameters:
      negative_prompt: text, watermark, ugly, messy, bad, photo
    output:
      url: images/graphis-01-05.jpg
  - text: graphis-01 cityscape at sunset
    parameters:
      negative_prompt: text, watermark, ugly, messy, bad, photo
    output:
      url: images/graphis-01-06.jpg
  - text: graphis-01 cityscape at sunset, girl, cyberpunk, synthwave
    parameters:
      negative_prompt: text, watermark, ugly, messy, bad, photo
    output:
      url: images/graphis-01-07.jpg
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: graphis-01
license: creativeml-openrail-m

Graphis-01

Prompt
graphis-01, bubble tea

Negative Prompt
text, watermark, ugly, messy, bad, photo

Prompt
graphis-01 girl, cyberpunk, synthwave

Negative Prompt
text, watermark, ugly, messy, bad, photo

Prompt
graphis-01 flower

Negative Prompt
text, watermark, ugly, messy, bad, photo

Prompt
graphis-01 golden gate bridge

Negative Prompt
text, watermark, ugly, messy, bad, photo

Model description

This is a fun model creates a graphic flat look with textural, grainy smooth fall off. This was trained using my custom dataset of digital illustrations of graphic shapes on various types of paper. Using the trigger word "graphis-01" will yield better results. Feel free to push the LoRA weighting to get different stylistic effects. Recommended between 0.6 - 1.6 (in ComfyUI).

Trigger words

You should use graphis-01 to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.