These are Prgckwb/trpfrog-sdxl-lora LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using
DreamBooth.
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
You should use an icon of "trpfrog" to trigger the image generation.
1from diffusers import DiffusionPipeline
2import torch
3
4base_model_id = 'stabilityai/stable-diffusion-xl-base-1.0'
5lora_model_id = 'Prgckwb/trpfrog-sdxl-lora'
6
7pipe = DiffusionPipeline.from_pretrained(
8 base_model_id, torch_dtype=torch.float16
9).to("cuda")
10pipe.load_lora_weights(lora_model_id)
11
12image = pipe(
13 "an icon of trpfrog",
14 num_inference_steps=25
15).images[0]
16image.save('trpfrog.png')
