metadata

base_model: black-forest-labs/FLUX.1-schnell
license: apache-2.0
tags:
  - autotrain
  - spacerunner
  - text-to-image
  - flux
  - lora
  - diffusers
  - template:sd-lora
widget:
  - text: a pixel art of a closeup vew of a joker as a news anchor, balatrocard
    output:
      url: samples/02.png
  - text: >-
      a pixel art of a close up joker very angry, from the bottom, white
      background, balatrocard
    output:
      url: samples/10.png
  - text: a pixel art of sagrada familia in barcelona, balatrocard
    output:
      url: samples/04.png
instance_prompt: balatrocard

balatro-poker-cards

Model trained with 150 of 160 poker cards from the popular game 'Balatro'

Prompt
a pixel art of a closeup vew of a joker as a news anchor, balatrocard

Prompt
a pixel art of a close up joker very angry, from the bottom, white background, balatrocard

Prompt
a pixel art of sagrada familia in barcelona, balatrocard

Trigger words

You should use balatrocard to trigger the image generation. It's good to start the prompt with 'a pixel art of a.'

I created a template in Photoshop with the card border and the word 'JOKER' to make it more integrated.

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('Wakkamaruh/balatro-poker-cards', weight_name='balatro-poker-cards')
image = pipeline('a pixel art card of a samurai balatrocard').images[0]
image.save("my_image.png")

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