from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('rootonchair/2x2_sticker_sheet', weight_name='pytorch_lora_weights.safetensors', adapter_name='2x2_sticker_sheet')
pipeline.set_adapters(['2x2_sticker_sheet'], adapter_weights=[0.8])

image = pipeline('This set of four image depicts a cartoon black cat wearing a pirate hat; [IMAGE1] The cat is happy, holding a bouquet; [IMAGE2] The cat is happy, surrounded with music notes; [IMAGE3] The cat is riding a bicycle; [IMAGE4] The cat is eating an ice cream', width=512, height=512, num_inference_steps=28, guidance_scale=3.5).images[0]

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

License

Please adhere to the licensing terms as described here.

Trigger words

You should use This set of four image depicts a cartoon <subject>; [IMAGE1]; [IMAGE2]; [IMAGE3]; [IMAGE4] to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.